# Table of Contents - [FASHN Virtual Try-On V1.5 | Image to Image | fal.ai](#fashn-virtual-try-on-v1-5-image-to-image-fal-ai) - [fal.ai](#fal-ai) - [Unknown](#unknown) - [Pricing | fal.ai](#pricing-fal-ai) - [fal AI Demos](#fal-ai-demos) - [Login || fal.ai](#login-fal-ai) - [Train Flux LoRA | Training | fal.ai](#train-flux-lora-training-fal-ai) - [Careers at fal](#careers-at-fal) - [About Us - fal](#about-us-fal) - [Flux Realism | Unknown | fal.ai](#flux-realism-unknown-fal-ai) - [AuraFlow | Text to Image | fal.ai](#auraflow-text-to-image-fal-ai) - [FLUX.1 [schnell] | Text to Image | fal.ai](#flux-1-schnell-text-to-image-fal-ai) - [FLUX.1 [dev] | Text to Image | fal.ai](#flux-1-dev-text-to-image-fal-ai) - [FLUX.1 [dev] with LoRAs | Text to Image | fal.ai](#flux-1-dev-with-loras-text-to-image-fal-ai) - [Login || fal.ai](#login-fal-ai) - [fal.ai | The generative media platform for developers](#fal-ai-the-generative-media-platform-for-developers) - [Generative Media for Enterprise](#generative-media-for-enterprise) - [Model Gallery | fal.ai](#model-gallery-fal-ai) - [Login || fal.ai](#login-fal-ai) - [Email Protection | Cloudflare](#email-protection-cloudflare) - [Login || fal.ai](#login-fal-ai) --- # FASHN Virtual Try-On V1.5 | Image to Image | fal.ai [](/) [](/) [Docs](https://docs.fal.ai) [Blog](https://blog.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Careers](/careers) [Research Grants](/grants) [Log-in](/login?returnTo=/models/fal-ai/fashn/tryon/v1.5/api) [Sign-up](/login?returnTo=/models/fal-ai/fashn/tryon/v1.5/api) FASHN Virtual Try-On V1.5 Image to Image ======================================== fal-ai/fashn/tryon/v1.5 FASHN v1.5 delivers precise virtual try-on capabilities, accurately rendering garment details like text and patterns at 576x864 resolution from both on-model and flat-lay photo references. Inference Commercial use [Schema](/api/openapi/queue/openapi.json?endpoint_id=fal-ai/fashn/tryon/v1.5) [Playground](/models/fal-ai/fashn/tryon/v1.5/playground) [API](/models/fal-ai/fashn/tryon/v1.5/api) ### Table of contents JavaScript / Node.js [#### 1\. Calling the API](/models/fal-ai/fashn/tryon/v1.5/api#api-call) * [Install the client](/models/fal-ai/fashn/tryon/v1.5/api#api-call-install) * [Setup your API Key](/models/fal-ai/fashn/tryon/v1.5/api#api-call-setup) * [Submit a request](/models/fal-ai/fashn/tryon/v1.5/api#api-call-submit-request) [#### 2\. Authentication](/models/fal-ai/fashn/tryon/v1.5/api#auth) * [API Key](/models/fal-ai/fashn/tryon/v1.5/api#auth-api-key) [#### 3\. Queue](/models/fal-ai/fashn/tryon/v1.5/api#queue) * [Submit a request](/models/fal-ai/fashn/tryon/v1.5/api#queue-submit) * [Fetch request status](/models/fal-ai/fashn/tryon/v1.5/api#queue-status) * [Get the result](/models/fal-ai/fashn/tryon/v1.5/api#queue-result) [#### 4\. Files](/models/fal-ai/fashn/tryon/v1.5/api#files) * [Data URI (base64)](/models/fal-ai/fashn/tryon/v1.5/api#files-data-uri) * [Hosted files (URL)](/models/fal-ai/fashn/tryon/v1.5/api#files-from-url) * [Uploading files](/models/fal-ai/fashn/tryon/v1.5/api#files-upload) [#### 5\. Schema](/models/fal-ai/fashn/tryon/v1.5/api#schema) * [Input](/models/fal-ai/fashn/tryon/v1.5/api#schema-input) * [Output](/models/fal-ai/fashn/tryon/v1.5/api#schema-output) * [Other](/models/fal-ai/fashn/tryon/v1.5/api#schema-other) ### About Generate Image ### 1\. Calling the API[#](#api-call-install) ### Install the client[#](#api-call-install) The client provides a convenient way to interact with the model API. npmyarnpnpmbun npm install --save @fal-ai/client ##### Migrate to @fal-ai/client The `@fal-ai/serverless-client` package has been deprecated in favor of `@fal-ai/client`. Please check the [migration guide](https://docs.fal.ai/clients/javascript#migration-from-serverless-client-to-client) for more information. ### Setup your API Key[#](#api-call-setup) Set `FAL_KEY` as an environment variable in your runtime. export FAL_KEY="YOUR_API_KEY" ### Submit a request[#](#api-call-submit-request) The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed. import { fal } from "@fal-ai/client"; const result = await fal.subscribe("fal-ai/fashn/tryon/v1.5", { input: { model_image: "https://utfs.io/f/wXFHUNfTHmLj4prvqbRMQ6JXFyUr3IT0avK2HSOmZWiAsxg9", garment_image: "https://utfs.io/f/wXFHUNfTHmLjtkhepmqOUnkr8XxZbNIFmRWldShDLu320TeC" }, logs: true, onQueueUpdate: (update) => { if (update.status === "IN_PROGRESS") { update.logs.map((log) => log.message).forEach(console.log); } }, }); console.log(result.data); console.log(result.requestId); 2\. Authentication[#](#auth) ----------------------------- The API uses an API Key for authentication. It is recommended you set the `FAL_KEY` environment variable in your runtime when possible. ### API Key[#](#auth-api-key) In case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration. import { fal } from "@fal-ai/client"; fal.config({ credentials: "YOUR_FAL_KEY" }); ##### Protect your API Key When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your `FAL_KEY`. Instead, **use a server-side proxy** to make requests to the API. For more information, check out our [server-side integration guide](https://docs.fal.ai/model-endpoints/server-side) . 3\. Queue[#](#queue) --------------------- ##### Long-running requests For long-running requests, such as _training_ jobs or models with slower inference times, it is recommended to check the [Queue](https://docs.fal.ai/model-endpoints/queue) status and rely on [Webhooks](https://docs.fal.ai/model-endpoints/webhooks) instead of blocking while waiting for the result. ### Submit a request[#](#queue-submit) The client API provides a convenient way to submit requests to the model. import { fal } from "@fal-ai/client"; const { request_id } = await fal.queue.submit("fal-ai/fashn/tryon/v1.5", { input: { model_image: "https://utfs.io/f/wXFHUNfTHmLj4prvqbRMQ6JXFyUr3IT0avK2HSOmZWiAsxg9", garment_image: "https://utfs.io/f/wXFHUNfTHmLjtkhepmqOUnkr8XxZbNIFmRWldShDLu320TeC" }, webhookUrl: "https://optional.webhook.url/for/results", }); ### Fetch request status[#](#queue-status) You can fetch the status of a request to check if it is completed or still in progress. import { fal } from "@fal-ai/client"; const status = await fal.queue.status("fal-ai/fashn/tryon/v1.5", { requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b", logs: true, }); ### Get the result[#](#queue-result) Once the request is completed, you can fetch the result. See the [Output Schema](#schema-output) for the expected result format. import { fal } from "@fal-ai/client"; const result = await fal.queue.result("fal-ai/fashn/tryon/v1.5", { requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b" }); console.log(result.data); console.log(result.requestId); 4\. Files[#](#files) --------------------- Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI. ### Data URI (base64)[#](#files-data-uri) You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance. ### Hosted files (URL)[#](#files-from-url) You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot. ### Uploading files[#](#files-upload) We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests. import { fal } from "@fal-ai/client"; const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" }); const url = await fal.storage.upload(file); ##### Auto uploads The client will auto-upload the file for you if you pass a binary object (e.g. `File`, `Data`). Read more about file handling in our [file upload guide](https://docs.fal.ai/model-endpoints#file-uploads) . 5\. Schema[#](#schema) ----------------------- ### Input[#](#schema-input) `model_image` `string`\* required URL or base64 of the model image `garment_image` `string`\* required URL or base64 of the garment image `category` `CategoryEnum` Category of the garment to try-on. 'auto' will attempt to automatically detect the category of the garment. Default value: `"auto"` Possible enum values: `tops, bottoms, one-pieces, auto` `mode` `ModeEnum` Specifies the mode of operation. 'performance' mode is faster but may sacrifice quality, 'balanced' mode is a balance between speed and quality, and 'quality' mode is slower but produces higher quality results. Default value: `"balanced"` Possible enum values: `performance, balanced, quality` `garment_photo_type` `GarmentPhotoTypeEnum` Specifies the type of garment photo to optimize internal parameters for better performance. 'model' is for photos of garments on a model, 'flat-lay' is for flat-lay or ghost mannequin images, and 'auto' attempts to automatically detect the photo type. Default value: `"auto"` Possible enum values: `auto, model, flat-lay` `moderation_level` `ModerationLevelEnum` Content moderation level for garment images. 'none' disables moderation, 'permissive' blocks only explicit content, 'conservative' also blocks underwear and swimwear. Default value: `"permissive"` Possible enum values: `none, permissive, conservative` `seed` `integer` Sets random operations to a fixed state. Use the same seed to reproduce results with the same inputs, or different seed to force different results. Default value: `42` `num_samples` `integer` Number of images to generate in a single run. Image generation has a random element in it, so trying multiple images at once increases the chances of getting a good result. Default value: `1` `segmentation_free` `boolean` Disables human parsing on the model image. Default value: `true` { "model_image": "https://utfs.io/f/wXFHUNfTHmLj4prvqbRMQ6JXFyUr3IT0avK2HSOmZWiAsxg9", "garment_image": "https://utfs.io/f/wXFHUNfTHmLjtkhepmqOUnkr8XxZbNIFmRWldShDLu320TeC", "category": "auto", "mode": "balanced", "garment_photo_type": "auto", "moderation_level": "permissive", "seed": 42, "num_samples": 1, "segmentation_free": true } ### Output[#](#schema-output) `images` `list<[File](#type-File) >`\* required { "images": [\ {\ "url": "https://cdn.staging.fashn.ai/464eeeb1-4faa-4a2d-8c17-342d0d35c4c1/output_0.png"\ }\ ] } ### Other types[#](#schema-other) #### File[#](#type-File) `url` `string`\* required The URL where the file can be downloaded from. `content_type` `string` The mime type of the file. `file_name` `string` The name of the file. It will be auto-generated if not provided. `file_size` `integer` The size of the file in bytes. `file_data` `string` File data --- # fal.ai ![](/landing/bg-side-page.svg)![](/landing/bg-mobile-side-page.svg) [](/) [Model Gallery](/models) [Documentation](https://docs.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Research Grants](/grants) [Get started](/login) Grants ====== fal Research Grants ------------------- At fal, we believe in the power of open source projects to drive progress and support the AI community. That's why we've established the **fal Research Grants** program, which provides free compute resources to researchers and developers working on cutting-edge open source initiatives. Eligibility ----------- The **fal Research Grants** program is open to anyone passionate about advancing AI through open source projects. Whether you're a seasoned researcher or a self-taught developer, we welcome your applications. No formal degree is required - your ideas and dedication are what matter most. How to Apply ------------ To apply for a fal Research Grant, simply reach out to us at [\[email protected\]](/cdn-cgi/l/email-protection#6c0b1e0d02181f2c0a0d00420d05) . In your application, please include a description of your project, its goals, and how it aligns with our mission of fostering open source innovation in AI. Don't forget to share any relevant work or GitHub repositories that showcase your skills and enthusiasm. Testimonials ------------ "The fal Research Grant was a huge accelerator for my work on the Moondream project. Getting access to powerful compute helped accelerate training for features like high-resolution image processing and multi-object detection. This support has helped us improve the quality of the model and contribute effectively to the open-source community." \- Vik Korrapati, Author of Moondream "Thanks to the support from **fal Research Grants**, I could accelerate the implementation of my ideas and bring more of my innovation to the open-source community." \- Peng Zheng, Author of BiRefNet ### Join us in shaping the future of creativity. --- # Unknown {"openapi":"3.0.0","info":{"title":"Fal Queue API","version":"1.0.0","description":"The Fal Queue API."},"components":{"securitySchemes":{"apiKeyAuth":{"type":"apiKey","in":"header","name":"Authorization","description":"Fal Key"}},"schemas":{"QueueStatus":{"type":"object","properties":{"status":{"type":"string","enum":\["IN\_QUEUE","IN\_PROGRESS","COMPLETED"\]},"request\_id":{"type":"string","description":"The request id."},"response\_url":{"type":"string","description":"The response url."},"status\_url":{"type":"string","description":"The status url."},"cancel\_url":{"type":"string","description":"The cancel url."},"logs":{"type":"object","description":"The logs.","additionalProperties":true},"metrics":{"type":"object","description":"The metrics.","additionalProperties":true},"queue\_position":{"type":"integer","description":"The queue position."}},"required":\["status","request\_id"\]},"FashnTryonV15Input":{"title":"Input","type":"object","properties":{"model\_image":{"title":"Model Image","type":"string","description":"URL or base64 of the model image"},"moderation\_level":{"enum":\["none","permissive","conservative"\],"title":"Moderation Level","type":"string","description":"Content moderation level for garment images. 'none' disables moderation, 'permissive' blocks only explicit content, 'conservative' also blocks underwear and swimwear.","default":"permissive"},"garment\_photo\_type":{"enum":\["auto","model","flat-lay"\],"title":"Garment Photo Type","type":"string","description":"Specifies the type of garment photo to optimize internal parameters for better performance. 'model' is for photos of garments on a model, 'flat-lay' is for flat-lay or ghost mannequin images, and 'auto' attempts to automatically detect the photo type.","default":"auto"},"garment\_image":{"title":"Garment Image","type":"string","description":"URL or base64 of the garment image"},"category":{"enum":\["tops","bottoms","one-pieces","auto"\],"title":"Category","type":"string","description":"Category of the garment to try-on. 'auto' will attempt to automatically detect the category of the garment.","default":"auto"},"num\_samples":{"minimum":1,"maximum":4,"type":"integer","title":"Num Samples","description":"Number of images to generate in a single run. Image generation has a random element in it, so trying multiple images at once increases the chances of getting a good result.","default":1},"segmentation\_free":{"title":"Segmentation Free","type":"boolean","description":"Disables human parsing on the model image.","default":true},"mode":{"enum":\["performance","balanced","quality"\],"title":"Mode","type":"string","description":"Specifies the mode of operation. 'performance' mode is faster but may sacrifice quality, 'balanced' mode is a balance between speed and quality, and 'quality' mode is slower but produces higher quality results.","default":"balanced"},"seed":{"minimum":0,"maximum":4294967295,"type":"integer","title":"Seed","description":"Sets random operations to a fixed state. Use the same seed to reproduce results with the same inputs, or different seed to force different results.","default":42}},"x-fal-order-properties":\["model\_image","garment\_image","category","mode","garment\_photo\_type","moderation\_level","seed","num\_samples","segmentation\_free"\],"required":\["model\_image","garment\_image"\]},"FashnTryonV15Output":{"title":"Output","type":"object","properties":{"images":{"title":"Images","type":"array","items":{"$ref":"#/components/schemas/File"}}},"x-fal-order-properties":\["images"\],"required":\["images"\]},"File":{"title":"File","type":"object","properties":{"file\_size":{"title":"File Size","type":"integer","description":"The size of the file in bytes."},"file\_name":{"title":"File Name","type":"string","description":"The name of the file. It will be auto-generated if not provided."},"content\_type":{"title":"Content Type","type":"string","description":"The mime type of the file."},"url":{"title":"Url","type":"string","description":"The URL where the file can be downloaded from."},"file\_data":{"format":"binary","title":"File Data","type":"string","description":"File data"}},"x-fal-order-properties":\["url","content\_type","file\_name","file\_size","file\_data"\],"required":\["url"\]}}},"paths":{"/fal-ai/fashn/tryon/v1.5/requests/{request\_id}/status":{"get":{"parameters":\[{"name":"request\_id","in":"path","required":true,"schema":{"type":"string","description":"Request ID"}},{"name":"logs","in":"query","required":false,"schema":{"type":"number","description":"Whether to include logs (\`1\`) in the response or not (\`0\`)."}}\],"responses":{"200":{"description":"The request status.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/QueueStatus"}}}}}}},"/fal-ai/fashn/tryon/v1.5/requests/{request\_id}/cancel":{"put":{"parameters":\[{"name":"request\_id","in":"path","required":true,"schema":{"type":"string","description":"Request ID"}}\],"responses":{"200":{"description":"The request was cancelled.","content":{"application/json":{"schema":{"type":"object","properties":{"success":{"type":"boolean","description":"Whether the request was cancelled successfully."}}}}}}}}},"/fal-ai/fashn/tryon/v1.5":{"post":{"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/FashnTryonV15Input"}}}},"responses":{"200":{"description":"The request status.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/QueueStatus"}}}}}}},"/fal-ai/fashn/tryon/v1.5/requests/{request\_id}":{"get":{"parameters":\[{"name":"request\_id","in":"path","required":true,"schema":{"type":"string","description":"Request ID"}}\],"responses":{"200":{"description":"Result of the request.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/FashnTryonV15Output"}}}}}}}},"servers":\[{"url":"https://queue.fal.run"}\],"security":\[{"apiKeyAuth":\[\]}\]} --- # Pricing | fal.ai [](/) [](/) [Docs](https://docs.fal.ai) [Blog](https://blog.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Careers](/careers) [Research Grants](/grants) [Log-in](/login?returnTo=/pricing) [Sign-up](/login?returnTo=/pricing) ![](/landing/landing-left-1.webp)![](/landing/landing-right-1.webp) Pricing ======= #### Pricing ### Fast, reliable, and cost-efficient. fal.ai adapts to your usage, ensuring you only pay for the computing power you consume. It's cost-effective scalability at its best. For private serverless model pricing, please see our [enterprise pricing page](/enterprise#pricing) . ### API Billing Based on Compute Seconds Competitive pricing for custom deployments. Get H100s from from as low as $1.99/hr. Contact support, [\[email protected\]](/cdn-cgi/l/email-protection) , to get started. ![GPU H100 icon](/landing/fal-gpu-icon-green.svg) GPUH100 VRAM80GB Price per hour\*$1.99/h Price per second\*$0.0006/s ![GPU H200 icon](/landing/fal-gpu-icon-blue.svg) GPUH200 VRAM141GB Price per hour\*$2.10/h Price per second\*$0.0006/s ![GPU A100 icon](/landing/fal-gpu-icon-dark-blue.svg) GPUA100 VRAM40GB Price per hour\*$0.99/h Price per second\*$0.0003/s ![GPU A6000 icon](/landing/fal-gpu-icon-red.svg) GPUA6000 VRAM48GB Price per hour\*$0.60/h Price per second\*$0.0002/s ![GPU GPU-B200 icon](/landing/fal-gpu-icon-green.svg) GPUGPU-B200 VRAM192GB Price per hour\*contact us Price per second\*contact us \*starting at ### API Billing Based on Model Output Some models are billed by model output, instead of compute seconds. For more details, see each model page. | Model Name | Unit Price (USD) | | | --- | --- | --- | | [Veo 2 Image to Video](/models/fal-ai/veo2/image-to-video) | 0.25 per second | | | [Hunyuan Video](/models/fal-ai/hunyuan-video) | 0.4 per video | | | [Kling 1.6 Pro Video](/models/fal-ai/kling-video/v1.6/pro/text-to-video) | 0.095 per second of video | | | [Kling 2 Master Video](/models/fal-ai/kling-video/v2/master/image-to-video) | 0.28 per second of video | | | [Alibaba Wan Video](/models/fal-ai/wan-i2v) | 0.4 per video | | | [FLUX.1 \[dev\]](/models/fal-ai/flux/dev) | 0.025 per megapixel | | | [FLUX.1 \[schnell\]](/models/fal-ai/flux/schnell) | 0.003 per megapixel | | | [FLUX.1 \[pro\]](/models/fal-ai/flux-pro) | 0.05 per megapixel | | | [Stable Diffusion 3 - Medium](/models/fal-ai/stable-diffusion-v3-medium) | 0.035 per image | | | [Stable Video](/models/fal-ai/stable-video) | 0.075 per video | | | [MiniMax Video Live](/models/fal-ai/minimax/video-01-live) | 0.5 per video | | --- # fal AI Demos [](/) [](/) [Docs](https://docs.fal.ai) [Blog](https://blog.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Careers](/careers) [Research Grants](/grants) [Log-in](/login?returnTo=/demos) [Sign-up](/login?returnTo=/demos) Demo Gallery ------------ See all available demos provided by fal.ai [##### Face Control - Realtime\ \ Control the face of a character in real-time.](/demos/face-control) [##### Live Portrait - Realtime\ \ Turn live footage of yourself into an animated portrait of any character.](/demos/live-portrait) [##### Upscaler Arena\ \ A demo comparing different upscalers served by fal.ai](https://upscaler.party) [##### 3D Canvas\ \ A demo generating 3d assets from text descriptions.](https://3dcanvas.party) [##### Lightning\ \ Run SDXL at hyperspeed - API demo by fal.ai](/demos/fastsdxl) [##### Realtime Birefnet\ \ Realtime Birefnet - API demo by fal.ai](https://realtime-birefnet.vercel.app/) [##### Realtime Camera\ \ Turn live footage into artistic images or simulations at over 30+ fps.](/demos/camera) --- # Login || fal.ai ![](/landing/landing-left-1.webp)![](/landing/landing-right-1.webp) Log in to fal.ai ================ [Continue with GitHub](/api/auth/v2/connect/github?returnTo=/models/fal-ai/fashn/tryon/v1.5/api) Continue with SSO By clicking continue, you agree to our [Terms of Service](/terms.html) and [Privacy Policy](/privacy.html) ### Enterprise Single Sign-On Domain [Continue](/api/auth/connect/?returnTo=/models/fal-ai/fashn/tryon/v1.5/api) Back Do you want to become an enterprise customer with SSO login? [Contact us](/cdn-cgi/l/email-protection#c2b1a3aea7b182a4a3aeeca3ab) Don't have an account yet? [Sign up](/api/auth/v2/connect/github?returnTo=/models/fal-ai/fashn/tryon/v1.5/api) --- # Train Flux LoRA | Training | fal.ai [](/) [](/) [Docs](https://docs.fal.ai) [Blog](https://blog.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Careers](/careers) [Research Grants](/grants) [Log-in](/login?returnTo=/models/fal-ai/flux-lora-fast-training) [Sign-up](/login?returnTo=/models/fal-ai/flux-lora-fast-training) Train Flux LoRA Training ======================== fal-ai/flux-lora-fast-training Train styles, people and other subjects at blazing speeds. Training Commercial use [Schema](/api/openapi/queue/openapi.json?endpoint_id=fal-ai/flux-lora-fast-training) [Playground](/models/fal-ai/flux-lora-fast-training/playground) [API](/models/fal-ai/flux-lora-fast-training/api) ### Input Form Images Data Url\* Add ImageorPick a .zip file Trigger Word Is Style Additional Settings More Customize your input with more control. Reset[Sign in to run](/login?returnTo=/models/fal-ai/flux-lora-fast-training) Your request will cost **$2 per training run** (scales linearly with steps). For **$2** you can run this model with **approximately 1 times**. ### Training history [See all](/models/fal-ai/flux-lora-fast-training/requests) ##### Nothing here yet... Fine-tune your training parameters and start right now. **Note:** these are the most recent training requests. For the full history, check the requests tab. --- # Careers at fal ![](/landing/bg-side-page-red.svg)![](/landing/bg-mobile-side-page-red.svg) [](/) [Model Gallery](/models) [Documentation](https://docs.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Research Grants](/grants) [Get started](/login) Careers ======= ![](/about/left-1-red.svg) Hi there! We are fal, and we are on a mission to build world’s first generative media platform for developers. We built a serverless runtime for Python that is optimized to run large ML models on 1000s of GPUs efficiently. The applications built on our platform are currently serving millions of users around the world and our goal is to 1000x that over the next few years. To see some examples of our product in action, go to [our model gallery](/models) and [docs](/docs) fal was set up as a fully remote company from the start. Today, we are 20 people strong, distributed across the world. We are looking for founding team members who share our excitement about the fast moving nature of AI and can independently build world-class infrastructure. Let’s chat! ![](/about/left-2.svg) ![](/about/right-2.webp) Open Roles ---------- ### Staff Software Engineer, Compute You are an experienced software engineer who thrives on building large scale computation platforms. You have deep expertise in backend systems that orchestrate workloads and route requests efficiently, while taking care of capacity and resource constraints. You possess a strong understanding of foundational cloud infrastructure and Linux provisioning and management tools. You know how to achieve reliability and scale with minimum operational load. [Show more](/careers/staff-software-engineer-compute) ### Staff Software Engineer, ML Performance & Systems Help fal maintain its frontier position on model performance for generative media models. Design and implement novel approaches to model serving architecture on top of our in-house inference engine, focusing on maximizing throughput while minimizing latency and resource usage. Develop performance monitoring and profiling tools to identify bottlenecks and optimization opportunities. Work closely with our Applied ML team and customers (frontier labs on the media space) and make sure their workloads benefit from our accelerator. [Show more](/careers/staff-software-engineer-ml-performance-systems) ### Senior ML Researcher (Personalization) You are an ML engineer with expertise in technologies such as dreambooth and LoRA finetunes. You have experience in constructing pre-training pipelines to optimize outcomes. You are deeply concerned with training speed and likeness. You keep up with the latest papers from leading researchers and the most recent Comfyui workflows from the community. [Show more](/careers/senior-ml-researcher-personalization) ### Applied ML Engineer You are an ML engineer who excels at bridging cutting-edge research and real-world applications. You have hands-on experience training, deploying, and maintaining machine learning models, ensuring they perform at scale. You stay current with new developments in AI, but your focus is always on delivering impactful solutions in production environments. [Show more](/careers/applied-ml-engineer) ### Senior Account Executive You are a seasoned Account Executive with a proven track record of driving significant revenue growth in AI, SaaS, or technology startups. You excel at navigating complex sales cycles, building long-term relationships with enterprise customers, and leading strategic negotiations. By leveraging your deep understanding of AI infrastructure, you will help innovative organizations adopt fal's platform, amplify their capabilities, and shape the future of AI-powered media on a global scale. [Show more](/careers/senior-account-executive) ### Product Engineer You are a versatile engineer who thrives on building and deploying seamless user experiences. You possess a strong understanding of both backend and frontend technologies, enabling you to take ownership of features from concept to launch. You are proficient in crafting robust APIs, managing databases, and developing interactive user interfaces. Your focus is on delivering high-quality, scalable, and maintainable products. [Show more](/careers/product-engineer) ![](/about/right-4.webp) More Roles ---------- ### Researcher in Residence (3-Month Role) Are you an academic (Masters or PhD) with a passion for AI and computer vision? Or perhaps you're self-taught with impressive open-source contributions in the AI comp vision space? Whether you're free due to holidays, about to graduate, or looking to experience the industry, this role is for you. [Show more](/careers/researcher-in-residence) ### Customer Success Manager We're looking for a Customer Success Manager to lead customer engagement across a large and dynamic portfolio of customers. As a trusted advisor, you'll play a critical role in shaping how our customers bring AI-powered experiences to life. [Show more](/careers/customer-success-manager) ![](/about/right-3.svg) Careers ------- ### What we offer at fal * Interesting and challenging work * Competitive salary and equity * Employee-friendly equity terms (early exercise, extended exercise) * We are currently hiring in downtown San Francisco. We prefer to work in-person but we also offer remote work opportunities for exceptional candidates. * We offer visa sponsorship and will help you relocate to San Francisco. * Health, dental, and vision insurance (US) * Regular team events and offsites [Apply](https://jobs.ashbyhq.com/fal?employmentType=FullTime&locationId=228ca189-e0b1-4ef4-a63d-3c36721a58a4) --- # About Us - fal ![](/landing/bg-side-page.svg)![](/landing/bg-mobile-side-page.svg) [](/) [Model Gallery](/models) [Documentation](https://docs.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Research Grants](/grants) [Get started](/login) About Us ======== ![](/about/left-1.svg) Founded in 2021 by Burkay Gur and Gorkem Yurtseven, our company was born out of a shared passion for AI and a desire to address the challenges in AI infrastructure observed during their tenures at Coinbase and Amazon. Since then, we've achieved remarkable milestones, including developing the fastest inference for models like SDXL and Whisper. Our solutions now support hundreds of millions of customers, demonstrating our ability to serve at an impressive scale. Operating at the forefront of AI Inference, particularly in generative media, we empower developers to create the next generation of creativity tools. Our work facilitates easier access to AI's potential, enabling transformative experiences for consumers. We are backed by the best Silicon Valley investors and angels. We are headquartered in San Francisco, but our team spans the globe, comprised of the best global talent. ![](/about/right-1.webp) ![](/about/left-2.svg) ![](/about/right-2.webp) Our Mission ----------- Our mission is to amplify and expand human creativity. We recognize that the true potential of generative AI lies in its ability to revolutionize creative processes across various domains. However, slow inference speeds and high costs often hinder the seamless integration of these powerful models into real-world applications. By providing the fastest inference for generative models, we tackle these challenges head-on, making it possible for developers to create responsive, immersive, and cost-effective experiences. In a world where visual content reigns supreme, we firmly believe that generative AI for media represents the future. Our focus on optimizing inference speeds and efficiency not only enhances the end-user experience but also ensures that developers can build scalable applications, even amidst the current GPU shortage. Ultimately, our mission is to reduce the barriers to creative expression by making generative AI accessible to all. Just as recorded music empowered musicians and YouTube enabled video creators, we envision a future where our platform serves as a catalyst for a new generation of creators, unleashing their imagination and redefining the boundaries of what's possible. ![](/about/right-4.webp) Our Mission ----------- Bias towards action and hard workWe believe in taking initiative and moving quickly. Our team is driven by a proactive mindset, ensuring continuous progress. We care deeply about our work and each other, demonstrating our commitment through hard work and mutual support. Collaboration and growthWe foster an environment where everyones voice is heard. By listening to each other and promoting collaboration, we create a space where individuals can achieve their best work. We are dedicated to the growth and development of our team, encouraging continuous learning and personal advancement. Innovation and open source advocacyWe are passionate about developing cutting-edge technology and pushing the boundaries of AI. As strong advocates for open source, we believe that sharing knowledge and resources is essential for technological advancement and benefits the entire community. ![](/about/right-3.svg) Careers ------- ### See Open Positions fal.ai adapts to your usage, ensuring you only pay for the computing power you consume. It's cost-effective scalability at its best. [See open positions](/careers) --- # Flux Realism | Unknown | fal.ai [](/) [](/) [Docs](https://docs.fal.ai) [Blog](https://blog.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Careers](/careers) [Research Grants](/grants) [Log-in](/login?returnTo=/models/fal-ai/flux-realism) [Sign-up](/login?returnTo=/models/fal-ai/flux-realism) Flux Realism Unknown ==================== fal-ai/flux-realism Inference Private [Schema](/api/openapi/queue/openapi.json?endpoint_id=fal-ai/flux-realism) [Playground](/models/fal-ai/flux-realism/playground) [API](/models/fal-ai/flux-realism/api) ### Input Form Prompt\* A charismatic speaker is captured mid-speech. He has long, slightly wavy blonde hair tied back in a ponytail. His expressive face, adorned with a salt-and-pepper beard and mustache, is animated as he gestures with his left hand, displaying a large ring on his pinky finger. He is holding a black microphone in his right hand, speaking passionately. The man is wearing a dark, textured shirt with unique, slightly shimmering patterns, and a green lanyard with multiple badges and logos hanging around his neck. The lanyard features the "Autodesk" and "V-Ray" logos prominently. Behind him, there is a blurred background with a white banner containing logos and text, indicating a professional or conference setting. The overall scene is vibrant and dynamic, capturing the energy of a live presentation. Additional Settings More Customize your input with more control. Reset[Sign in to run](/login?returnTo=/models/fal-ai/flux-realism) ### Result Idle Preview Waiting for your input... { "images": [\ {\ "url": "",\ "content_type": "image/jpeg"\ }\ ], "prompt": "" } ### Logs Show --- # AuraFlow | Text to Image | fal.ai [](/) [](/) [Docs](https://docs.fal.ai) [Blog](https://blog.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Careers](/careers) [Research Grants](/grants) [Log-in](/login?returnTo=/models/fal-ai/aura-flow) [Sign-up](/login?returnTo=/models/fal-ai/aura-flow) AuraFlow Text to Image ====================== fal-ai/aura-flow AuraFlow v0.3 is an open-source flow-based text-to-image generation model that achieves state-of-the-art results on GenEval. The model is currently in beta. Inference Commercial use [Schema](/api/openapi/queue/openapi.json?endpoint_id=fal-ai/aura-flow) [Playground](/models/fal-ai/aura-flow/playground) [API](/models/fal-ai/aura-flow/api) [Examples](/models/fal-ai/aura-flow/examples) CreatorDev ### Input Form Prompt\* Close-up portrait of a majestic iguana with vibrant blue-green scales, piercing amber eyes, and orange spiky crest. Intricate textures and details visible on scaly skin. Wrapped in dark hood, giving regal appearance. Dramatic lighting against black background. Hyper-realistic, high-resolution image showcasing the reptile's expressive features and coloration. Additional Settings More Customize your input with more control. Reset Run⌘↵ ### Result Idle Preview Waiting for your input... { "images": [\ {\ "url": "",\ "content_type": "image/png",\ "file_name": "z9RV14K95DvU.png",\ "file_size": 4404019,\ "width": 1024,\ "height": 1024\ }\ ], "prompt": "" } Your request will cost $0.00111 per compute second. For $1 you can run this model approximately 901 times. ### Logs Show --- # FLUX.1 [schnell] | Text to Image | fal.ai [](/) [](/) [Docs](https://docs.fal.ai) [Blog](https://blog.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Careers](/careers) [Research Grants](/grants) [Log-in](/login?returnTo=/models/fal-ai/flux/schnell) [Sign-up](/login?returnTo=/models/fal-ai/flux/schnell) FLUX.1 \[schnell\] Text to Image ================================ fal-ai/flux/schnell Text to Image \[schnell\] FLUX.1 \[schnell\] is a 12 billion parameter flow transformer that generates high-quality images from text in 1 to 4 steps, suitable for personal and commercial use. Inference Commercial use [Schema](/api/openapi/queue/openapi.json?endpoint_id=fal-ai/flux/schnell) [Playground](/models/fal-ai/flux/schnell/playground) [API](/models/fal-ai/flux/schnell/api) [Examples](/models/fal-ai/flux/schnell/examples) CreatorDev ### Input Form Prompt\* Extreme close-up of a single tiger eye, direct frontal view. Detailed iris and pupil. Sharp focus on eye texture and color. Natural lighting to capture authentic eye shine and depth. The word "FLUX" is painted over it in big, white brush strokes with visible texture. Additional Settings More Customize your input with more control. Reset[Sign in to run](/login?returnTo=/models/fal-ai/flux/schnell) ### Result Idle Preview Waiting for your input... { "images": [\ {\ "url": "",\ "content_type": "image/jpeg"\ }\ ], "prompt": "" } Your request will cost $0.003 per megapixel. For $1 you can run this model approximately 333 times. Images are billed by rounding up to the nearest megapixel. ### Logs Show --- # FLUX.1 [dev] | Text to Image | fal.ai [](/) [](/) [Docs](https://docs.fal.ai) [Blog](https://blog.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Careers](/careers) [Research Grants](/grants) [Log-in](/login?returnTo=/models/fal-ai/flux/dev) [Sign-up](/login?returnTo=/models/fal-ai/flux/dev) FLUX.1 \[dev\] Text to Image ============================ fal-ai/flux/dev Text to Image \[dev\] FLUX.1 \[dev\] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use. Inference Commercial use Streaming [Schema](/api/openapi/queue/openapi.json?endpoint_id=fal-ai/flux/dev) [Playground](/models/fal-ai/flux/dev/playground) [API](/models/fal-ai/flux/dev/api) [Examples](/models/fal-ai/flux/dev/examples) CreatorDev ### Input Form Prompt\* Extreme close-up of a single tiger eye, direct frontal view. Detailed iris and pupil. Sharp focus on eye texture and color. Natural lighting to capture authentic eye shine and depth. The word "FLUX" is painted over it in big, white brush strokes with visible texture. Additional Settings More Customize your input with more control. Streaming Reset[Sign in to run](/login?returnTo=/models/fal-ai/flux/dev) ### Result Idle Preview Waiting for your input... { "images": [\ {\ "url": "",\ "content_type": "image/jpeg"\ }\ ], "prompt": "" } Your request will cost $0.025 per megapixel. For $1 you can run this model approximately 40 times. Images are billed by rounding up to the nearest megapixel. ### Logs Show --- # FLUX.1 [dev] with LoRAs | Text to Image | fal.ai [](/) [](/) [Docs](https://docs.fal.ai) [Blog](https://blog.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Careers](/careers) [Research Grants](/grants) [Log-in](/login?returnTo=/models/fal-ai/flux-lora) [Sign-up](/login?returnTo=/models/fal-ai/flux-lora) FLUX.1 \[dev\] with LoRAs Text to Image ======================================= fal-ai/flux-lora Text to Image Super fast endpoint for the FLUX.1 \[dev\] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs. Inference Commercial use [Schema](/api/openapi/queue/openapi.json?endpoint_id=fal-ai/flux-lora) Training [Playground](/models/fal-ai/flux-lora/playground) [API](/models/fal-ai/flux-lora/api) [Examples](/models/fal-ai/flux-lora/examples) CreatorDev ### Input Form Prompt\* Extreme close-up of a single tiger eye, direct frontal view. Detailed iris and pupil. Sharp focus on eye texture and color. Natural lighting to capture authentic eye shine and depth. The word "FLUX" is painted over it in big, white brush strokes with visible texture. Loras Add item Additional Settings More Customize your input with more control. Reset[Sign in to run](/login?returnTo=/models/fal-ai/flux-lora) ### Result Idle Preview Waiting for your input... { "images": [\ {\ "url": "",\ "content_type": "image/jpeg"\ }\ ], "prompt": "" } Your request will cost $0.035 per megapixel. For $1 you can run this model approximately 29 times. Images are billed by rounding up to the nearest megapixel. ### Logs Show --- # Login || fal.ai ![](/landing/landing-left-1.webp)![](/landing/landing-right-1.webp) Log in to fal.ai ================ [Continue with GitHub](/api/auth/v2/connect/github?returnTo=/workflows) Continue with SSO By clicking continue, you agree to our [Terms of Service](/terms.html) and [Privacy Policy](/privacy.html) ### Enterprise Single Sign-On Domain [Continue](/api/auth/connect/?returnTo=/workflows) Back Do you want to become an enterprise customer with SSO login? [Contact us](/cdn-cgi/l/email-protection#295a48454c5a694f4845074840) Don't have an account yet? [Sign up](/api/auth/v2/connect/github?returnTo=/workflows) --- # fal.ai | The generative media platform for developers ![](/landing/left-1.webp)![](/landing/left-3.svg) ![](/landing/right-2.webp)![](/landing/right-4.svg) [](/) [Model Gallery](/models) [Documentation](https://docs.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Research Grants](/grants) [Get started](/login) Generative media platform for developers. ============================================= Build the next generation of creativity with fal. Lightning fast inference. [Documentation](/docs) [Get started](/login) Peak performance, no compromise on quality. Access the highest quality generative media models. Optimized by the fal Inference Engine™. Model Gallery ------------- [Kling 2.0 Masterimage-to-video](/models/fal-ai/kling-video/v2/master/image-to-video) [Kling 1.6image-to-video](/models/fal-ai/kling-video/v1.6/pro/image-to-video) [Veo 2 (Image to Video)image-to-videomotiontransformation](/models/fal-ai/veo2/image-to-video) [MiniMax (Hailuo AI) Video 01 Liveimage-to-videomotiontransformation](/models/fal-ai/minimax/video-01-live/image-to-video) [Imagen3text-to-image](/models/fal-ai/imagen3) [FLUX.1 \[dev\]text-to-image](/models/fal-ai/flux/dev) [Recraft V3text-to-imagevectortypographystyle](/models/fal-ai/recraft-v3) [Train Flux LoRAtraininglorapersonalization](/models/fal-ai/flux-lora-fast-training) [Train Flux LoRAs For Portraitstraininglorapersonalization](/models/fal-ai/flux-lora-portrait-trainer) [AuraFlowtext-to-imagetypographystyle](/models/fal-ai/aura-flow) [Explore more models](/models) ![](/landing/right-3.webp)![](/landing/right-3-1.webp)![](/landing/right-m-3-1.webp)![](/landing/right-3-2.webp) fal0.0s alternative 1 0.0s alternative 20.0s flux\[dev\] inference speed fal Inference Engine™ is the fastest way to run diffusion models Run diffusion models up to 4x faster. Enable new user experiences leveraging our real time infrastructure. Features -------- Where developer experience meets the fastest AI. ![](/landing/feature-3.webp) ### Inference for Your Private Diffusion Model If you are training your own diffusion transformer model, we would like to partner with you to run inference on your model. fal's inference engine can run your model up to 50% faster and cost effective. Scale to thousands of GPUs when needed and pay only for what you use. ![](/landing/feature-2.webp) ### Blazing Fast Inference Engine for Diffusion Models We have built world's fastest inference engine for diffusion models. We can run the FLUX models up to 400% faster than other alternatives. [Fine-tune your own models](https://fal.ai/models/fal-ai/flux-lora-fast-training) ### Best LoRA Trainer In the Industry for Flux fal's head of AI research, Simo Ryu, was the first to implement LoRAs for diffusion models. We now bring you the best LoRA trainer for FLUX. You can personalize or train a new style in less than 5 minutes. JavaScriptPythonSwift import { fal } from "@fal-ai/client"; const result = await fal.subscribe("fal-ai/fast-sdxl", { input: { prompt: "photo of a cat wearing a kimono" }, logs: true, onQueueUpdate: (update) => { if (update.status === "IN_PROGRESS") { update.logs.map((log) => log.message).forEach(console.log); } }, }); ### World class developer experience Use one of our client libraries to integrate fal directly into your applications. #### Pricing ### Fast, reliable, and cost-efficient. fal.ai adapts to your usage, ensuring you only pay for the computing power you consume. It's cost-effective scalability at its best. Competitive pricing for custom deployments. Get H100s from from as low as $1.99/hr. Contact support, [\[email protected\]](/cdn-cgi/l/email-protection) , to get started. ![GPU H100 icon](/landing/fal-gpu-icon-green.svg) GPUH100 VRAM80GB Price per hour\*$1.99/h Price per second\*$0.0006/s ![GPU H200 icon](/landing/fal-gpu-icon-blue.svg) GPUH200 VRAM141GB Price per hour\*$2.10/h Price per second\*$0.0006/s ![GPU A100 icon](/landing/fal-gpu-icon-dark-blue.svg) GPUA100 VRAM40GB Price per hour\*$0.99/h Price per second\*$0.0003/s ![GPU A6000 icon](/landing/fal-gpu-icon-red.svg) GPUA6000 VRAM48GB Price per hour\*$0.60/h Price per second\*$0.0002/s ![GPU GPU-B200 icon](/landing/fal-gpu-icon-green.svg) GPUGPU-B200 VRAM192GB Price per hour\*contact us Price per second\*contact us \*starting at Some models have custom pricing, for more details please see our [pricing page](/pricing) . [View all pricing](/pricing) --- # Generative Media for Enterprise [](/) [](/) [Docs](https://docs.fal.ai) [Blog](https://blog.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Careers](/careers) [Research Grants](/grants) [Log-in](/login?returnTo=/enterprise) [Sign-up](/login?returnTo=/enterprise) ![](/landing/landing-left-1.webp)![](/landing/landing-right-1.webp) Generative Media for Enterprise =============================== fal Enterprise provides fast, reliable APIs for AI-powered image, video, and audio generation at scale. We offer the infrastructure and expertise to implement and scale your AI projects efficiently. [Documentation](/docs) [Contact Sales](/enterprise#cta) Customer Highlights[#](#customer-highlights) --------------------------------------------- [PlayAI and falPlayAI creates voice models for text-to-speech applications, helping businesses integrate lifelike TTS into content creation, consumer apps, voice agents, and customer support solutions with high reliability and low latency.](/customer-case/playai-and-fal "PlayAI and fal") [Quora Poe and falPoe is Quora's AI hub, making advanced AI models accessible and user-friendly for everyone, similar to how web browsers democratized internet access.](/customer-case/quora-poe-and-fal "Quora Poe and fal") [Genspark and falGenspark is a platform that allows you to build and deploy autonomous AI agents.](/customer-case/genspark-and-fal "Genspark and fal") [Hedra and falHedra is a platform that redefines video creation, aiming to be the go-to solution for turning raw ideas into high-quality content. It makes professional-grade video production accessible to all, without the need for technical expertise or pre-made assets.](/customer-case/hedra-and-fal "Hedra and fal") Enterprise Solutions[#](#solutions) ------------------------------------ ### Powerful Generative Media APIs Create, manipulate, and optimize media at scale. Support for custom fine-tunes, LoRAs, ControlNets, and more. Ideal for cutting-edge AI-driven content creation and personalization. ![](/landing/feature-1.webp) ### Private Model Hosting Host your proprietary models securely on our infrastructure. Collaborate with our ML Engineers to co-develop models. Ensure data privacy and model exclusivity. ![](/landing/feature-3.webp) ### Inference and Training Kernels Custom optimization for your specific use cases. Our team writes bespoke kernels to maximize performance. Significantly improve inference speed and training efficiency. ![](/landing/feature-2.webp) ### Foundational Model Research Ground-up development of custom models. Tailored to your unique business requirements. Leverage our expertise to create proprietary AI solutions. ![](/fal-icon.svg) ### SOC2 Certification Security and privacy measures that aligns with legal and strategic needs of your company. Learn more about fal's compliance posture [trust.fal.ai](https://trust.fal.ai) ![SOC Icon](/landing/soc.webp) Ready to Transform Your Enterprise with AI?[#](#cta) ----------------------------------------------------- Take the first step towards AI-driven innovation. Our team of ML engineers is ready to help you prototype, develop, and scale your AI solutions. Name Email Company Message Submit [Request a Demo](/cdn-cgi/l/email-protection#780b19141d0b381e1914561911470b0d1a121d1b0c453c1d15175d4a482a1d090d1d0b0c5d4a481e170a5d4a483e39345d4a483d160c1d0a080a110b1d5e191508431a171c0145301d1414175d4a3b5d48395d4839315e5b004a4f43155d4a4811160c1d0a1d0b0c1d1c5d4a4811165d4a480b1b101d1c0d1411161f5d4a48195d4a481c1d15175d4a481e170a5d4a483e39345d4a483d160c1d0a080a110b1d565d48395d48393b1715081916015d4b395d4a485d48393619151d5d4b395d4a485d48392a17141d5d4b395d4a485d48395d48392c101916135d4a4801170d56) [Contact Sales](/cdn-cgi/l/email-protection#e093818c8593a086818cce8189df9395828a858394ddb3818c8593c5d2d0a98e9195899299c5d2d0868f92c5d2d0a6a1acc5d2d0a58e9485929092899385c6818d90db828f8499dda8858c8c8fc5d2a3c5d0a1c5d0a1a9c6c398d2d7db8dc5d2d0898e9485928593948584c5d2d0898ec5d2d08c8581928e898e87c5d2d08d8f9285c5d2d081828f9594c5d2d0a6a1acc5d2d0a58e9485929092899385c5d2d0938f8c9594898f8e93cec5d0a1c5d0a1a38f8d90818e99c5d3a1c5d2d0c5d0a1ae818d85c5d3a1c5d2d0c5d0a1b28f8c85c5d3a1c5d2d0c5d0a1c5d0a1b488818e8bc5d2d0998f95ce) ### Increased Data Privacy Your data stays yours, period. We never train our LLMs on our enterprise customers' data. We ensure that all data is handled with the highest level of security and privacy. Our infrastructure is designed to protect your data from unauthorized access and breaches. ### Enhanced Security Manage threats and prevent data loss with real-time notifications of suspicious behavior or risky activities. Our advanced security systems continuously monitor your data and provide instant alerts to ensure that any potential threats are addressed promptly. This proactive approach helps to safeguard your enterprise's sensitive information and maintain the integrity of your operations. ### User Management Add, remove, and manage team members easily. Our user management system allows you to control access, assign roles, and monitor activities of your team members, ensuring that everyone has the appropriate permissions and access to the resources they need. ### Single Sign-On (SSO) Securely integrate with your identity provider and enable users to log in with SSO. This simplifies the login process for your team, enhances security by centralizing authentication, and reduces the risk of password-related breaches. Our SSO integration supports various identity providers, ensuring a seamless and secure user experience. Pricing[#](#pricing) --------------------- Competitive pricing for custom deployments. Get H100s from from as low as $1.99/hr. Contact support, [\[email protected\]](/cdn-cgi/l/email-protection) , to get started. ![GPU H100 icon](/landing/fal-gpu-icon-green.svg) GPUH100 VRAM80GB Price per hour\*$1.99/h Price per second\*$0.0006/s ![GPU H200 icon](/landing/fal-gpu-icon-blue.svg) GPUH200 VRAM141GB Price per hour\*$2.10/h Price per second\*$0.0006/s ![GPU A100 icon](/landing/fal-gpu-icon-dark-blue.svg) GPUA100 VRAM40GB Price per hour\*$0.99/h Price per second\*$0.0003/s ![GPU A6000 icon](/landing/fal-gpu-icon-red.svg) GPUA6000 VRAM48GB Price per hour\*$0.60/h Price per second\*$0.0002/s ![GPU GPU-B200 icon](/landing/fal-gpu-icon-green.svg) GPUGPU-B200 VRAM192GB Price per hour\*contact us Price per second\*contact us \*starting at Enterprise-Ready Models[#](#models) ------------------------------------ Production-ready models with enterprise-grade SLAs and support. [FLUX1.1 \[pro\]FLUX1.1 \[pro\] is an enhanced version of FLUX.1 \[pro\], improved image generation capabilities, delivering superior composition, detail, and artistic fidelity compared to its predecessor.\ \ text-to-image](/models/fal-ai/flux-pro/v1.1 "FLUX1.1 [pro]") [Stable Diffusion 3.5 LargeStable Diffusion 3.5 Large is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.\ \ text-to-image\ \ diffusion\ \ typography\ \ style](/models/fal-ai/stable-diffusion-v35-large "Stable Diffusion 3.5 Large") [Mochi 1Mochi 1 preview is an open state-of-the-art video generation model with high-fidelity motion and strong prompt adherence in preliminary evaluation.\ \ text-to-video](/models/fal-ai/mochi-v1 "Mochi 1") [MiniMax (Hailuo AI) Video 01Generate video clips from your prompts using MiniMax model\ \ text-to-video\ \ motion\ \ transformation](/models/fal-ai/minimax/video-01 "MiniMax (Hailuo AI) Video 01") --- # Model Gallery | fal.ai [](/) [](/) [Docs](https://docs.fal.ai) [Blog](https://blog.fal.ai) [Pricing](/pricing) [Enterprise](/enterprise) [Careers](/careers) [Research Grants](/grants) [Log-in](/login?returnTo=/models) [Sign-up](/login?returnTo=/models) Model Gallery ------------- See all available model APIs provided by fal.ai Can't find a model?[Suggest a model](https://discord.gg/fal-ai) ### Kling 2.0 Master New Kling models are here! You can generate video clips from your prompts or images using Kling 2.0 with exceptional quality, realism, and control. [Try it!](/models/fal-ai/kling-video/v2/master/image-to-video) ### Search trends [Video models\ \ 121](/models?keywords=video) [Audio models\ \ 40](/models?keywords=audio) [Training\ \ 7](/models?categories=training) [Upscalers\ \ 11](/models?keywords=upscale) [Flux\ \ 48](/models?keywords=flux) [Background Removal\ \ 7](/models?keywords=remove) [Product Photography\ \ 5](/models?keywords=product) Featured Models --------------- Check out some of our most popular models Sort byMost relevant [fal-ai/kling-video/v2/master/image-to-video\ \ image-to-video\ \ Generate video clips from your images using Kling 2.0 Master\ \ new](/models/fal-ai/kling-video/v2/master/image-to-video) [fal-ai/wan-effects\ \ image-to-video\ \ Wan Effects generates high-quality videos with popular effects from images\ \ motion\ \ effects](/models/fal-ai/wan-effects) [fal-ai/wan-pro/image-to-video\ \ image-to-video\ \ Wan-2.1 Pro is a premium image-to-video model that generates high-quality 1080p videos at 30fps with up to 6 seconds duration, delivering exceptional visual quality and motion diversity from images\ \ image to video\ \ motion](/models/fal-ai/wan-pro/image-to-video) [fal-ai/veo2/image-to-video\ \ image-to-video\ \ Veo 2 creates videos from images with realistic motion and very high quality output.\ \ motion\ \ transformation](/models/fal-ai/veo2/image-to-video) [fal-ai/wan-i2v\ \ image-to-video\ \ Wan-2.1 is a image-to-video model that generates high-quality videos with high visual quality and motion diversity from images\ \ image to video\ \ motion](/models/fal-ai/wan-i2v) [fal-ai/kling-video/v1.6/pro/image-to-video\ \ image-to-video\ \ Generate video clips from your images using Kling 1.6 (pro)](/models/fal-ai/kling-video/v1.6/pro/image-to-video) [fal-ai/flux-lora-fast-training\ \ training\ \ Train styles, people and other subjects at blazing speeds.\ \ lora\ \ personalization](/models/fal-ai/flux-lora-fast-training) [fal-ai/playai/tts/dialog\ \ text-to-audio\ \ Generate natural-sounding multi-speaker dialogues, and audio. Perfect for expressive outputs, storytelling, games, animations, and interactive media.\ \ audio](/models/fal-ai/playai/tts/dialog) [fal-ai/flux-pro/v1.1-ultra\ \ text-to-image\ \ FLUX1.1 \[pro\] ultra is the newest version of FLUX1.1 \[pro\], maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism.\ \ high-res\ \ realism](/models/fal-ai/flux-pro/v1.1-ultra) ### All Models Explore all available models provided by fal.ai [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/recraft-v3\ \ text-to-image\ \ Recraft V3 is a text-to-image model with the ability to generate long texts, vector art, images in brand style, and much more. As of today, it is SOTA in image generation, proven by Hugging Face's industry-leading Text-to-Image Benchmark by Artificial Analysis.\ \ vector\ \ typography\ \ style](/models/fal-ai/recraft-v3) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/minimax/video-01/image-to-video\ \ image-to-video\ \ Generate video clips from your images using MiniMax Video model\ \ motion\ \ transformation](/models/fal-ai/minimax/video-01/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/tavus/hummingbird-lipsync/v0\ \ video-to-video\ \ Generate lip sync using Tavus' state-of-the-art model for high-quality synchronization.\ \ new](/models/fal-ai/tavus/hummingbird-lipsync/v0) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/v2/master/text-to-video\ \ text-to-video\ \ Generate video clips from your prompts using Kling 2.0 Master\ \ new](/models/fal-ai/kling-video/v2/master/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hidream-i1-full\ \ text-to-image\ \ HiDream-I1 full is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.\ \ new](/models/fal-ai/hidream-i1-full) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hidream-i1-dev\ \ text-to-image\ \ HiDream-I1 dev is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.\ \ new](/models/fal-ai/hidream-i1-dev) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hidream-i1-fast\ \ text-to-image\ \ HiDream-I1 fast is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within 16 steps.\ \ new](/models/fal-ai/hidream-i1-fast) [![background texture](/assets/models/pixel-texture.svg)\ \ cassetteai/video-sound-effects-generator\ \ video-to-video\ \ Add sound effects to your videos\ \ new\ \ sound-effects\ \ sfx\ \ cassetteai](/models/cassetteai/video-sound-effects-generator) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux/dev\ \ text-to-image\ \ FLUX.1 \[dev\] is a 12 billion parameter flow transformer that generates high-quality images from text. It is suitable for personal and commercial use.\ \ new](/models/fal-ai/flux/dev) [![background texture](/assets/models/pixel-texture.svg)\ \ cassetteai/music-generator\ \ text-to-audio\ \ CassetteAI’s model generates a 30-second sample in under 2 seconds and a full 3-minute track in under 10 seconds. At 44.1 kHz stereo audio, expect a level of professional consistency with no breaks, no squeaks, and no random interruptions in your creations.\ \ new\ \ music\ \ cassetteai](/models/cassetteai/music-generator) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/mmaudio-v2\ \ video-to-video\ \ MMAudio generates synchronized audio given video and/or text inputs. It can be combined with video models to get videos with audio.\ \ ai video\ \ fast](/models/fal-ai/mmaudio-v2) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ideogram/v2\ \ text-to-image\ \ Generate high-quality images, posters, and logos with Ideogram V2. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.\ \ realism\ \ typography](/models/fal-ai/ideogram/v2) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-lora-portrait-trainer\ \ training\ \ FLUX LoRA training optimized for portrait generation, with bright highlights, excellent prompt following and highly detailed results.\ \ lora\ \ personalization](/models/fal-ai/flux-lora-portrait-trainer) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/stable-diffusion-v35-large\ \ text-to-image\ \ Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.\ \ diffusion\ \ typography\ \ style](/models/fal-ai/stable-diffusion-v35-large) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-lora/inpainting\ \ text-to-image\ \ Super fast endpoint for the FLUX.1 \[dev\] inpainting model with LoRA support, enabling rapid and high-quality image inpaingting using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.\ \ lora\ \ personalization](/models/fal-ai/flux-lora/inpainting) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-general\ \ text-to-image\ \ A versatile endpoint for the FLUX.1 \[dev\] model that supports multiple AI extensions including LoRA, ControlNet conditioning, and IP-Adapter integration, enabling comprehensive control over image generation through various guidance methods.\ \ lora\ \ controlnet\ \ ip-adapter](/models/fal-ai/flux-general) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-lora\ \ text-to-image\ \ Super fast endpoint for the FLUX.1 \[dev\] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.\ \ lora\ \ personalization](/models/fal-ai/flux-lora) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux/dev/image-to-image\ \ image-to-image\ \ FLUX.1 Image-to-Image is a high-performance endpoint for the FLUX.1 \[dev\] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.\ \ style transfer](/models/fal-ai/flux/dev/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/aura-sr\ \ image-to-image\ \ Upscale your images with AuraSR.\ \ upscaling\ \ high-res](/models/fal-ai/aura-sr) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/clarity-upscaler\ \ image-to-image\ \ Clarity upscaler for upscaling images with high very fidelity.\ \ upscaling](/models/fal-ai/clarity-upscaler) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/gpt-image-1/edit-image/byok\ \ image-to-image\ \ OpenAI's latest image generation and editing model: gpt-1-image. Currently powered with bring-your-own-key.\ \ new](/models/fal-ai/gpt-image-1/edit-image/byok) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/gpt-image-1/text-to-image/byok\ \ text-to-image\ \ OpenAI's latest image generation and editing model: gpt-1-image. Currently powered with bring-your-own-key.\ \ new](/models/fal-ai/gpt-image-1/text-to-image/byok) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pixverse/v4/effects\ \ image-to-video\ \ Generate high quality video clips with different effects using PixVerse v4\ \ new\ \ image-to-video](/models/fal-ai/pixverse/v4/effects) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/magi-distilled/extend-video\ \ video-to-video\ \ MAGI-1 extends videos with an exceptional understanding of physical interactions and prompts\ \ new\ \ video-to-video\ \ video-extend](/models/fal-ai/magi-distilled/extend-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/magi-distilled/image-to-video\ \ image-to-video\ \ MAGI-1 generates videos from images with exceptional understanding of physical interactions and prompting\ \ new\ \ image-to-video](/models/fal-ai/magi-distilled/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/dia-tts/voice-clone\ \ audio-to-audio\ \ Clone dialog voices from a sample audio and generate dialogs from text prompts using the Dia TTS which leverages advanced AI techniques to create high-quality text-to-speech.\ \ new\ \ speech](/models/fal-ai/dia-tts/voice-clone) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/minimax-image/subject-reference\ \ image-to-image\ \ Generate images from text and a reference image using MiniMax Image-01 for consistent character appearance.\ \ new\ \ stylized\ \ transform](/models/fal-ai/minimax-image/subject-reference) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/dia-tts\ \ text-to-speech\ \ Dria directly generates realistic dialogue from transcripts. Audio conditioning enables emotion control. Produces natural nonverbals like laughter and throat clearing.\ \ new\ \ text-to-speech](/models/fal-ai/dia-tts) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/magi-distilled\ \ text-to-video\ \ MAGI-1 is a video generation model with exceptional understanding of physical interactions and cinematic prompts\ \ new\ \ text-to-video](/models/fal-ai/magi-distilled) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/smart-turn\ \ speech-to-text\ \ An open source, community-driven and native audio turn detection model by Pipecat AI.\ \ new](/models/fal-ai/smart-turn) [![background texture](/assets/models/pixel-texture.svg)\ \ rundiffusion-fal/juggernaut-flux-lora/inpainting\ \ image-to-image\ \ Juggernaut Base Flux LoRA Inpainting by RunDiffusion is a drop-in replacement for Flux \[Dev\] inpainting that delivers sharper details, richer colors, and enhanced realism to all your LoRAs and LyCORIS with full compatibility.\ \ new](/models/rundiffusion-fal/juggernaut-flux-lora/inpainting) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fashn/tryon/v1.5\ \ image-to-image\ \ FASHN v1.5 delivers precise virtual try-on capabilities, accurately rendering garment details like text and patterns at 576x864 resolution from both on-model and flat-lay photo references.\ \ new\ \ try-on\ \ fashion\ \ clothing](/models/fal-ai/fashn/tryon/v1.5) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/plushify\ \ image-to-image\ \ Turn any image into a cute plushie!\ \ new](/models/fal-ai/plushify) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/instant-character\ \ image-to-image\ \ InstantCharacter creates high-quality, consistent characters from text prompts, supporting diverse poses, styles, and appearances with strong identity control.\ \ new\ \ personalization\ \ customization](/models/fal-ai/instant-character) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/wan-flf2v\ \ image-to-video\ \ Wan-2.1 flf2v generates dynamic videos by intelligently bridging a given first frame to a desired end frame through smooth, coherent motion sequences.\ \ new\ \ image to video\ \ motion](/models/fal-ai/wan-flf2v) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/turbo-flux-trainer\ \ training\ \ A blazing fast FLUX dev LoRA trainer for subjects and styles.\ \ new](/models/fal-ai/turbo-flux-trainer) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/framepack\ \ image-to-video\ \ Framepack is an efficient Image-to-video model that autoregressively generates videos.\ \ new\ \ image to video\ \ motion](/models/fal-ai/framepack) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/cartoonify\ \ image-to-image\ \ Transform images into 3D cartoon artwork using an AI model that applies cartoon stylization while preserving the original image's composition and details.\ \ new\ \ stylized\ \ transform](/models/fal-ai/cartoonify) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/wan-vace\ \ video-to-video\ \ Vace a video generation model that uses a source image, mask, and video to create prompted videos with controllable sources.\ \ new\ \ video-to-video\ \ image-to-video\ \ text-to-video](/models/fal-ai/wan-vace) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/finegrain-eraser/mask\ \ image-to-image\ \ Finegrain Eraser removes any object selected with a mask—along with its shadows, reflections, and lighting artifacts—seamlessly reconstructing the scene with contextually accurate content.\ \ new\ \ utility\ \ editing](/models/fal-ai/finegrain-eraser/mask) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/finegrain-eraser/bbox\ \ image-to-image\ \ Finegrain Eraser removes any object selected with a bounding box—along with its shadows, reflections, and lighting artifacts—seamlessly reconstructing the scene with contextually accurate content.\ \ new\ \ utility\ \ editing](/models/fal-ai/finegrain-eraser/bbox) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/finegrain-eraser\ \ image-to-image\ \ Finegrain Eraser removes objects—along with their shadows, reflections, and lighting artifacts—using only natural language, seamlessly filling the scene with contextually accurate content.\ \ new\ \ utility\ \ editing](/models/fal-ai/finegrain-eraser) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/speech-to-text/turbo\ \ speech-to-text\ \ Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.\ \ new](/models/fal-ai/speech-to-text/turbo) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/speech-to-text/turbo/stream\ \ speech-to-text\ \ Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.\ \ new\ \ streaming](/models/fal-ai/speech-to-text/turbo/stream) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/speech-to-text/stream\ \ speech-to-text\ \ Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.\ \ new\ \ streaming](/models/fal-ai/speech-to-text/stream) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/speech-to-text\ \ speech-to-text\ \ Leverage the rapid processing capabilities of AI models to enable accurate and efficient real-time speech-to-text transcription.\ \ new](/models/fal-ai/speech-to-text) [![background texture](/assets/models/pixel-texture.svg)\ \ cassetteai/sound-effects-generator\ \ text-to-audio\ \ Create stunningly realistic sound effects in seconds - CassetteAI's Sound Effects Model generates high-quality SFX up to 30 seconds long in just 1 second of processing time\ \ new\ \ sound\ \ sfx\ \ sound-effects\ \ cassetteai](/models/cassetteai/sound-effects-generator) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sync-lipsync/v2\ \ video-to-video\ \ Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization with Sync Lipsync 2.0 model\ \ new\ \ animation\ \ lip sync](/models/fal-ai/sync-lipsync/v2) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/star-vector\ \ image-to-image\ \ AI vectorization model that transforms raster images into scalable SVG graphics, preserving visual details while enabling infinite scaling and easy editing capabilities.\ \ new\ \ image-to-image](/models/fal-ai/star-vector) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pixverse/v4/image-to-video/fast\ \ image-to-video\ \ Generate fast high quality video clips from text and image prompts using PixVerse v4\ \ new](/models/fal-ai/pixverse/v4/image-to-video/fast) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pixverse/v4/image-to-video\ \ image-to-video\ \ Generate high quality video clips from text and image prompts using PixVerse v4\ \ new](/models/fal-ai/pixverse/v4/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pixverse/v3.5/effects\ \ image-to-video\ \ Generate high quality video clips with different effects using PixVerse v3.5\ \ new](/models/fal-ai/pixverse/v3.5/effects) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pixverse/v4/text-to-video\ \ text-to-video\ \ Generate high quality video clips from text and image prompts using PixVerse v4\ \ new](/models/fal-ai/pixverse/v4/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pixverse/v3.5/transition\ \ image-to-video\ \ Create seamless transition between images using PixVerse v3.5\ \ new](/models/fal-ai/pixverse/v3.5/transition) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pixverse/v4/text-to-video/fast\ \ text-to-video\ \ Generate high quality and fast video clips from text and image prompts using PixVerse v4 fast\ \ new](/models/fal-ai/pixverse/v4/text-to-video/fast) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ghiblify\ \ image-to-image\ \ Reimagine and transform your ordinary photos into enchanting Studio Ghibli style artwork\ \ new\ \ stylized\ \ transform](/models/fal-ai/ghiblify) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/minimax-tts/voice-clone\ \ text-to-speech\ \ Clone a voice from a sample audio and generate speech from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality text-to-speech.\ \ new\ \ speech](/models/fal-ai/minimax-tts/voice-clone) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/minimax-tts/text-to-speech/turbo\ \ text-to-speech\ \ Generate fast speech from text prompts and different voices using the MiniMax Speech-02 Turbo model, which leverages advanced AI techniques to create high-quality text-to-speech.\ \ new\ \ speech](/models/fal-ai/minimax-tts/text-to-speech/turbo) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/minimax-tts/text-to-speech\ \ text-to-speech\ \ Generate speech from text prompts and different voices using the MiniMax Speech-02 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.\ \ new\ \ speech](/models/fal-ai/minimax-tts/text-to-speech) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/orpheus-tts\ \ text-to-speech\ \ Orpheus TTS is a state-of-the-art, Llama-based Speech-LLM designed for high-quality, empathetic text-to-speech generation. This model has been finetuned to deliver human-level speech synthesis, achieving exceptional clarity, expressiveness, and real-time performances.\ \ new\ \ text to speech\ \ voice synthesis\ \ high-fidelity](/models/fal-ai/orpheus-tts) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sana/sprint\ \ text-to-image\ \ Sana Sprint is a text-to-image model capable of generating 4K images with exceptional speed.\ \ new\ \ text to image\ \ 4k\ \ high-speed](/models/fal-ai/sana/sprint) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sana/v1.5/4.8b\ \ text-to-image\ \ Sana v1.5 4.8B is a powerful text-to-image model that generates ultra-high quality 4K images with remarkable detail.\ \ new\ \ text to image\ \ 4k\ \ high-quality](/models/fal-ai/sana/v1.5/4.8b) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sana/v1.5/1.6b\ \ text-to-image\ \ Sana v1.5 1.6B is a lightweight text-to-image model that delivers 4K image generation with impressive efficiency.\ \ new\ \ text to image\ \ 4k\ \ lightweight](/models/fal-ai/sana/v1.5/1.6b) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/lipsync/audio-to-video\ \ text-to-video\ \ Kling LipSync is an audio-to-video model that generates realistic lip movements from audio input.\ \ new\ \ audio to video\ \ lipsync](/models/fal-ai/kling-video/lipsync/audio-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/lipsync/text-to-video\ \ text-to-video\ \ Kling LipSync is a text-to-video model that generates realistic lip movements from text input.\ \ new\ \ text to video\ \ lipsync](/models/fal-ai/kling-video/lipsync/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/latentsync\ \ video-to-video\ \ LatentSync is a video-to-video model that generates lip sync animations from audio using advanced algorithms for high-quality synchronization.\ \ animation\ \ lip sync](/models/fal-ai/latentsync) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/wan-t2v-lora\ \ text-to-video\ \ Add custom LoRAs to Wan-2.1 is a text-to-video model that generates high-quality videos with high visual quality and motion diversity from images\ \ "text to video"\ \ "motion"\ \ "lora"](/models/fal-ai/wan-t2v-lora) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/wan-trainer\ \ training\ \ Train custom LoRAs for Wan-2.1\ \ lora\ \ training](/models/fal-ai/wan-trainer) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/thera\ \ image-to-image\ \ Fix low resolution images with fast speed and quality of thera.](/models/fal-ai/thera) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/mix-dehaze-net\ \ image-to-image\ \ An advanced dehaze model to remove atmospheric haze, restoring clarity and detail in images through intelligent neural network processing.](/models/fal-ai/mix-dehaze-net) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/gemini-flash-edit/multi\ \ image-to-image\ \ Gemini Flash Edit Multi Image is a model that can edit multiple images using a text prompt and a reference image.\ \ editing](/models/fal-ai/gemini-flash-edit/multi) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hunyuan3d/v2\ \ image-to-3d\ \ Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.\ \ stylized](/models/fal-ai/hunyuan3d/v2) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hunyuan3d/v2/mini\ \ image-to-3d\ \ Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.\ \ stylized](/models/fal-ai/hunyuan3d/v2/mini) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hunyuan3d/v2/multi-view\ \ image-to-3d\ \ Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.\ \ stylized](/models/fal-ai/hunyuan3d/v2/multi-view) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hunyuan3d/v2/mini/turbo\ \ image-to-3d\ \ Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.\ \ stylized](/models/fal-ai/hunyuan3d/v2/mini/turbo) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hunyuan3d/v2/turbo\ \ image-to-3d\ \ Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.\ \ stylized](/models/fal-ai/hunyuan3d/v2/turbo) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/gemini-flash-edit\ \ image-to-image\ \ Gemini Flash Edit is a model that can edit single image using a text prompt and a reference image.\ \ editing](/models/fal-ai/gemini-flash-edit) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hunyuan3d/v2/multi-view/turbo\ \ image-to-3d\ \ Generate 3D models from your images using Hunyuan 3D. A native 3D generative model enabling versatile and high-quality 3D asset creation.\ \ stylized](/models/fal-ai/hunyuan3d/v2/multi-view/turbo) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/luma-dream-machine/ray-2-flash/image-to-video\ \ image-to-video\ \ Ray2 Flash is a fast video generative model capable of creating realistic visuals with natural, coherent motion.\ \ motion\ \ transformation](/models/fal-ai/luma-dream-machine/ray-2-flash/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/luma-dream-machine/ray-2-flash\ \ text-to-video\ \ Ray2 Flash is a fast video generative model capable of creating realistic visuals with natural, coherent motion.\ \ motion\ \ transformation](/models/fal-ai/luma-dream-machine/ray-2-flash) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pika/v2/turbo/image-to-video\ \ image-to-video\ \ Pika v2 Turbo creates videos from images with high quality output.\ \ editing\ \ effects\ \ animation](/models/fal-ai/pika/v2/turbo/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pika/v2.1/text-to-video\ \ text-to-video\ \ Pika v2.1 creates videos from a text prompt with high quality output.\ \ editing\ \ effects\ \ animation](/models/fal-ai/pika/v2.1/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pika/v1.5/pikaffects\ \ image-to-video\ \ Pika Effects are AI-powered video effects designed to modify objects, characters, and environments in a fun, engaging, and visually compelling manner.\ \ editing\ \ effects\ \ animation](/models/fal-ai/pika/v1.5/pikaffects) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pika/v2/turbo/text-to-video\ \ text-to-video\ \ Pika v2 Turbo creates videos from a text prompt with high quality output.\ \ editing\ \ effects\ \ animation](/models/fal-ai/pika/v2/turbo/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pika/v2.1/image-to-video\ \ image-to-video\ \ Pika v2.1 creates videos from images with high quality output.\ \ editing\ \ effects\ \ animation](/models/fal-ai/pika/v2.1/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pika/v2.2/image-to-video\ \ image-to-video\ \ Pika v2.2 creates videos from images with high quality output.\ \ editing\ \ effects\ \ animation](/models/fal-ai/pika/v2.2/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pika/v2.2/text-to-video\ \ text-to-video\ \ Pika v2.2 creates videos from a text prompt with high quality output.\ \ editing\ \ effects\ \ animation](/models/fal-ai/pika/v2.2/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pika/v2.2/pikascenes\ \ image-to-video\ \ Pika Scenes v2.2 creates videos from a images with high quality output.\ \ editing\ \ effects\ \ animation](/models/fal-ai/pika/v2.2/pikascenes) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/invisible-watermark\ \ image-to-image\ \ Invisible Watermark is a model that can add an invisible watermark to an image.\ \ utility\ \ editing](/models/fal-ai/invisible-watermark) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/csm-1b\ \ text-to-audio\ \ CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs.\ \ conversational\ \ text to speech](/models/fal-ai/csm-1b) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/vidu/start-end-to-video\ \ image-to-video\ \ Vidu Start-End to Video generates smooth transition videos between specified start and end images.\ \ motion\ \ transition](/models/fal-ai/vidu/start-end-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/vidu/template-to-video\ \ image-to-video\ \ Vidu Template to Video lets you create different effects by applying motion templates to your images.\ \ motion\ \ template](/models/fal-ai/vidu/template-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/vidu/image-to-video\ \ image-to-video\ \ Vidu Image to Video generates high-quality videos with exceptional visual quality and motion diversity from a single image\ \ motion\ \ image to video](/models/fal-ai/vidu/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/vidu/reference-to-video\ \ image-to-video\ \ Vidu Reference to Video creates videos by using a reference images and combining them with a prompt.\ \ motion\ \ reference](/models/fal-ai/vidu/reference-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/wan-pro/text-to-video\ \ text-to-video\ \ Wan-2.1 Pro is a premium text-to-video model that generates high-quality 1080p videos at 30fps with up to 6 seconds duration, delivering exceptional visual quality and motion diversity from text prompts\ \ text to video\ \ motion](/models/fal-ai/wan-pro/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ easel-ai/advanced-face-swap\ \ image-to-image\ \ Swap faces of one or two people at once, while preserving user and scene details!\ \ face swap\ \ utility\ \ editing](/models/easel-ai/advanced-face-swap) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/v1/standard/effects\ \ text-to-video\ \ Generate video clips from your prompts using Kling 1.0\ \ motion](/models/fal-ai/kling-video/v1/standard/effects) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/minimax-image\ \ text-to-image\ \ Generate high quality images from text prompts using MiniMax Image-01. Longer text prompts will result in better quality images.\ \ stylized\ \ realism](/models/fal-ai/minimax-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/v1.6/standard/effects\ \ text-to-video\ \ Generate video clips from your prompts using Kling 1.6 (std)](/models/fal-ai/kling-video/v1.6/standard/effects) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/v1.5/pro/effects\ \ text-to-video\ \ Generate video clips from your prompts using Kling 1.5 (pro)](/models/fal-ai/kling-video/v1.5/pro/effects) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/v1.6/pro/effects\ \ text-to-video\ \ Generate video clips from your prompts using Kling 1.6 (pro)](/models/fal-ai/kling-video/v1.6/pro/effects) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hunyuan-video-image-to-video\ \ image-to-video\ \ Image to Video for the high-quality Hunyuan Video I2V model.\ \ motion](/models/fal-ai/hunyuan-video-image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ rundiffusion-fal/juggernaut-flux/pro\ \ text-to-image\ \ Juggernaut Pro Flux by RunDiffusion is the flagship Juggernaut model rivaling some of the most advanced image models available, often surpassing them in realism. It combines Juggernaut Base with RunDiffusion Photo and features enhancements like reduced background blurriness.\ \ image generation](/models/rundiffusion-fal/juggernaut-flux/pro) [![background texture](/assets/models/pixel-texture.svg)\ \ rundiffusion-fal/juggernaut-flux/lightning\ \ text-to-image\ \ Juggernaut Lightning Flux by RunDiffusion provides blazing-fast, high-quality images rendered at five times the speed of Flux. Perfect for mood boards and mass ideation, this model excels in both realism and prompt adherence.\ \ image generation](/models/rundiffusion-fal/juggernaut-flux/lightning) [![background texture](/assets/models/pixel-texture.svg)\ \ rundiffusion-fal/juggernaut-flux/pro/image-to-image\ \ image-to-image\ \ Juggernaut Pro Flux by RunDiffusion is the flagship Juggernaut model rivaling some of the most advanced image models available, often surpassing them in realism. It combines Juggernaut Base with RunDiffusion Photo and features enhancements like reduced background blurriness.\ \ image generation](/models/rundiffusion-fal/juggernaut-flux/pro/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ltx-video-v095/image-to-video\ \ image-to-video\ \ Generate videos from prompts and images using LTX Video-0.9.5\ \ video\ \ image-to-video](/models/fal-ai/ltx-video-v095/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ rundiffusion-fal/juggernaut-flux/base\ \ text-to-image\ \ Juggernaut Base Flux by RunDiffusion is a drop-in replacement for Flux \[Dev\] that delivers sharper details, richer colors, and enhanced realism, while instantly boosting LoRAs and LyCORIS with full compatibility.\ \ image generation](/models/rundiffusion-fal/juggernaut-flux/base) [![background texture](/assets/models/pixel-texture.svg)\ \ rundiffusion-fal/rundiffusion-photo-flux\ \ text-to-image\ \ RunDiffusion Photo Flux provides insane realism. With this enhancer, textures and skin details burst to life, turning your favorite prompts into vivid, lifelike creations. Recommended to keep it at 0.65 to 0.80 weight. Supports resolutions up to 1536x1536.\ \ image generation\ \ lora](/models/rundiffusion-fal/rundiffusion-photo-flux) [![background texture](/assets/models/pixel-texture.svg)\ \ rundiffusion-fal/juggernaut-flux-lora\ \ text-to-image\ \ Juggernaut Base Flux LoRA by RunDiffusion is a drop-in replacement for Flux \[Dev\] that delivers sharper details, richer colors, and enhanced realism to all your LoRAs and LyCORIS with full compatibility.\ \ image generation](/models/rundiffusion-fal/juggernaut-flux-lora) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ltx-video-v095/extend\ \ video-to-video\ \ Generate videos from prompts and videos using LTX Video-0.9.5\ \ video\ \ video-to-video](/models/fal-ai/ltx-video-v095/extend) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ltx-video-v095\ \ text-to-video\ \ Generate videos from prompts using LTX Video-0.9.5\ \ video\ \ text-video](/models/fal-ai/ltx-video-v095) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ltx-video-v095/multiconditioning\ \ video-to-video\ \ Generate videos from prompts,images, and videos using LTX Video-0.9.5\ \ video\ \ image-to-video\ \ text-to-video](/models/fal-ai/ltx-video-v095/multiconditioning) [![background texture](/assets/models/pixel-texture.svg)\ \ rundiffusion-fal/juggernaut-flux/base/image-to-image\ \ image-to-image\ \ Juggernaut Base Flux by RunDiffusion is a drop-in replacement for Flux \[Dev\] that delivers sharper details, richer colors, and enhanced realism, while instantly boosting LoRAs and LyCORIS with full compatibility.\ \ image generation](/models/rundiffusion-fal/juggernaut-flux/base/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/cogview4\ \ text-to-image\ \ Generate high quality images from text prompts using CogView4. Longer text prompts will result in better quality images.\ \ stylized](/models/fal-ai/cogview4) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/eye-correct\ \ video-to-video\ \ Eye Correct is a video-to-video model that can correct eye direction in videos. It can be used to correct eye direction in videos.\ \ utility\ \ editing\ \ faces](/models/fal-ai/eye-correct) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/diffrhythm\ \ text-to-audio\ \ DiffRhythm is a blazing fast model for transforming lyrics into full songs. It boasts the capability to generate full songs in less than 30 seconds.\ \ music](/models/fal-ai/diffrhythm) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/topaz/upscale/video\ \ video-to-video\ \ Professional-grade video upscaling using Topaz technology. Enhance your videos with high-quality upscaling.\ \ upscaling\ \ high-res](/models/fal-ai/topaz/upscale/video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/docres/dewarp\ \ image-to-image\ \ Enhance wraped, folded documents with the superior quality of docres for sharper, clearer results.\ \ image-enhancement](/models/fal-ai/docres/dewarp) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/docres\ \ image-to-image\ \ Enhance low-resolution, blur, shadowed documents with the superior quality of docres for sharper, clearer results.\ \ image-enhancement](/models/fal-ai/docres) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/swin2sr\ \ image-to-image\ \ Enhance low-resolution images with the superior quality of Swin2SR for sharper, clearer results.\ \ image-enhancement](/models/fal-ai/swin2sr) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/v1.6/pro/text-to-video\ \ text-to-video\ \ Generate video clips from your prompts using Kling 1.6 (pro)](/models/fal-ai/kling-video/v1.6/pro/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/wan/v2.1/1.3b/text-to-video\ \ text-to-video\ \ Wan-2.1 1.3B is a text-to-video model that generates high-quality videos with high visual quality and motion diversity from text promptsat faster speeds.\ \ text to video\ \ motion](/models/fal-ai/wan/v2.1/1.3b/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ideogram/v2a/turbo/remix\ \ image-to-image\ \ Rapidly create image variations with Ideogram V2A Turbo Remix. Fast and efficient reimagining of existing images while maintaining creative control through prompt guidance.\ \ realism\ \ typography](/models/fal-ai/ideogram/v2a/turbo/remix) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/elevenlabs/speech-to-text\ \ speech-to-text\ \ Generate text from speech using ElevenLabs advanced speech-to-text model.\ \ speech](/models/fal-ai/elevenlabs/speech-to-text) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/elevenlabs/audio-isolation\ \ audio-to-audio\ \ Isolate audio tracks using ElevenLabs advanced audio isolation technology.\ \ audio](/models/fal-ai/elevenlabs/audio-isolation) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/elevenlabs/sound-effects\ \ text-to-audio\ \ Generate sound effects using ElevenLabs advanced sound effects model.\ \ sound](/models/fal-ai/elevenlabs/sound-effects) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ideogram/v2a/turbo\ \ text-to-image\ \ Accelerated image generation with Ideogram V2A Turbo. Create high-quality visuals, posters, and logos with enhanced speed while maintaining Ideogram's signature quality.\ \ realism\ \ typography](/models/fal-ai/ideogram/v2a/turbo) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/elevenlabs/tts/multilingual-v2\ \ text-to-audio\ \ Generate multilingual text-to-speech audio using ElevenLabs TTS Multilingual v2.\ \ audio](/models/fal-ai/elevenlabs/tts/multilingual-v2) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ideogram/v2a\ \ text-to-image\ \ Generate high-quality images, posters, and logos with Ideogram V2A. Features exceptional typography handling and realistic outputs optimized for commercial and creative use.\ \ realism\ \ typography](/models/fal-ai/ideogram/v2a) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/elevenlabs/tts/turbo-v2.5\ \ text-to-speech\ \ Generate high-speed text-to-speech audio using ElevenLabs TTS Turbo v2.5.\ \ audio](/models/fal-ai/elevenlabs/tts/turbo-v2.5) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ideogram/v2a/remix\ \ image-to-image\ \ Create variations of existing images with Ideogram V2A Remix while maintaining creative control through prompt guidance.\ \ realism\ \ typography](/models/fal-ai/ideogram/v2a/remix) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/evf-sam\ \ image-to-image\ \ EVF-SAM2 combines natural language understanding with advanced segmentation capabilities, allowing you to precisely mask image regions using intuitive positive and negative text prompts.\ \ segmentation\ \ mask](/models/fal-ai/evf-sam) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ddcolor\ \ image-to-image\ \ Bring colors into old or new black and white photos with DDColor.\ \ image-recolorization\ \ faces\ \ utility](/models/fal-ai/ddcolor) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sam2/auto-segment\ \ image-to-image\ \ SAM 2 is a model for segmenting images automatically. It can return individual masks or a single mask for the entire image.\ \ segmentation\ \ mask](/models/fal-ai/sam2/auto-segment) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/video-prompt-generator\ \ llm\ \ Generate video prompts using a variety of techniques including camera direction, style, pacing, special effects and more.\ \ motion\ \ transformation\ \ chat\ \ claude\ \ gpt](/models/fal-ai/video-prompt-generator) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/wan-t2v\ \ text-to-video\ \ Wan-2.1 is a text-to-video model that generates high-quality videos with high visual quality and motion diversity from text prompts\ \ text to video\ \ motion](/models/fal-ai/wan-t2v) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/minimax/video-01-director/image-to-video\ \ image-to-video\ \ Generate video clips more accurately with respect to initial image, natural language descriptions, and using camera movement instructions for shot control.\ \ motion\ \ transformation\ \ camera-controls](/models/fal-ai/minimax/video-01-director/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/drct-super-resolution\ \ image-to-image\ \ Upscale your images with DRCT-Super-Resolution.\ \ upscaling\ \ high-res](/models/fal-ai/drct-super-resolution) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/veo2\ \ text-to-video\ \ Veo 2 creates videos with realistic motion and high quality output. Explore different styles and find your own with extensive camera controls.\ \ motion\ \ transformation](/models/fal-ai/veo2) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/nafnet/denoise\ \ image-to-image\ \ Use NAFNet to fix issues like blurriness and noise in your images. This model specializes in image restoration and can help enhance the overall quality of your photography.\ \ image-restoration\ \ deblur\ \ denoise](/models/fal-ai/nafnet/denoise) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/nafnet/deblur\ \ image-to-image\ \ Use NAFNet to fix issues like blurriness and noise in your images. This model specializes in image restoration and can help enhance the overall quality of your photography.\ \ image-restoration\ \ deblur\ \ denoise](/models/fal-ai/nafnet/deblur) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/post-processing\ \ image-to-image\ \ Post Processing is an endpoint that can enhance images using a variety of techniques including grain, blur, sharpen, and more.\ \ stylized\ \ utility](/models/fal-ai/post-processing) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/skyreels-i2v\ \ image-to-video\ \ SkyReels V1 is the first and most advanced open-source human-centric video foundation model. By fine-tuning HunyuanVideo on O(10M) high-quality film and television clips\ \ motion](/models/fal-ai/skyreels-i2v) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/stepfun-video\ \ text-to-video\ \ Step-Video is a state-of-the-art (SoTA) text-to-video pre-trained model with 30 billion parameters and the capability to generate videos up to 204 frames.\ \ motion](/models/fal-ai/stepfun-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kokoro/mandarin-chinese\ \ text-to-audio\ \ A highly efficient Mandarin Chinese text-to-speech model that captures natural tones and prosody.\ \ speech](/models/fal-ai/kokoro/mandarin-chinese) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/zonos\ \ text-to-audio\ \ Clone voice of any person and speak anything in their voice using zonos' voice cloning.\ \ voice cloning](/models/fal-ai/zonos) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kokoro/british-english\ \ text-to-audio\ \ A high-quality British English text-to-speech model offering natural and expressive voice synthesis.\ \ speech](/models/fal-ai/kokoro/british-english) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kokoro/hindi\ \ text-to-audio\ \ A fast and expressive Hindi text-to-speech model with clear pronunciation and accurate intonation.\ \ speech](/models/fal-ai/kokoro/hindi) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kokoro/spanish\ \ text-to-audio\ \ A natural-sounding Spanish text-to-speech model optimized for Latin American and European Spanish.\ \ speech](/models/fal-ai/kokoro/spanish) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kokoro/brazilian-portuguese\ \ text-to-audio\ \ A natural and expressive Brazilian Portuguese text-to-speech model optimized for clarity and fluency.\ \ speech](/models/fal-ai/kokoro/brazilian-portuguese) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kokoro/american-english\ \ text-to-audio\ \ Kokoro is a lightweight text-to-speech model that delivers comparable quality to larger models while being significantly faster and more cost-efficient.\ \ speech](/models/fal-ai/kokoro/american-english) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kokoro/italian\ \ text-to-audio\ \ A high-quality Italian text-to-speech model delivering smooth and expressive speech synthesis.\ \ speech](/models/fal-ai/kokoro/italian) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flowedit\ \ text-to-image\ \ The model provides you high quality image editing capabilities.\ \ editing](/models/fal-ai/flowedit) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kokoro/japanese\ \ text-to-audio\ \ A fast and natural-sounding Japanese text-to-speech model optimized for smooth pronunciation.\ \ speech](/models/fal-ai/kokoro/japanese) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/luma-dream-machine/ray-2/image-to-video\ \ image-to-video\ \ Ray2 is a large-scale video generative model capable of creating realistic visuals with natural, coherent motion.\ \ motion\ \ transformation](/models/fal-ai/luma-dream-machine/ray-2/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kokoro/french\ \ text-to-audio\ \ An expressive and natural French text-to-speech model for both European and Canadian French.\ \ speech](/models/fal-ai/kokoro/french) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/got-ocr/v2\ \ vision\ \ GOT-OCR2 works on a wide range of tasks, including plain document OCR, scene text OCR, formatted document OCR, and even OCR for tables, charts, mathematical formulas, geometric shapes, molecular formulas and sheet music.\ \ optical character recognition\ \ high-res\ \ utility](/models/fal-ai/got-ocr/v2) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ben/v2/video\ \ video-to-video\ \ A model for high quality and smooth background removal for videos.\ \ segmentation\ \ background removal](/models/fal-ai/ben/v2/video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/minimax/video-01-director\ \ text-to-video\ \ Generate video clips more accurately with respect to natural language descriptions and using camera movement instructions for shot control.\ \ motion\ \ transformation\ \ camera-controls](/models/fal-ai/minimax/video-01-director) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-control-lora-canny\ \ text-to-image\ \ FLUX Control LoRA Canny is a high-performance endpoint that uses a control image to transfer structure to the generated image, using a Canny edge map.\ \ lora\ \ style transfer](/models/fal-ai/flux-control-lora-canny) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-control-lora-depth\ \ text-to-image\ \ FLUX Control LoRA Depth is a high-performance endpoint that uses a control image to transfer structure to the generated image, using a depth map.\ \ lora\ \ style transfer](/models/fal-ai/flux-control-lora-depth) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-control-lora-canny/image-to-image\ \ image-to-image\ \ FLUX Control LoRA Canny is a high-performance endpoint that uses a control image using a Canny edge map to transfer structure to the generated image and another initial image to guide color.\ \ lora\ \ style transfer](/models/fal-ai/flux-control-lora-canny/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-control-lora-depth/image-to-image\ \ image-to-image\ \ FLUX Control LoRA Depth is a high-performance endpoint that uses a control image using a depth map to transfer structure to the generated image and another initial image to guide color.\ \ lora\ \ style transfer](/models/fal-ai/flux-control-lora-depth/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ben/v2/image\ \ image-to-image\ \ A fast and high quality model for image background removal.\ \ background removal](/models/fal-ai/ben/v2/image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/imagen3/fast\ \ text-to-image\ \ Imagen3 Fast is a high-quality text-to-image model that generates realistic images from text prompts.](/models/fal-ai/imagen3/fast) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ideogram/upscale\ \ image-to-image\ \ Ideogram Upscale enhances the resolution of the reference image by up to 2X and might enhance the reference image too. Optionally refine outputs with a prompt for guided improvements.\ \ upscaling\ \ high-res](/models/fal-ai/ideogram/upscale) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/imagen3\ \ text-to-image\ \ Imagen3 is a high-quality text-to-image model that generates realistic images from text prompts.](/models/fal-ai/imagen3) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hunyuan-video-img2vid-lora\ \ image-to-video\ \ Image to Video for the Hunyuan Video model using a custom trained LoRA.\ \ motion](/models/fal-ai/hunyuan-video-img2vid-lora) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/lumina-image/v2\ \ text-to-image\ \ Lumina-Image-2.0 is a 2 billion parameter flow-based diffusion transforer which features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.\ \ diffusion\ \ typography\ \ style](/models/fal-ai/lumina-image/v2) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/codeformer\ \ image-to-image\ \ Fix distorted or blurred photos of people with CodeFormer.\ \ image-restoration\ \ faces\ \ utility](/models/fal-ai/codeformer) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hunyuan-video-lora/video-to-video\ \ video-to-video\ \ Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. Use this endpoint to generate videos from videos.\ \ video to video\ \ motion\ \ lora](/models/fal-ai/hunyuan-video-lora/video-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hunyuan-video/video-to-video\ \ video-to-video\ \ Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. Use this endpoint to generate videos from videos.\ \ video to video\ \ motion](/models/fal-ai/hunyuan-video/video-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pixverse/v3.5/text-to-video/fast\ \ text-to-video\ \ Generate high quality video clips quickly from text prompts using PixVerse v3.5 Fast](/models/fal-ai/pixverse/v3.5/text-to-video/fast) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pixverse/v3.5/text-to-video\ \ text-to-video\ \ Generate high quality video clips from text prompts using PixVerse v3.5](/models/fal-ai/pixverse/v3.5/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pixverse/v3.5/image-to-video/fast\ \ image-to-video\ \ Generate high quality video clips from text and image prompts quickly using PixVerse v3.5 Fast](/models/fal-ai/pixverse/v3.5/image-to-video/fast) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pixverse/v3.5/image-to-video\ \ image-to-video\ \ Generate high quality video clips from text and image prompts using PixVerse v3.5](/models/fal-ai/pixverse/v3.5/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/yue\ \ text-to-audio\ \ YuE is a groundbreaking series of open-source foundation models designed for music generation, specifically for transforming lyrics into full songs.\ \ music](/models/fal-ai/yue) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/janus\ \ text-to-image\ \ DeepSeek Janus-Pro is a novel text-to-image model that unifies multimodal understanding and generation through an autoregressive framework\ \ stylized](/models/fal-ai/janus) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/luma-dream-machine/ray-2\ \ text-to-video\ \ Ray2 is a large-scale video generative model capable of creating realistic visuals with natural, coherent motion.\ \ motion\ \ transformation](/models/fal-ai/luma-dream-machine/ray-2) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling/v1-5/kolors-virtual-try-on\ \ image-to-image\ \ Kling Kolors Virtual TryOn v1.5 is a high quality image based Try-On endpoint which can be used for commercial try on.\ \ try-on\ \ fashion\ \ clothing](/models/fal-ai/kling/v1-5/kolors-virtual-try-on) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ffmpeg-api/waveform\ \ json\ \ Get waveform data from audio files using FFmpeg API.\ \ ffmpeg](/models/fal-ai/ffmpeg-api/waveform) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ffmpeg-api/metadata\ \ json\ \ Get encoding metadata from video and audio files using FFmpeg API.\ \ ffmpeg](/models/fal-ai/ffmpeg-api/metadata) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ffmpeg-api/compose\ \ video-to-video\ \ Compose videos from multiple media sources using FFmpeg API.\ \ ffmpeg](/models/fal-ai/ffmpeg-api/compose) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/minimax/video-01-subject-reference\ \ image-to-video\ \ Generate video clips maintaining consistent, realistic facial features and identity across dynamic video content\ \ subject\ \ transformation](/models/fal-ai/minimax/video-01-subject-reference) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/moondream-next/batch\ \ vision\ \ MoonDreamNext Batch is a multimodal vision-language model for batch captioning.\ \ multimodal](/models/fal-ai/moondream-next/batch) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-pro/v1.1-ultra-finetuned\ \ text-to-image\ \ FLUX1.1 \[pro\] ultra fine-tuned is the newest version of FLUX1.1 \[pro\] with a fine-tuned LoRA, maintaining professional-grade image quality while delivering up to 2K resolution with improved photo realism.\ \ high-res\ \ realism](/models/fal-ai/flux-pro/v1.1-ultra-finetuned) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-pro-trainer\ \ training\ \ FLUX LoRA for Pro endpoints.\ \ lora\ \ personalization](/models/fal-ai/flux-pro-trainer) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-pro/v1/depth\ \ image-to-image\ \ Generate high-quality images from depth maps using Flux.1 \[pro\] depth estimation model. The model produces accurate depth representations for scene understanding and 3D visualization.\ \ depth\ \ utility\ \ composition](/models/fal-ai/flux-pro/v1/depth) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-pro/v1/depth-finetuned\ \ image-to-image\ \ Generate high-quality images from depth maps using Flux.1 \[pro\] depth estimation model with a fine-tuned LoRA. The model produces accurate depth representations for scene understanding and 3D visualization.\ \ depth\ \ utility\ \ composition](/models/fal-ai/flux-pro/v1/depth-finetuned) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-pro/v1/canny\ \ image-to-image\ \ Utilize Flux.1 \[pro\] Controlnet to generate high-quality images with precise control over composition, style, and structure through advanced edge detection and guidance mechanisms.\ \ controlnet\ \ detection\ \ editing\ \ composition](/models/fal-ai/flux-pro/v1/canny) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hunyuan-video-lora\ \ text-to-video\ \ Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability](/models/fal-ai/hunyuan-video-lora) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-pro/v1.1\ \ text-to-image\ \ FLUX1.1 \[pro\] is an enhanced version of FLUX.1 \[pro\], improved image generation capabilities, delivering superior composition, detail, and artistic fidelity compared to its predecessor.](/models/fal-ai/flux-pro/v1.1) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-pro/v1/canny-finetuned\ \ image-to-image\ \ Utilize Flux.1 \[pro\] Controlnet with a fine-tuned LoRA to generate high-quality images with precise control over composition, style, and structure through advanced edge detection and guidance mechanisms.\ \ controlnet\ \ detection\ \ editing\ \ composition](/models/fal-ai/flux-pro/v1/canny-finetuned) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-pro/v1/fill-finetuned\ \ image-to-image\ \ FLUX.1 \[pro\] Fill Fine-tuned is a high-performance endpoint for the FLUX.1 \[pro\] model with a fine-tuned LoRA that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.\ \ editing](/models/fal-ai/flux-pro/v1/fill-finetuned) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-lora-canny\ \ image-to-image\ \ Utilize Flux.1 \[dev\] Controlnet to generate high-quality images with precise control over composition, style, and structure through advanced edge detection and guidance mechanisms.\ \ controlnet\ \ detection\ \ lora\ \ editing\ \ composition](/models/fal-ai/flux-lora-canny) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/cogvideox-5b\ \ text-to-video\ \ Generate videos from prompts using CogVideoX-5B](/models/fal-ai/cogvideox-5b) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/transpixar\ \ text-to-video\ \ Transform text into stunning videos with TransPixar - an AI model that generates both RGB footage and alpha channels, enabling seamless compositing and creative video effects.](/models/fal-ai/transpixar) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hunyuan-video-lora-training\ \ training\ \ Train Hunyuan Video lora on people, objects, characters and more!\ \ lora\ \ personalization](/models/fal-ai/hunyuan-video-lora-training) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sa2va/4b/video\ \ vision\ \ Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels\ \ multimodal\ \ vision](/models/fal-ai/sa2va/4b/video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sa2va/4b/image\ \ vision\ \ Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels\ \ multimodal\ \ vision](/models/fal-ai/sa2va/4b/image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/mini-cpm\ \ vision\ \ Multimodal vision-language model for single/multi image understanding\ \ multimodal\ \ vision](/models/fal-ai/mini-cpm) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sa2va/8b/video\ \ vision\ \ Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels\ \ multimodal\ \ vision](/models/fal-ai/sa2va/8b/video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sa2va/8b/image\ \ vision\ \ Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels\ \ multimodal\ \ vision](/models/fal-ai/sa2va/8b/image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sync-lipsync\ \ video-to-video\ \ Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization.\ \ animation\ \ lip sync](/models/fal-ai/sync-lipsync) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/recraft-crisp-upscale\ \ image-to-image\ \ Enhances a given raster image using 'crisp upscale' tool, boosting resolution with a focus on refining small details and faces.\ \ upscaling](/models/fal-ai/recraft-crisp-upscale) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/moondream-next/detection\ \ image-to-image\ \ MoonDreamNext Detection is a multimodal vision-language model for gaze detection, bbox detection, point detection, and more.\ \ multimodal](/models/fal-ai/moondream-next/detection) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/moondream-next\ \ vision\ \ MoonDreamNext is a multimodal vision-language model for captioning, gaze detection, bbox detection, point detection, and more.\ \ multimodal\ \ vision](/models/fal-ai/moondream-next) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/v1.6/standard/image-to-video\ \ image-to-video\ \ Generate video clips from your images using Kling 1.6 (std)](/models/fal-ai/kling-video/v1.6/standard/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/v1.6/standard/text-to-video\ \ text-to-video\ \ Generate video clips from your prompts using Kling 1.6 (std)](/models/fal-ai/kling-video/v1.6/standard/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/auto-caption\ \ video-to-video\ \ Automatically generates text captions for your videos from the audio as per text colour/font specifications\ \ captioning\ \ video](/models/fal-ai/auto-caption) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/switti/512\ \ text-to-image\ \ Switti is a scale-wise transformer for fast text-to-image generation that outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being faster than distilled diffusion models.](/models/fal-ai/switti/512) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/switti\ \ text-to-image\ \ Switti is a scale-wise transformer for fast text-to-image generation that outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being faster than distilled diffusion models.](/models/fal-ai/switti) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/mmaudio-v2/text-to-audio\ \ text-to-audio\ \ MMAudio generates synchronized audio given text inputs. It can generate sounds described by a prompt.\ \ audio\ \ fast](/models/fal-ai/mmaudio-v2/text-to-audio) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/dubbing\ \ video-to-video\ \ This endpoint delivers seamlessly localized videos by generating lip-synced dubs in multiple languages, ensuring natural and immersive multilingual experiences\ \ animation\ \ lip sync\ \ dubbing](/models/fal-ai/dubbing) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sadtalker/reference\ \ image-to-video\ \ Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation\ \ animation](/models/fal-ai/sadtalker/reference) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/bria/background/remove\ \ image-to-image\ \ Bria RMBG 2.0 enables seamless removal of backgrounds from images, ideal for professional editing tasks. Trained exclusively on licensed data for safe and risk-free commercial use. Model weights for commercial use are available here: https://share-eu1.hsforms.com/2GLpEVQqJTI2Lj7AMYwgfIwf4e04\ \ background removal\ \ image segmentation\ \ high resolution\ \ utility\ \ rembg](/models/fal-ai/bria/background/remove) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-lora-fill\ \ image-to-image\ \ FLUX.1 \[dev\] Fill is a high-performance endpoint for the FLUX.1 \[pro\] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.\ \ editing\ \ lora](/models/fal-ai/flux-lora-fill) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/bria/product-shot\ \ image-to-image\ \ Place any product in any scenery with just a prompt or reference image while maintaining high integrity of the product. Trained exclusively on licensed data for safe and risk-free commercial use and optimized for eCommerce.\ \ product photography](/models/fal-ai/bria/product-shot) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/bria/background/replace\ \ image-to-image\ \ Bria Background Replace allows for efficient swapping of backgrounds in images via text prompts or reference image, delivering realistic and polished results. Trained exclusively on licensed data for safe and risk-free commercial use\ \ image editing](/models/fal-ai/bria/background/replace) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/bria/text-to-image/fast\ \ text-to-image\ \ Bria's Text-to-Image model with perfect harmony of latency and quality. Trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us\ \ image generation](/models/fal-ai/bria/text-to-image/fast) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/bria/expand\ \ image-to-image\ \ Bria Expand expands images beyond their borders in high quality. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us\ \ outpainting](/models/fal-ai/bria/expand) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/playai/tts/v3\ \ text-to-speech\ \ Blazing-fast text-to-speech. Generate audio with improved emotional tones and extensive multilingual support. Ideal for high-volume processing and efficient workflows.](/models/fal-ai/playai/tts/v3) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/bria/genfill\ \ image-to-image\ \ Bria GenFill enables high-quality object addition or visual transformation. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us\ \ image editing](/models/fal-ai/bria/genfill) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/bria/text-to-image/hd\ \ text-to-image\ \ Bria's Text-to-Image model for HD images. Trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us\ \ image generation](/models/fal-ai/bria/text-to-image/hd) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/bria/text-to-image/base\ \ text-to-image\ \ Bria's Text-to-Image model, trained exclusively on licensed data for safe and risk-free commercial use. Available also as source code and weights. For access to weights: https://bria.ai/contact-us\ \ image generation](/models/fal-ai/bria/text-to-image/base) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/bria/eraser\ \ image-to-image\ \ Bria Eraser enables precise removal of unwanted objects from images while maintaining high-quality outputs. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us\ \ image editing\ \ object removal](/models/fal-ai/bria/eraser) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/cat-vton\ \ image-to-image\ \ Image based high quality Virtual Try-On\ \ try-on\ \ fashion\ \ clothing](/models/fal-ai/cat-vton) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/minimax-music\ \ text-to-audio\ \ Generate music from text prompts using the MiniMax model, which leverages advanced AI techniques to create high-quality, diverse musical compositions.\ \ music](/models/fal-ai/minimax-music) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/leffa/pose-transfer\ \ image-to-image\ \ Leffa Pose Transfer is an endpoint for changing pose of an image with a reference image.\ \ pose\ \ utility](/models/fal-ai/leffa/pose-transfer) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/leffa/virtual-tryon\ \ image-to-image\ \ Leffa Virtual TryOn is a high quality image based Try-On endpoint which can be used for commercial try on.\ \ try-on\ \ fashion\ \ clothing](/models/fal-ai/leffa/virtual-tryon) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/minimax/video-01-live\ \ text-to-video\ \ Generate video clips from your prompts using MiniMax model\ \ motion\ \ transformation](/models/fal-ai/minimax/video-01-live) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hyper3d/rodin\ \ image-to-3d\ \ Rodin by Hyper3D generates realistic and production ready 3D models from text or images.\ \ stylized](/models/fal-ai/hyper3d/rodin) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/recraft-20b\ \ text-to-image\ \ Recraft 20b is a new and affordable text-to-image model.\ \ image generation\ \ vector art\ \ typograph\ \ style](/models/fal-ai/recraft-20b) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/minimax/video-01-live/image-to-video\ \ image-to-video\ \ Generate video clips from your images using MiniMax Video model\ \ motion\ \ transformation](/models/fal-ai/minimax/video-01-live/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ideogram/v2/edit\ \ image-to-image\ \ Transform existing images with Ideogram V2's editing capabilities. Modify, adjust, and refine images while maintaining high fidelity and realistic outputs with precise prompt control.\ \ realism\ \ typography](/models/fal-ai/ideogram/v2/edit) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/trellis\ \ image-to-3d\ \ Generate 3D models from your images using Trellis. A native 3D generative model enabling versatile and high-quality 3D asset creation.\ \ stylized](/models/fal-ai/trellis) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/luma-dream-machine\ \ text-to-video\ \ Generate video clips from your prompts using Luma Dream Machine v1.5\ \ motion\ \ transformation](/models/fal-ai/luma-dream-machine) [![background texture](/assets/models/pixel-texture.svg)\ \ fashn/tryon\ \ image-to-image\ \ FASHN delivers precise virtual try-on capabilities, accurately rendering garment details like text and patterns at 576x864 resolution from both on-model and flat-lay photo references.\ \ try-on\ \ fashion\ \ clothing](/models/fashn/tryon) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ideogram/v2/remix\ \ image-to-image\ \ Reimagine existing images with Ideogram V2's remix feature. Create variations and adaptations while preserving core elements and adding new creative directions through prompt guidance.\ \ realism\ \ typography](/models/fal-ai/ideogram/v2/remix) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ideogram/v2/turbo\ \ text-to-image\ \ Accelerated image generation with Ideogram V2 Turbo. Create high-quality visuals, posters, and logos with enhanced speed while maintaining Ideogram's signature quality.\ \ realism\ \ typography](/models/fal-ai/ideogram/v2/turbo) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/video-upscaler\ \ video-to-video\ \ The video upscaler endpoint uses RealESRGAN on each frame of the input video to upscale the video to a higher resolution.\ \ video generation\ \ video to video\ \ ai video\ \ high fidelity motion](/models/fal-ai/video-upscaler) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ideogram/v2/turbo/edit\ \ image-to-image\ \ Edit images faster with Ideogram V2 Turbo. Quick modifications and adjustments while preserving the high-quality standards and realistic outputs of Ideogram.\ \ realism\ \ typography](/models/fal-ai/ideogram/v2/turbo/edit) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ideogram/v2/turbo/remix\ \ image-to-image\ \ Rapidly create image variations with Ideogram V2 Turbo Remix. Fast and efficient reimagining of existing images while maintaining creative control through prompt guidance.\ \ realism\ \ typography](/models/fal-ai/ideogram/v2/turbo/remix) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/v1/standard/text-to-video\ \ text-to-video\ \ Generate video clips from your prompts using Kling 1.0\ \ motion](/models/fal-ai/kling-video/v1/standard/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/luma-photon/flash\ \ text-to-image\ \ Generate images from your prompts using Luma Photon Flash. Photon Flash is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.](/models/fal-ai/luma-photon/flash) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/aura-flow\ \ text-to-image\ \ AuraFlow v0.3 is an open-source flow-based text-to-image generation model that achieves state-of-the-art results on GenEval. The model is currently in beta.\ \ typography\ \ style](/models/fal-ai/aura-flow) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/omnigen-v1\ \ text-to-image\ \ OmniGen is a unified image generation model that can generate a wide range of images from multi-modal prompts. It can be used for various tasks such as Image Editing, Personalized Image Generation, Virtual Try-On, Multi Person Generation and more!\ \ multimodal\ \ editing\ \ try-on](/models/fal-ai/omnigen-v1) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux/schnell/redux\ \ image-to-image\ \ FLUX.1 \[schnell\] Redux is a high-performance endpoint for the FLUX.1 \[schnell\] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.\ \ style transfer](/models/fal-ai/flux/schnell/redux) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/v1.5/pro/text-to-video\ \ text-to-video\ \ Generate video clips from your prompts using Kling 1.5 (pro)](/models/fal-ai/kling-video/v1.5/pro/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux/schnell\ \ text-to-image\ \ FLUX.1 \[schnell\] is a 12 billion parameter flow transformer that generates high-quality images from text in 1 to 4 steps, suitable for personal and commercial use.](/models/fal-ai/flux/schnell) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux/dev/redux\ \ image-to-image\ \ FLUX.1 \[dev\] Redux is a high-performance endpoint for the FLUX.1 \[dev\] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.\ \ style transfer\ \ lora](/models/fal-ai/flux/dev/redux) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-pro/v1.1/redux\ \ image-to-image\ \ FLUX1.1 \[pro\] Redux is a high-performance endpoint for the FLUX1.1 \[pro\] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.\ \ style transfer](/models/fal-ai/flux-pro/v1.1/redux) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-pro/v1/fill\ \ image-to-image\ \ FLUX.1 \[pro\] Fill is a high-performance endpoint for the FLUX.1 \[pro\] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.\ \ editing](/models/fal-ai/flux-pro/v1/fill) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ltx-video/image-to-video\ \ image-to-video\ \ Generate videos from images using LTX Video](/models/fal-ai/ltx-video/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-pro/v1/redux\ \ image-to-image\ \ FLUX.1 \[pro\] Redux is a high-performance endpoint for the FLUX.1 \[pro\] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.\ \ style transfer](/models/fal-ai/flux-pro/v1/redux) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-lora-depth\ \ image-to-image\ \ Generate high-quality images from depth maps using Flux.1 \[dev\] depth estimation model. The model produces accurate depth representations for scene understanding and 3D visualization.\ \ depth\ \ lora\ \ utility\ \ composition](/models/fal-ai/flux-lora-depth) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-pro/v1.1-ultra/redux\ \ image-to-image\ \ FLUX1.1 \[pro\] ultra Redux is a high-performance endpoint for the FLUX1.1 \[pro\] model that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.\ \ style transfer\ \ high-res](/models/fal-ai/flux-pro/v1.1-ultra/redux) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kolors/image-to-image\ \ image-to-image\ \ Photorealistic Image-to-Image\ \ realism\ \ editing\ \ diffusion](/models/fal-ai/kolors/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/iclight-v2\ \ image-to-image\ \ An endpoint for re-lighting photos and changing their backgrounds per a given description\ \ relighting\ \ editing](/models/fal-ai/iclight-v2) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/mochi-v1\ \ text-to-video\ \ Mochi 1 preview is an open state-of-the-art video generation model with high-fidelity motion and strong prompt adherence in preliminary evaluation.](/models/fal-ai/mochi-v1) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-differential-diffusion\ \ image-to-image\ \ FLUX.1 Differential Diffusion is a rapid endpoint that enables swift, granular control over image transformations through change maps, delivering fast and precise region-specific modifications while maintaining FLUX.1 \[dev\]'s high-quality output.\ \ transformation](/models/fal-ai/flux-differential-diffusion) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/recraft-v3/create-style\ \ training\ \ Recraft V3 Create Style is capable of creating unique styles for Recraft V3 based on your images.\ \ style\ \ vector\ \ personalization](/models/fal-ai/recraft-v3/create-style) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-pulid\ \ image-to-image\ \ An endpoint for personalized image generation using Flux as per given description.\ \ personalization\ \ style transfer](/models/fal-ai/flux-pulid) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/birefnet/v2\ \ image-to-image\ \ bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)\ \ background removal\ \ segmentation\ \ high-res\ \ utility](/models/fal-ai/birefnet/v2) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/stable-diffusion-v35-medium\ \ text-to-image\ \ Stable Diffusion 3.5 Medium is a Multimodal Diffusion Transformer (MMDiT) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.\ \ diffusion\ \ typography\ \ style](/models/fal-ai/stable-diffusion-v35-medium) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hunyuan-video\ \ text-to-video\ \ Hunyuan Video is an Open video generation model with high visual quality, motion diversity, text-video alignment, and generation stability. This endpoint generates videos from text descriptions.\ \ motion](/models/fal-ai/hunyuan-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/cogvideox-5b/image-to-video\ \ image-to-video\ \ Generate videos from images and prompts using CogVideoX-5B](/models/fal-ai/cogvideox-5b/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/f5-tts\ \ text-to-audio\ \ F5 TTS\ \ speech](/models/fal-ai/f5-tts) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/cogvideox-5b/video-to-video\ \ video-to-video\ \ Generate videos from videos and prompts using CogVideoX-5B\ \ editing](/models/fal-ai/cogvideox-5b/video-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/any-llm/vision\ \ vision\ \ Use any vision language model from our selected catalogue (powered by OpenRouter)\ \ multimodal\ \ vision\ \ streaming](/models/fal-ai/any-llm/vision) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/v1.5/pro/image-to-video\ \ image-to-video\ \ Generate video clips from your images using Kling 1.5 (pro)](/models/fal-ai/kling-video/v1.5/pro/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ltx-video\ \ text-to-video\ \ Generate videos from prompts using LTX Video](/models/fal-ai/ltx-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/v1/standard/image-to-video\ \ image-to-video\ \ Generate video clips from your images using Kling 1.0\ \ motion](/models/fal-ai/kling-video/v1/standard/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/v1/pro/text-to-video\ \ text-to-video\ \ Generate video clips from your prompts using Kling 1.0 (pro)\ \ motion](/models/fal-ai/kling-video/v1/pro/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kling-video/v1/pro/image-to-video\ \ image-to-video\ \ Generate video clips from your images using Kling 1.0 (pro)\ \ motion](/models/fal-ai/kling-video/v1/pro/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-pro/new\ \ text-to-image\ \ FLUX.1 \[pro\] new is an accelerated version of FLUX.1 \[pro\], maintaining professional-grade image quality while delivering significantly faster generation speeds.](/models/fal-ai/flux-pro/new) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/live-portrait/image\ \ image-to-image\ \ Transfer expression from a video to a portrait.\ \ expression\ \ animation](/models/fal-ai/live-portrait/image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-general/rf-inversion\ \ image-to-image\ \ A general purpose endpoint for the FLUX.1 \[dev\] model, implementing the RF-Inversion pipeline. This can be used to edit a reference image based on a prompt.\ \ rf-inversion\ \ editing\ \ lora](/models/fal-ai/flux-general/rf-inversion) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/stable-video\ \ image-to-video\ \ Generate short video clips from your images using SVD v1.1](/models/fal-ai/stable-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/image-preprocessors/hed\ \ image-to-image\ \ Holistically-Nested Edge Detection (HED) preprocessor.\ \ preprocess\ \ detection\ \ utility\ \ controlnet](/models/fal-ai/image-preprocessors/hed) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/image-preprocessors/zoe\ \ image-to-image\ \ ZoeDepth preprocessor.\ \ depth\ \ preprocess\ \ utility\ \ controlnet](/models/fal-ai/image-preprocessors/zoe) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-svd/text-to-video\ \ text-to-video\ \ Generate short video clips from your prompts using SVD v1.1](/models/fal-ai/fast-svd/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/image-preprocessors/teed\ \ image-to-image\ \ TEED (Temporal Edge Enhancement Detection) preprocessor.\ \ preprocess\ \ detection\ \ utility\ \ controlnet](/models/fal-ai/image-preprocessors/teed) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/image-preprocessors/scribble\ \ image-to-image\ \ Scribble preprocessor.\ \ preprocess\ \ utility\ \ editing\ \ controlnet\ \ sketch](/models/fal-ai/image-preprocessors/scribble) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/image-preprocessors/pidi\ \ image-to-image\ \ PIDI (Pidinet) preprocessor.\ \ detection\ \ preprocess\ \ utility\ \ controlnet](/models/fal-ai/image-preprocessors/pidi) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/image-preprocessors/mlsd\ \ image-to-image\ \ M-LSD line segment detection preprocessor.\ \ preprocess\ \ utility\ \ controlnet](/models/fal-ai/image-preprocessors/mlsd) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/image-preprocessors/sam\ \ image-to-image\ \ Segment Anything Model (SAM) preprocessor.\ \ segmentation\ \ preprocess\ \ utility\ \ mask\ \ controlnet](/models/fal-ai/image-preprocessors/sam) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/image-preprocessors/depth-anything/v2\ \ image-to-image\ \ Depth Anything v2 preprocessor.\ \ depth\ \ preprocess\ \ utility\ \ controlnet](/models/fal-ai/image-preprocessors/depth-anything/v2) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/image-preprocessors/midas\ \ image-to-image\ \ MiDaS depth estimation preprocessor.\ \ depth\ \ preprocess\ \ utility\ \ controlnet](/models/fal-ai/image-preprocessors/midas) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/image-preprocessors/lineart\ \ image-to-image\ \ Line art preprocessor.\ \ preprocess\ \ utility\ \ sketch\ \ controlnet](/models/fal-ai/image-preprocessors/lineart) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/controlnext\ \ video-to-video\ \ Animate a reference image with a driving video using ControlNeXt.\ \ animation\ \ stylized](/models/fal-ai/controlnext) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/mini-cpm/video\ \ vision\ \ Multimodal vision-language model for video understanding\ \ multimodal\ \ vision](/models/fal-ai/mini-cpm/video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/stable-diffusion-v3-medium\ \ text-to-image\ \ Stable Diffusion 3 Medium (Text to Image) is a Multimodal Diffusion Transformer (MMDiT) model that improves image quality, typography, prompt understanding, and efficiency.\ \ diffusion\ \ style](/models/fal-ai/stable-diffusion-v3-medium) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sam2/video\ \ video-to-video\ \ SAM 2 is a model for segmenting images and videos in real-time.\ \ segmentation\ \ mask\ \ real-time](/models/fal-ai/sam2/video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sam2/image\ \ image-to-image\ \ SAM 2 is a model for segmenting images and videos in real-time.\ \ segmentation\ \ mask\ \ real-time](/models/fal-ai/sam2/image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-general/inpainting\ \ image-to-image\ \ FLUX General Inpainting is a versatile endpoint that enables precise image editing and completion, supporting multiple AI extensions including LoRA, ControlNet, and IP-Adapter for enhanced control over inpainting results and sophisticated image modifications.\ \ lora\ \ controlnet\ \ ip-adapter](/models/fal-ai/flux-general/inpainting) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-general/image-to-image\ \ image-to-image\ \ FLUX General Image-to-Image is a versatile endpoint that transforms existing images with support for LoRA, ControlNet, and IP-Adapter extensions, enabling precise control over style transfer, modifications, and artistic variations through multiple guidance methods.\ \ lora\ \ controlnet\ \ ip-adapter](/models/fal-ai/flux-general/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-general/differential-diffusion\ \ image-to-image\ \ A specialized FLUX endpoint combining differential diffusion control with LoRA, ControlNet, and IP-Adapter support, enabling precise, region-specific image transformations through customizable change maps.\ \ lora\ \ controlnet\ \ ip-adapter](/models/fal-ai/flux-general/differential-diffusion) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-lora/image-to-image\ \ image-to-image\ \ FLUX LoRA Image-to-Image is a high-performance endpoint that transforms existing images using FLUX models, leveraging LoRA adaptations to enable rapid and precise image style transfer, modifications, and artistic variations.\ \ lora\ \ style transfer](/models/fal-ai/flux-lora/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fooocus/upscale-or-vary\ \ text-to-image\ \ Default parameters with automated optimizations and quality improvements.\ \ upscaling\ \ vary\ \ stylized](/models/fal-ai/fooocus/upscale-or-vary) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pixart-sigma\ \ text-to-image\ \ Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation\ \ diffusion](/models/fal-ai/pixart-sigma) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sana\ \ text-to-image\ \ Sana can synthesize high-resolution, high-quality images with strong text-image alignment at a remarkably fast speed, with the ability to generate 4K images in less than a second.](/models/fal-ai/sana) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/flux-subject\ \ text-to-image\ \ Super fast endpoint for the FLUX.1 \[schnell\] model with subject input capabilities, enabling rapid and high-quality image generation for personalization, specific styles, brand identities, and product-specific outputs.\ \ personalization\ \ customization](/models/fal-ai/flux-subject) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sdxl-controlnet-union\ \ text-to-image\ \ An efficent SDXL multi-controlnet text-to-image model.\ \ diffusion\ \ controlnet\ \ composition](/models/fal-ai/sdxl-controlnet-union) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sdxl-controlnet-union/inpainting\ \ image-to-image\ \ An efficent SDXL multi-controlnet inpainting model.\ \ diffusion\ \ controlnet\ \ composition](/models/fal-ai/sdxl-controlnet-union/inpainting) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sdxl-controlnet-union/image-to-image\ \ image-to-image\ \ An efficent SDXL multi-controlnet image-to-image model.\ \ diffusion\ \ controlnet\ \ composition](/models/fal-ai/sdxl-controlnet-union/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/kolors\ \ text-to-image\ \ Photorealistic Text-to-Image\ \ realism\ \ diffusion](/models/fal-ai/kolors) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/amt-interpolation/frame-interpolation\ \ image-to-video\ \ Interpolate between image frames\ \ interpolation\ \ editing](/models/fal-ai/amt-interpolation/frame-interpolation) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/live-portrait\ \ image-to-video\ \ Transfer expression from a video to a portrait.\ \ expression\ \ animation](/models/fal-ai/live-portrait) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/era-3d\ \ image-to-image\ \ A powerful image to novel multiview model with normals.](/models/fal-ai/era-3d) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/stable-cascade\ \ text-to-image\ \ Stable Cascade: Image generation on a smaller & cheaper latent space.\ \ diffusion\ \ lcm](/models/fal-ai/stable-cascade) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/florence-2-large/referring-expression-segmentation\ \ image-to-image\ \ Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks\ \ multimodal\ \ vision\ \ segmentation](/models/fal-ai/florence-2-large/referring-expression-segmentation) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/florence-2-large/ocr-with-region\ \ image-to-image\ \ Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks\ \ ocr\ \ multimodal\ \ vision](/models/fal-ai/florence-2-large/ocr-with-region) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/florence-2-large/region-to-description\ \ vision\ \ Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks\ \ multimodal\ \ vision](/models/fal-ai/florence-2-large/region-to-description) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/florence-2-large/region-to-category\ \ vision\ \ Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks\ \ multimodal\ \ vision](/models/fal-ai/florence-2-large/region-to-category) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/florence-2-large/ocr\ \ vision\ \ Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks\ \ ocr\ \ multimodal\ \ vision](/models/fal-ai/florence-2-large/ocr) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/florence-2-large/open-vocabulary-detection\ \ image-to-image\ \ Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks\ \ multimodal\ \ vision\ \ detection](/models/fal-ai/florence-2-large/open-vocabulary-detection) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/florence-2-large/region-to-segmentation\ \ image-to-image\ \ Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks\ \ multimodal\ \ vision\ \ segmentation](/models/fal-ai/florence-2-large/region-to-segmentation) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/florence-2-large/more-detailed-caption\ \ vision\ \ Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks\ \ captioning\ \ multimodal\ \ vision](/models/fal-ai/florence-2-large/more-detailed-caption) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/florence-2-large/caption-to-phrase-grounding\ \ image-to-image\ \ Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks\ \ multimodal\ \ vision](/models/fal-ai/florence-2-large/caption-to-phrase-grounding) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/florence-2-large/region-proposal\ \ image-to-image\ \ Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks\ \ multimodal\ \ vision](/models/fal-ai/florence-2-large/region-proposal) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/florence-2-large/detailed-caption\ \ vision\ \ Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks\ \ captioning\ \ multimodal\ \ vision](/models/fal-ai/florence-2-large/detailed-caption) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/florence-2-large/dense-region-caption\ \ image-to-image\ \ Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks\ \ multimodal\ \ vision](/models/fal-ai/florence-2-large/dense-region-caption) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/florence-2-large/object-detection\ \ image-to-image\ \ Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks\ \ detection\ \ multimodal\ \ vision](/models/fal-ai/florence-2-large/object-detection) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/florence-2-large/caption\ \ vision\ \ Florence-2 is an advanced vision foundation model that uses a prompt-based approach to handle a wide range of vision and vision-language tasks\ \ captioning\ \ multimodal\ \ vision](/models/fal-ai/florence-2-large/caption) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/stable-diffusion-v3-medium/image-to-image\ \ image-to-image\ \ Stable Diffusion 3 Medium (Image to Image) is a Multimodal Diffusion Transformer (MMDiT) model that improves image quality, typography, prompt understanding, and efficiency.\ \ diffusion\ \ editing\ \ style](/models/fal-ai/stable-diffusion-v3-medium/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-sdxl\ \ text-to-image\ \ Run SDXL at the speed of light\ \ diffusion\ \ lora\ \ embeddings\ \ high-res\ \ style](/models/fal-ai/fast-sdxl) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/stable-cascade/sote-diffusion\ \ text-to-image\ \ Anime finetune of Würstchen V3.\ \ lcm\ \ stylized](/models/fal-ai/stable-cascade/sote-diffusion) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/luma-photon\ \ text-to-image\ \ Generate images from your prompts using Luma Photon. Photon is the most creative, personalizable, and intelligent visual models for creatives, bringing a step-function change in the cost of high-quality image generation.](/models/fal-ai/luma-photon) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/luma-dream-machine/image-to-video\ \ image-to-video\ \ Generate video clips from your images using Luma Dream Machine v1.5\ \ motion\ \ transformation](/models/fal-ai/luma-dream-machine/image-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-svd-lcm/text-to-video\ \ text-to-video\ \ Generate short video clips from your images using SVD v1.1 at Lightning Speed\ \ lcm\ \ diffusion\ \ turbo](/models/fal-ai/fast-svd-lcm/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/dwpose\ \ image-to-image\ \ Predict poses.\ \ pose\ \ utility](/models/fal-ai/dwpose) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sd15-depth-controlnet\ \ image-to-image\ \ SD 1.5 ControlNet\ \ diffusion\ \ editing\ \ manipulation\ \ controlnet](/models/fal-ai/sd15-depth-controlnet) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ccsr\ \ image-to-image\ \ SOTA Image Upscaler\ \ upscaling](/models/fal-ai/ccsr) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/playground-v25\ \ text-to-image\ \ State-of-the-art open-source model in aesthetic quality\ \ artistic\ \ style](/models/fal-ai/playground-v25) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/dreamshaper\ \ text-to-image\ \ Dreamshaper model.\ \ stylized\ \ diffusion](/models/fal-ai/dreamshaper) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/omni-zero\ \ image-to-image\ \ Any pose, any style, any identity\ \ style transfer](/models/fal-ai/omni-zero) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/lightning-models\ \ text-to-image\ \ Collection of SDXL Lightning models.\ \ diffusion\ \ lightning](/models/fal-ai/lightning-models) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hyper-sdxl/inpainting\ \ image-to-image\ \ Hyper-charge SDXL's performance and creativity.\ \ diffusion](/models/fal-ai/hyper-sdxl/inpainting) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/realistic-vision\ \ text-to-image\ \ Generate realistic images.\ \ realism\ \ diffusion](/models/fal-ai/realistic-vision) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hyper-sdxl/image-to-image\ \ image-to-image\ \ Hyper-charge SDXL's performance and creativity.\ \ diffusion\ \ editing](/models/fal-ai/hyper-sdxl/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/ip-adapter-face-id\ \ image-to-image\ \ High quality zero-shot personalization\ \ ip-adapter\ \ personalization\ \ customization\ \ editing](/models/fal-ai/ip-adapter-face-id) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/lora/inpaint\ \ image-to-image\ \ Run Any Stable Diffusion model with customizable LoRA weights.\ \ diffusion\ \ lora\ \ customization\ \ fine-tuning](/models/fal-ai/lora/inpaint) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/lora/image-to-image\ \ image-to-image\ \ Run Any Stable Diffusion model with customizable LoRA weights.\ \ diffusion\ \ lora\ \ customization\ \ fine-tuning](/models/fal-ai/lora/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/stable-diffusion-v15\ \ text-to-image\ \ Stable Diffusion v1.5\ \ diffusion](/models/fal-ai/stable-diffusion-v15) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-sdxl/inpainting\ \ image-to-image\ \ Run SDXL at the speed of light\ \ diffusion\ \ high-res\ \ lora\ \ ip-adapter\ \ controlnet](/models/fal-ai/fast-sdxl/inpainting) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-sdxl/image-to-image\ \ image-to-image\ \ Run SDXL at the speed of light\ \ diffusion\ \ high-res\ \ lora\ \ ip-adapter\ \ controlnet](/models/fal-ai/fast-sdxl/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/layer-diffusion\ \ text-to-image\ \ SDXL with an alpha channel.](/models/fal-ai/layer-diffusion) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-lightning-sdxl\ \ text-to-image\ \ Run SDXL at the speed of light\ \ diffusion\ \ lightning\ \ real-time](/models/fal-ai/fast-lightning-sdxl) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/sadtalker\ \ image-to-video\ \ Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation\ \ animation](/models/fal-ai/sadtalker) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/musetalk\ \ image-to-video\ \ MuseTalk is a real-time high quality audio-driven lip-syncing model. Use MuseTalk to animate a face with your own audio.\ \ animation\ \ lip sync\ \ real-time](/models/fal-ai/musetalk) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/wizper\ \ speech-to-text\ \ \[Experimental\] Whisper v3 Large -- but optimized by our inference wizards. Same WER, double the performance!\ \ transcription\ \ speech](/models/fal-ai/wizper) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/imageutils/nsfw\ \ vision\ \ Predict the probability of an image being NSFW.\ \ filter\ \ safety\ \ utility](/models/fal-ai/imageutils/nsfw) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/moondream/batched\ \ vision\ \ Answer questions from the images.\ \ multimodal\ \ vision](/models/fal-ai/moondream/batched) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-fooocus-sdxl/image-to-image\ \ text-to-image\ \ Fooocus extreme speed mode as a standalone app.\ \ stylized](/models/fal-ai/fast-fooocus-sdxl/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/face-to-sticker\ \ image-to-image\ \ Create stickers from faces.\ \ sticker\ \ editing](/models/fal-ai/face-to-sticker) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/photomaker\ \ image-to-image\ \ Customizing Realistic Human Photos via Stacked ID Embedding\ \ editing\ \ customization\ \ realism\ \ personalization](/models/fal-ai/photomaker) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/t2v-turbo\ \ text-to-video\ \ Generate short video clips from your prompts\ \ turbo](/models/fal-ai/t2v-turbo) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-sdxl-controlnet-canny\ \ text-to-image\ \ Generate Images with ControlNet.\ \ diffusion\ \ controlnet\ \ manipulation](/models/fal-ai/fast-sdxl-controlnet-canny) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/creative-upscaler\ \ image-to-image\ \ Create creative upscaled images.\ \ upscaling](/models/fal-ai/creative-upscaler) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/animatediff-v2v/turbo\ \ video-to-video\ \ Re-animate your videos with evolved consistency!\ \ animation\ \ stylized\ \ turbo](/models/fal-ai/animatediff-v2v/turbo) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/birefnet\ \ image-to-image\ \ bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)\ \ background removal\ \ segmentation\ \ high-res\ \ utility](/models/fal-ai/birefnet) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/amt-interpolation\ \ video-to-video\ \ Interpolate between video frames\ \ interpolation\ \ editing](/models/fal-ai/amt-interpolation) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/hyper-sdxl\ \ text-to-image\ \ Hyper-charge SDXL's performance and creativity.\ \ diffusion\ \ real-time](/models/fal-ai/hyper-sdxl) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/playground-v25/image-to-image\ \ image-to-image\ \ State-of-the-art open-source model in aesthetic quality\ \ artistic\ \ style](/models/fal-ai/playground-v25/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-animatediff/text-to-video\ \ text-to-video\ \ Animate your ideas!\ \ animation\ \ stylized](/models/fal-ai/fast-animatediff/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-lightning-sdxl/image-to-image\ \ image-to-image\ \ Run SDXL at the speed of light\ \ diffusion\ \ lightning\ \ editing](/models/fal-ai/fast-lightning-sdxl/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-lightning-sdxl/inpainting\ \ image-to-image\ \ Run SDXL at the speed of light\ \ diffusion\ \ lightning](/models/fal-ai/fast-lightning-sdxl/inpainting) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/playground-v25/inpainting\ \ image-to-image\ \ State-of-the-art open-source model in aesthetic quality\ \ inpaint\ \ artistic\ \ style](/models/fal-ai/playground-v25/inpainting) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/whisper\ \ speech-to-text\ \ Whisper is a model for speech transcription and translation.\ \ transcription\ \ translation\ \ speech](/models/fal-ai/whisper) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-lcm-diffusion\ \ text-to-image\ \ Run SDXL at the speed of light\ \ lcm\ \ diffusion\ \ turbo\ \ real-time](/models/fal-ai/fast-lcm-diffusion) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-lcm-diffusion/image-to-image\ \ image-to-image\ \ Run SDXL at the speed of light\ \ lcm\ \ diffusion\ \ turbo\ \ real-time\ \ editing](/models/fal-ai/fast-lcm-diffusion/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-lcm-diffusion/inpainting\ \ image-to-image\ \ Run SDXL at the speed of light\ \ lcm\ \ diffusion\ \ turbo\ \ real-time\ \ editing](/models/fal-ai/fast-lcm-diffusion/inpainting) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-fooocus-sdxl\ \ text-to-image\ \ Fooocus extreme speed mode as a standalone app.](/models/fal-ai/fast-fooocus-sdxl) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/any-llm\ \ llm\ \ Use any large language model from our selected catalogue (powered by OpenRouter)\ \ chat\ \ claude\ \ gpt\ \ streaming](/models/fal-ai/any-llm) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/llava-next\ \ vision\ \ Vision\ \ multimodal\ \ vision](/models/fal-ai/llava-next) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-animatediff/turbo/text-to-video\ \ text-to-video\ \ Animate your ideas in lightning speed!\ \ animation\ \ stylized\ \ turbo](/models/fal-ai/fast-animatediff/turbo/text-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/imageutils/depth\ \ image-to-image\ \ Create depth maps using Midas depth estimation.\ \ depth\ \ utility](/models/fal-ai/imageutils/depth) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fooocus/image-prompt\ \ text-to-image\ \ Default parameters with automated optimizations and quality improvements.\ \ stylized](/models/fal-ai/fooocus/image-prompt) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/illusion-diffusion\ \ text-to-image\ \ Create illusions conditioned on image.\ \ composition\ \ stylized](/models/fal-ai/illusion-diffusion) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-animatediff/video-to-video\ \ video-to-video\ \ Re-animate your videos!\ \ animation\ \ stylized](/models/fal-ai/fast-animatediff/video-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/retoucher\ \ image-to-image\ \ Automatically retouches faces to smooth skin and remove blemishes.\ \ editing](/models/fal-ai/retoucher) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/animatediff-v2v\ \ video-to-video\ \ Re-animate your videos with evolved consistency!\ \ animation\ \ stylized](/models/fal-ai/animatediff-v2v) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fooocus/inpaint\ \ text-to-image\ \ Default parameters with automated optimizations and quality improvements.\ \ stylized\ \ editing](/models/fal-ai/fooocus/inpaint) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/minimax/video-01\ \ text-to-video\ \ Generate video clips from your prompts using MiniMax model\ \ motion\ \ transformation](/models/fal-ai/minimax/video-01) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-svd-lcm\ \ image-to-video\ \ Generate short video clips from your images using SVD v1.1 at Lightning Speed\ \ turbo](/models/fal-ai/fast-svd-lcm) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-animatediff/turbo/video-to-video\ \ video-to-video\ \ Re-animate your videos in lightning speed!\ \ animation\ \ stylized\ \ turbo](/models/fal-ai/fast-animatediff/turbo/video-to-video) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/lcm\ \ text-to-image\ \ Produce high-quality images with minimal inference steps.\ \ diffusion\ \ lcm\ \ real-time](/models/fal-ai/lcm) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/triposr\ \ image-to-3d\ \ State of the art Image to 3D Object generation](/models/fal-ai/triposr) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/diffusion-edge\ \ text-to-image\ \ Diffusion based high quality edge detection\ \ detection](/models/fal-ai/diffusion-edge) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/stable-audio\ \ text-to-audio\ \ Open source text-to-audio model.\ \ music](/models/fal-ai/stable-audio) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/imageutils/marigold-depth\ \ image-to-image\ \ Create depth maps using Marigold depth estimation.\ \ depth\ \ utility](/models/fal-ai/imageutils/marigold-depth) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/pulid\ \ image-to-image\ \ Tuning-free ID customization.\ \ editing\ \ customization\ \ personalization](/models/fal-ai/pulid) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-sdxl-controlnet-canny/image-to-image\ \ image-to-image\ \ Generate Images with ControlNet.\ \ diffusion\ \ controlnet\ \ editing\ \ manipulation](/models/fal-ai/fast-sdxl-controlnet-canny/image-to-image) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fast-sdxl-controlnet-canny/inpainting\ \ image-to-image\ \ Generate Images with ControlNet.\ \ diffusion\ \ controlnet\ \ editing\ \ manipulation](/models/fal-ai/fast-sdxl-controlnet-canny/inpainting) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/fooocus\ \ text-to-image\ \ Default parameters with automated optimizations and quality improvements.\ \ stylized](/models/fal-ai/fooocus) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/animatediff-sparsectrl-lcm\ \ text-to-video\ \ Animate Your Drawings with Latent Consistency Models!\ \ lcm\ \ animation\ \ stylized](/models/fal-ai/animatediff-sparsectrl-lcm) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/lcm-sd15-i2i\ \ image-to-image\ \ Produce high-quality images with minimal inference steps. Optimized for 512x512 input image size.\ \ diffusion\ \ lcm\ \ real-time](/models/fal-ai/lcm-sd15-i2i) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/inpaint\ \ image-to-image\ \ Inpaint images with SD and SDXL\ \ editing\ \ diffusion](/models/fal-ai/inpaint) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/esrgan\ \ image-to-image\ \ Upscale images by a given factor.\ \ upscaling\ \ high-res](/models/fal-ai/esrgan) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/imageutils/rembg\ \ image-to-image\ \ Remove the background from an image.\ \ background removal\ \ utility\ \ editing](/models/fal-ai/imageutils/rembg) [![background texture](/assets/models/pixel-texture.svg)\ \ fal-ai/lora\ \ text-to-image\ \ Run Any Stable Diffusion model with customizable LoRA weights.\ \ diffusion\ \ lora\ \ customization](/models/fal-ai/lora) --- # Login || fal.ai ![](/landing/landing-left-1.webp)![](/landing/landing-right-1.webp) Log in to fal.ai ================ [Continue with GitHub](/api/auth/v2/connect/github?returnTo=/dashboard) Continue with SSO By clicking continue, you agree to our [Terms of Service](/terms.html) and [Privacy Policy](/privacy.html) ### Enterprise Single Sign-On Domain [Continue](/api/auth/connect/?returnTo=/dashboard) Back Do you want to become an enterprise customer with SSO login? [Contact us](/cdn-cgi/l/email-protection#344755585147745255581a555d) Don't have an account yet? [Sign up](/api/auth/v2/connect/github?returnTo=/dashboard) --- # Email Protection | Cloudflare Please enable cookies. Email Protection ================ You are unable to access this email address fal.ai -------------------------------------------------- The website from which you got to this page is protected by Cloudflare. Email addresses on that page have been hidden in order to keep them from being accessed by malicious bots. **You must enable Javascript in your browser in order to decode the e-mail address**. If you have a website and are interested in protecting it in a similar way, you can [sign up for Cloudflare](https://www.cloudflare.com/sign-up?utm_source=email_protection) . * [How does Cloudflare protect email addresses on website from spammers?](https://support.cloudflare.com/hc/en-us/articles/200170016-What-is-Email-Address-Obfuscation-) * [Can I sign up for Cloudflare?](https://support.cloudflare.com/hc/en-us/categories/200275218-Getting-Started) Cloudflare Ray ID: **935db5ee0f162d05** • Your IP: Click to reveal 54.237.218.47 • Performance & security by [Cloudflare](https://www.cloudflare.com/5xx-error-landing) --- # Login || fal.ai ![](/landing/landing-left-1.webp)![](/landing/landing-right-1.webp) Log in to fal.ai ================ [Continue with GitHub](/api/auth/v2/connect/github?returnTo=/pricing) Continue with SSO By clicking continue, you agree to our [Terms of Service](/terms.html) and [Privacy Policy](/privacy.html) ### Enterprise Single Sign-On Domain [Continue](/api/auth/connect/?returnTo=/pricing) Back Do you want to become an enterprise customer with SSO login? [Contact us](/cdn-cgi/l/email-protection#7e0d1f121b0d3e181f12501f17) Don't have an account yet? [Sign up](/api/auth/v2/connect/github?returnTo=/pricing) ---