{"models":[{"endpoint_id":"fal-ai/nano-banana-pro/edit","metadata":{"display_name":"Nano Banana Pro","category":"image-to-image","description":"Nano Banana Pro is Google's new state-of-the-art image generation and editing model","status":"active","tags":["realism","typography"],"updated_at":"2026-10-20T21:51:05.959Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9c2f0f/p3rXI18zMYTBz1M0qP2h4_b9a2087ce0b64cd788cb5ec067edc26e.jpg","model_url":"https://fal.run/fal-ai/nano-banana-pro/edit","license_type":"commercial","date":"2025-11-20T14:27:03.344Z","group":{"key":"Nano-Banana-Pro","label":"Image Editing"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/nano-banana-2/edit","metadata":{"display_name":"Nano Banana 2","category":"image-to-image","description":"Nano Banana 2 is Google's new state-of-the-art image generation and editing model\n","status":"active","tags":[],"updated_at":"2026-10-20T22:20:30.114Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a900b75/DHb_RgXoXsYLdvzQz6mdn_95e87a44239c43448939b4c382dd957c.jpg","model_url":"https://fal.run/fal-ai/nano-banana-2/edit","license_type":"commercial","date":"2026-02-26T16:20:09.685Z","group":{"key":"nano-banana-2","label":"Image Editing"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"openai/gpt-image-2.5/sunburst/edit","metadata":{"display_name":"GPT Image 2.5 Sunburst Edit ","category":"image-to-image","description":"Editing built for the tightest control, edits scoped precisely to the instruction, with subject and composition preserved across many rounds of revision.","status":"active","tags":["stylized","transform","editing"],"updated_at":"2026-09-11T19:34:21.150Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa9a3b8/cSrDjg-ke-PcqgHiY_gxn.jpg","model_url":"https://fal.run/openai/gpt-image-2.5/sunburst/edit","license_type":"commercial","date":"2026-09-08T19:43:14.655Z","group":{"key":"gpt-25","label":"Image Editing Sunburst"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"google/nano-banana-2.1/edit","metadata":{"display_name":"Nano Banana 2.1 Edit","category":"image-to-image","description":"Nano Banana 2.1 Edit by Google transforms reference images using text instructions, with output resolutions up to 4K and optional video or PDF context.","status":"active","tags":["image editing","image to image","photorealism","typography","text rendering"],"updated_at":"2026-10-20T22:22:33.129Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaad14e/urvX9oiQqWKRcaZngAlID.jpg","model_url":"https://fal.run/google/nano-banana-2.1/edit","license_type":"commercial","date":"2026-10-06T15:48:52.103Z","group":{"key":"nano-banana-2.1","label":"Edit"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/flux/schnell","metadata":{"display_name":"FLUX.1 [schnell]","category":"text-to-image","description":"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.","status":"active","tags":[],"updated_at":"2026-06-24T23:02:10.109Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9af64d/GxvCUPd3gO-MSYcy06g0x_1641cfe028c2429b8e12e4fc320eb0a8.jpg","model_url":"https://fal.run/fal-ai/flux/schnell","github_url":"https://www.apache.org/licenses/LICENSE-2.0.txt","license_type":"commercial","date":"2024-11-25T00:00:00.000Z","group":{"key":"flux-1","label":"Text to Image [schnell]"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/nano-banana-pro","metadata":{"display_name":"Nano Banana Pro","category":"text-to-image","description":"Nano Banana Pro is Google's new state-of-the-art image generation and editing model","status":"active","tags":["realism","typography"],"updated_at":"2026-10-20T21:51:06.977Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8691ce/SR0_u1zPJbx8jCIO6bJR0_8c83f0d66bbd48f3b55f825117941f84.jpg","model_url":"https://fal.run/fal-ai/nano-banana-pro","license_type":"commercial","date":"2025-11-20T14:24:45.001Z","group":{"key":"Nano-Banana-Pro","label":"Text to Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"openai/gpt-image-2/edit","metadata":{"display_name":"GPT Image 2 API","category":"image-to-image","description":"GPT Image 2, OpenAI's latest image model, is capable of making fine-grained, detailed edits to images.","status":"active","tags":["gpt-image-2","openai","chatgpt-images-2"],"updated_at":"2026-08-13T21:01:03.124Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9c2f0d/G7gs81xziNgfaucyi7NO7_cfb3919cd2914dfba679e44ce8bbecdc.jpg","model_url":"https://fal.run/openai/gpt-image-2/edit","license_type":"commercial","date":"2026-04-20T19:16:13.451Z","group":{"key":"gpt-image-2","label":"Edit"},"highlighted":false,"kind":"inference","stream_url":"https://fal.run/openai/gpt-image-2/edit/stream","pinned":false}},{"endpoint_id":"fal-ai/nano-banana-2","metadata":{"display_name":"Nano Banana 2","category":"text-to-image","description":"Nano Banana 2 is Google's new state-of-the-art fast image generation and editing model","status":"active","tags":[],"updated_at":"2026-10-20T22:20:27.165Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a900b9e/ptbZcVWIQ_fXGGHfv8Zez_0ea5ca41bdf143a29e21e30a53120672.jpg","model_url":"https://fal.run/fal-ai/nano-banana-2","license_type":"commercial","date":"2026-02-26T16:08:01.361Z","group":{"key":"nano-banana-2","label":"Text to Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"openai/gpt-image-2.5/flare/edit","metadata":{"display_name":"GPT Image 2.5 Flare Edit","category":"image-to-image","description":"Precise image editing that changes only what's asked, keeping subject, composition, and background intact, with reference subjects staying recognizable across styles and successive edits.","status":"active","tags":["stylized","transform","editing"],"updated_at":"2026-09-11T19:34:21.150Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa9a3a4/LkWSlm_4F_SXsNlc4limv.jpg","model_url":"https://fal.run/openai/gpt-image-2.5/flare/edit","license_type":"commercial","date":"2026-09-08T19:39:52.983Z","group":{"key":"gpt-25","label":"Image Editing Flare"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/birefnet/v2","metadata":{"display_name":"Birefnet Background Removal V2","category":"image-to-image","description":"bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)","status":"active","tags":["background removal","segmentation","high-res","utility"],"updated_at":"2026-07-10T21:29:33.954Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/birefnet.webp","thumbnail_animated_url":"https://storage.googleapis.com/falserverless/gallery/birefnet-animated.webp","model_url":"https://fal.run/fal-ai/birefnet/v2","license_type":"commercial","date":"2024-10-28T00:00:00.000Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/nano-banana/edit","metadata":{"display_name":"Nano Banana","category":"image-to-image","description":"Google's famous original image generation and editing model","status":"active","tags":["image-editing"],"updated_at":"2026-10-20T21:52:29.017Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f9a4a/mjFnPPGaaBaf5OHrDSoSO_ns4MA9ac.png","model_url":"https://fal.run/fal-ai/nano-banana/edit","license_type":"commercial","date":"2025-08-19T22:16:18.949Z","group":{"key":"nano-banana","label":"Image Editing"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/v3/pro/image-to-video","metadata":{"display_name":"Kling Video v3 Image to Video [Pro]","category":"image-to-video","description":"Kling 3.0 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support.","status":"active","tags":["image-to-video"],"updated_at":"2026-05-29T18:50:02.672Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9c2fb3/yPzcdzINnY5RdSoEqHc8G_382d4ec9337344ccaacf5599057f6cd0.jpg","model_url":"https://fal.run/fal-ai/kling-video/v3/pro/image-to-video","license_type":"commercial","date":"2026-02-04T15:48:44.935Z","group":{"key":"kling-v3","label":"Image to Video (pro)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"minimax/h3-max/image-to-video","metadata":{"display_name":"H3 Max Image to Video","category":"image-to-video","description":"fal's H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-10-30T18:45:22.007Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa7658f/fSQlWMcduHn4_abgJ7qhQ.jpg","model_url":"https://fal.run/minimax/h3-max/image-to-video","license_type":"commercial","date":"2026-08-23T18:01:01.388Z","group":{"key":"hailuo-03-new-turbo","label":"Image to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"google/nano-banana-2.1","metadata":{"display_name":"Nano Banana 2.1","category":"text-to-image","description":"Nano Banana 2.1 by Google generates images from text prompts, with output resolutions up to 4K, adjustable aspect ratios, and optional web search grounding.","status":"active","tags":["image generation","photorealism","typography","text rendering"],"updated_at":"2026-10-20T22:22:30.076Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaad149/0HLWjH4WLjtFUmi3bYfF4.jpg","model_url":"https://fal.run/google/nano-banana-2.1","license_type":"commercial","date":"2026-10-06T15:47:22.891Z","group":{"key":"nano-banana-2.1","label":"Text to Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"openai/gpt-image-2","metadata":{"display_name":"GPT Image 2 API","category":"text-to-image","description":"GPT Image 2, OpenAI's latest image model, is capable of creating extremely detailed images with fine typography.","status":"active","tags":["gpt-image-2","openai","typography","chatgpt-images-2"],"updated_at":"2026-09-01T17:33:00.839Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a970c4a/BkrYELYOiaZMXCw-pgRcB_QlgOenEx.png","model_url":"https://fal.run/openai/gpt-image-2","license_type":"commercial","date":"2026-04-20T19:16:42.065Z","group":{"key":"gpt-image-2","label":"Text to Image"},"highlighted":false,"kind":"inference","stream_url":"https://fal.run/openai/gpt-image-2/stream","pinned":false}},{"endpoint_id":"openai/gpt-image-2.5/flare/text-to-image","metadata":{"display_name":"GPT Image 2.5 Flare Text to Image","category":"text-to-image","description":"OpenAI's default image model for most applications. Fast, high-quality generation with natural lighting, rich textures, and support for complex layouts including transparent backgrounds.","status":"active","tags":["realism","typography","stylized"],"updated_at":"2026-09-11T19:34:21.150Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa9a39a/1RpGwGDfDZbwC_QBhudJo.jpg","model_url":"https://fal.run/openai/gpt-image-2.5/flare/text-to-image","license_type":"commercial","date":"2026-09-08T19:38:25.222Z","group":{"key":"gpt-25","label":"Text to Image Flare"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/flux/dev","metadata":{"display_name":"FLUX.1 [dev]","category":"text-to-image","description":"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.","status":"active","tags":[],"updated_at":"2026-04-21T17:47:32.206Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/fal_cdn/fal/Upscale-1.jpeg","model_url":"https://fal.run/fal-ai/flux/dev","license_type":"commercial","date":"2025-04-01T18:10:42.284Z","group":{"key":"flux-1","label":"Text to Image [dev]"},"highlighted":false,"kind":"inference","stream_url":"https://fal.run/fal-ai/flux/dev/stream","pinned":false}},{"endpoint_id":"minimax/h3-max-turbo/image-to-video","metadata":{"display_name":"H3 Max Turbo Image to Video","category":"image-to-video","description":"fal's H3 Max Turbo is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-10-30T18:46:24.968Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa8d532/tsMg9lPG9DaXI7bqzqz6Y.jpg","model_url":"https://fal.run/minimax/h3-max-turbo/image-to-video","license_type":"commercial","date":"2026-09-02T16:51:51.105Z","group":{"key":"hailuo-03-new-max-turbo","label":"Image to Video Max Turbo"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"openai/gpt-image-2.5/sunburst/text-to-image","metadata":{"display_name":"GPT Image 2.5 Sunburst Text to Image","category":"text-to-image","description":"OpenAI's precision-focused image model, built for premium visual work, extra fidelity on intricate detail, in exchange for longer generation times.","status":"active","tags":["realism","typography","stylized"],"updated_at":"2026-09-11T19:34:21.150Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa9a3c6/xpKm5FzsZBuvm2Bf8xY7W.jpg","model_url":"https://fal.run/openai/gpt-image-2.5/sunburst/text-to-image","license_type":"commercial","date":"2026-09-08T19:41:24.961Z","group":{"key":"gpt-25","label":"Text to Image Sunburst"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"bytedance/seedream/v5/pro/edit","metadata":{"display_name":"Seedream 5.0 Pro Image Editing","category":"image-to-image","description":"Seedream 5.0 Pro is grounded, region-precise image editing model that changes one element while keeping the rest of the frame intact with layer separation, sketch completion, and up to 10 reference images.","status":"active","tags":["realism","typography","stylized"],"updated_at":"2026-10-20T22:18:56.016Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa15606/l4xYHHjF6aMrdoonScgXK.jpg","model_url":"https://fal.run/bytedance/seedream/v5/pro/edit","license_type":"commercial","date":"2026-07-07T20:08:05.177Z","group":{"key":"seedream-5-pro","label":"Image Editing"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/elevenlabs/sound-effects/v2","metadata":{"display_name":"Elevenlabs Sound Effects V2","category":"text-to-audio","description":"Generate sound effects using ElevenLabs advanced sound effects model.","status":"active","tags":["sound"],"updated_at":"2026-04-21T17:45:09.690Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/web-examples/elevenlabs/elevenlabs_thumbnail.webp","model_url":"https://fal.run/fal-ai/elevenlabs/sound-effects/v2","license_type":"commercial","date":"2025-09-02T20:11:50.270Z","group":{"key":"elevenlabs-audio","label":"Sound Effects V2"},"highlighted":false,"kind":"inference","stream_url":"https://fal.ai/models/fal-ai/elevenlabs/sound-effects/v2/stream","pinned":false}},{"endpoint_id":"minimax/h3-max/reference-to-video","metadata":{"display_name":"H3 Max Reference to Video","category":"image-to-video","description":"fal's H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality","status":"active","tags":["stylized","transform","typography"],"updated_at":"2026-10-23T00:37:07.747Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa84d7e/Weqd1RIL2EmDlzxnkQzCq.jpg","model_url":"https://fal.run/minimax/h3-max/reference-to-video","license_type":"commercial","date":"2026-08-29T16:21:32.325Z","group":{"key":"hailuo-03-new-turbo","label":"Reference to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/v2.5-turbo/pro/image-to-video","metadata":{"display_name":"Kling Video","category":"image-to-video","description":"Kling 2.5 Turbo Pro: Top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.","status":"active","tags":["stylized","transform"],"updated_at":"2026-04-26T22:25:17.147Z","is_favorited":null,"thumbnail_url":"https://v3.fal.media/files/rabbit/2KNBk1qkmEBXK0FLgfHCl_ee4bb1ada254433bbab296893a8636e3.jpg","model_url":"https://fal.run/fal-ai/kling-video/v2.5-turbo/pro/image-to-video","license_type":"commercial","date":"2025-09-22T22:51:16.379Z","group":{"key":"kling-video-v25","label":"2.5 Turbo (Image to Video) Pro"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/elevenlabs/tts/eleven-v3","metadata":{"display_name":"Elevenlabs Tts Eleven V3","category":"text-to-audio","description":"Generate text-to-speech audio using Eleven-v3 from ElevenLabs.","status":"active","tags":["audio"],"updated_at":"2026-06-24T10:32:10.977Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f91a8/oTkavdBnqhpPaT65B3FG8_euEcQphX.png","model_url":"https://fal.run/fal-ai/elevenlabs/tts/eleven-v3","license_type":"commercial","date":"2025-08-20T19:22:36.745Z","highlighted":false,"kind":"inference","stream_url":"https://fal.run/fal-ai/elevenlabs/tts/eleven-v3/stream","pinned":false}},{"endpoint_id":"fal-ai/flux-2-pro","metadata":{"display_name":"Flux 2 Pro","category":"text-to-image","description":"Image editing with FLUX.2 [pro] from Black Forest Labs. Ideal for high-quality image manipulation, style transfer, and sequential editing workflows","status":"active","tags":[],"updated_at":"2026-10-20T22:53:36.708Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/penguin/UfryXXm9my6IM8HsoP9FL_054c2c2953dc491996904114c6e04836.jpg","model_url":"https://fal.run/fal-ai/flux-2-pro","license_type":"commercial","date":"2025-11-23T00:14:31.608Z","group":{"key":"Flux2-Pro","label":"Text to Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/nano-banana","metadata":{"display_name":"Nano Banana","category":"text-to-image","description":"Google's famous original image generation and editing model","status":"active","tags":["image-generation"],"updated_at":"2026-10-20T21:51:11.766Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f91a7/UOFMBU7hW6hqvFYvXHH-o_MZBJlwLt.png","model_url":"https://fal.run/fal-ai/nano-banana","license_type":"commercial","date":"2025-08-19T22:11:04.357Z","group":{"key":"nano-banana","label":"Text to Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/seedvr/upscale/image","metadata":{"display_name":"SeedVR2","category":"image-to-image","description":"Use SeedVR2 to upscale your images","status":"active","tags":["upscale","image-to-image"],"updated_at":"2026-05-26T23:37:45.620Z","is_favorited":null,"thumbnail_url":"https://v3.fal.media/files/panda/_-1rRy0_I6w-fbt3q0RDL_2f47fece6e2b433994dda482e8d20bb9.jpg","model_url":"https://fal.run/fal-ai/seedvr/upscale/image","license_type":"commercial","date":"2025-09-22T18:19:28.476Z","group":{"key":"seedvr2","label":"Upscale Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"openrouter/router/vision","metadata":{"display_name":"OpenRouter [Vision]","category":"vision","description":"Run any Vision Language Model with fal. Analyze and understand images using Claude (Anthropic), GPT-5 / GPT-4o (OpenAI), Gemini (Google), Grok (xAI), Llama (Meta), Qwen, Pixtral (Mistral), and more. Send one or multiple images for captioning, analysis, OCR, or visual Q&A. Powered by OpenRouter. ","status":"active","tags":[],"updated_at":"2026-06-26T15:54:21.304Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/penguin/v-wl5CGbHxNVatcGXntIY_e14c7922d88348769a90469d1c206501.jpg","model_url":"https://fal.run/openrouter/router/vision","license_type":"commercial","date":"2025-11-12T20:20:52.668Z","group":{"key":"openrouter/router","label":"Any VLM"},"highlighted":false,"kind":"inference","stream_url":"https://fal.run/openrouter/router/vision/stream","pinned":false}},{"endpoint_id":"fal-ai/flux-pro/kontext","metadata":{"display_name":"FLUX.1 Kontext [pro]","category":"image-to-image","description":"FLUX.1 Kontext [pro] handles both text and reference images as inputs, seamlessly enabling targeted, local edits and complex transformations of entire scenes.","status":"active","tags":[],"updated_at":"2026-04-21T17:47:19.221Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/fal_cdn/fal/Training-2.jpg","model_url":"https://fal.run/fal-ai/flux-pro/kontext","license_type":"commercial","date":"2025-05-28T18:30:52.718Z","group":{"key":"flux-pro-kontext","label":"Kontext [pro] -- Editing"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/elevenlabs/speech-to-text/scribe-v2","metadata":{"display_name":"ElevenLabs Speech to Text - Scribe V2","category":"speech-to-text","description":"Use Scribe-V2 from ElevenLabs to do blazingly fast speech to text inferences!","status":"active","tags":["speech-to-text"],"updated_at":"2026-10-20T22:07:58.113Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8a5d77/3XtHpcC46Sg0ItPRjB6Uk_82a3a831177745b38f925d35a7b5ed66.jpg","model_url":"https://fal.run/fal-ai/elevenlabs/speech-to-text/scribe-v2","license_type":"commercial","date":"2026-01-14T14:30:10.342Z","group":{"key":"e11-speech-to-text","label":"Scribe V2"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"elevenlabs/tts/eleven-v4","metadata":{"display_name":"Eleven v4","category":"text-to-speech","description":"Generate expressive speech with Eleven v4 from ElevenLabs. Control delivery with audio tags, voice stability, similarity settings, and IPA pronunciation.","status":"active","tags":["audio","text-to-speech","voiceover"],"updated_at":"2026-10-02T19:10:00.967Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aac4241/SUZvoStueCW3Z6uEtzMiA.jpg","model_url":"https://fal.run/elevenlabs/tts/eleven-v4","license_type":"commercial","date":"2026-09-28T16:35:18.269Z","group":{"key":"eleven-v4","label":"Eleven V4"},"highlighted":false,"kind":"inference","stream_url":"https://fal.run/elevenlabs/tts/eleven-v4/stream","pinned":false}},{"endpoint_id":"fal-ai/bria/background/remove","metadata":{"display_name":"Bria RMBG 2.0","category":"image-to-image","description":"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","status":"active","tags":["background removal","image segmentation","high resolution","utility","rembg"],"updated_at":"2026-10-20T22:19:05.471Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f91b0/MLLgU8RVRvmMXjLkFNHwH_DWC4dcir.png","model_url":"https://fal.run/fal-ai/bria/background/remove","license_type":"commercial","date":"2024-12-19T00:00:00.000Z","group":{"key":"bria","label":"Remove Background"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"kling/v4/image-to-video","metadata":{"display_name":"Kling 4.0 Image to Video","category":"image-to-video","description":"Kling 4.0 animates a starting image into a 3 to 30-second video at 720p or 1080p, with optional ending frames and per-shot prompts.  ","status":"active","tags":["image-to-video","multi-shot","cinematic","kling"],"updated_at":"2026-10-23T16:51:06.932Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaea00f/kDSSuRNelHs4Q40pk4QFR.jpg","model_url":"https://fal.run/kling/v4/image-to-video","license_type":"commercial","date":"2026-10-16T15:20:11.407Z","group":{"key":"kling-v4","label":"Image to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"openrouter/router/openai/v1/chat/completions","metadata":{"display_name":"OpenRouter Chat Completions [OpenAI Compatible]","category":"llm","description":"OpenAI-compatible chat completions API. Drop-in replacement for the OpenAI API — use any OpenAI SDK or client to access Claude, Gemini, Grok, DeepSeek, Llama, Qwen, Mistral, and all OpenAI models (GPT-5, GPT-4o, o3) through fal. Powered by OpenRouter.","status":"active","tags":[],"updated_at":"2026-05-06T21:21:33.117Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/kangaroo/tll4XzKQE4bopYdZOX1q2_c3e4d28642484971932f8dbe3523af5a.jpg","model_url":"https://fal.run/openrouter/router/openai/v1/chat/completions","license_type":"commercial","date":"2025-11-12T20:15:52.898Z","group":{"key":"openrouter/router","label":"Chat Completions [OpenAI Compatible]"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/flux-pro/v1.1","metadata":{"display_name":"FLUX1.1 [pro]","category":"text-to-image","description":"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.","status":"active","tags":[],"updated_at":"2026-04-21T17:47:23.571Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/turbo_thumbnail.jpg","model_url":"https://fal.run/fal-ai/flux-pro/v1.1","license_type":"commercial","date":"2025-01-16T00:00:00.000Z","group":{"key":"flux-pro","label":"FLUX 1.1 [pro]"},"highlighted":false,"pinned":false}},{"endpoint_id":"fal-ai/bytedance/seedream/v4.5/edit","metadata":{"display_name":"Bytedance Seedream V4.5 Edit","category":"image-to-image","description":"A new-generation image creation model ByteDance, Seedream 4.5 integrates image generation and image editing capabilities into a single, unified architecture.\n","status":"active","tags":["stylized","transform"],"updated_at":"2026-04-26T21:58:12.077Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a84910b/lDvWLqpxcFmzQHdadDA7t_4012f28b4f79444782d90d8927b42c29.jpg","model_url":"https://fal.run/fal-ai/bytedance/seedream/v4.5/edit","license_type":"commercial","date":"2025-12-03T10:44:48.263Z","group":{"key":"Seedream45","label":"Image Editing"},"highlighted":false,"kind":"inference","duration_estimate":1,"pinned":false}},{"endpoint_id":"fal-ai/sam-3/image","metadata":{"display_name":"Segment Anything Model 3","category":"image-to-image","description":"SAM 3 is a unified foundation model for promptable segmentation in images and videos. It can detect, segment, and track objects using text or visual prompts such as points, boxes, and masks. ","status":"active","tags":["segmentation","mask","real-time"],"updated_at":"2026-10-20T22:21:55.344Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/rabbit/kJhu6OfXaBwWYM1PUrWAL_6519f8ea79d649a9bead2e6118f4b997.jpg","model_url":"https://fal.run/fal-ai/sam-3/image","license_type":"commercial","date":"2025-11-20T19:45:11.630Z","group":{"key":"sam3","label":"Image to Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/v3/standard/image-to-video","metadata":{"display_name":"Kling Video v3 Image to Video [Standard]","category":"image-to-video","description":"Kling 3.0 Standard: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support.","status":"active","tags":["image-to-video"],"updated_at":"2026-04-26T22:25:17.147Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8cfcdb/TywpxxNj5_vDG8AUw3Yum_e2172b5c00e64a91a434ab5a38e496f0.jpg","model_url":"https://fal.run/fal-ai/kling-video/v3/standard/image-to-video","license_type":"commercial","date":"2026-02-04T15:48:44.935Z","group":{"key":"kling-v3","label":"Image To Video (standard)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"openrouter/router","metadata":{"display_name":"OpenRouter","category":"llm","description":"Run any LLM with fal. Access Claude (Anthropic), ChatGPT / GPT-5 / GPT-4o (OpenAI), Gemini (Google), Grok (xAI), DeepSeek, Llama (Meta), Qwen (Alibaba), Mistral, and 200+ more models through a single API. Supports reasoning, structured output, and streaming. Powered by OpenRouter.","status":"active","tags":[],"updated_at":"2026-05-06T21:21:33.117Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/rabbit/ZNwvLfWhMW6FsYU4bwn2N_365de1c02b7c4c42bec7659c157b6da4.jpg","model_url":"https://fal.run/openrouter/router","license_type":"commercial","date":"2025-11-12T20:17:58.937Z","group":{"key":"openrouter/router","label":"Any LLM"},"highlighted":false,"kind":"inference","stream_url":"https://fal.run/openrouter/router/stream","pinned":false}},{"endpoint_id":"fal-ai/elevenlabs/music","metadata":{"display_name":"Elevenlabs Music","category":"text-to-audio","description":"Generate high quality, realistic music with fine controls using Elevenlabs Music!","status":"active","tags":["music","text-to-music"],"updated_at":"2026-09-15T03:31:04.015Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a875694/SZffdb8layV90JxfN5fkP_d2048a658d9e4dc9973598f3542833a0.jpg","model_url":"https://fal.run/fal-ai/elevenlabs/music","license_type":"commercial","date":"2025-12-22T15:22:56.999Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"bytedance/seedream/v5/pro/text-to-image","metadata":{"display_name":"Seedream 5.0 Pro Text to Image","category":"text-to-image","description":"ByteDance's Seedream 5.0 Pro is flagship text-to-image model, with deep-thinking prompt understanding, native text in 14 languages, and precise control over dense layouts and structured designs.","status":"active","tags":["realism","typography","stylized"],"updated_at":"2026-10-20T22:53:35.171Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa1561a/Rb0DDLUI2sx4gevoh1HKt.jpg","model_url":"https://fal.run/bytedance/seedream/v5/pro/text-to-image","license_type":"commercial","date":"2026-07-07T20:10:11.334Z","group":{"key":"seedream-5-pro","label":"Text to Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"blackforestlabs/flux-3-max/image-to-video","metadata":{"display_name":"FLUX 3 Max Image to Video","category":"image-to-video","description":"fal’s FLUX 3 Max is a post-trained variant of FLUX 3 Video, tuned for stronger prompt adherence and better visual quality while optimized for lower latency.","status":"active","tags":["image-to-video","fast","audio"],"updated_at":"2026-10-28T20:23:04.519Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaf0ae2/vqNYPsX9h49SQulyxqJyL.jpg","model_url":"https://fal.run/blackforestlabs/flux-3-max/image-to-video","license_type":"commercial","date":"2026-10-16T01:41:04.623Z","group":{"key":"flux-3-max","label":"Image to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/flux-pro/v1.1-ultra","metadata":{"display_name":"FLUX1.1 [pro] ultra","category":"text-to-image","description":"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.","status":"active","tags":["high-res","realism"],"updated_at":"2026-04-21T17:47:24.374Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/flux-pro-v1-1-ultra.webp","model_url":"https://fal.run/fal-ai/flux-pro/v1.1-ultra","license_type":"commercial","date":"2024-12-17T00:00:00.000Z","group":{"key":"flux-pro","label":"FLUX 1.1 [pro] (ultra)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/elevenlabs/tts/multilingual-v2","metadata":{"display_name":"ElevenLabs TTS Multilingual v2","category":"text-to-audio","description":"Generate multilingual text-to-speech audio using ElevenLabs TTS Multilingual v2.","status":"active","tags":["audio"],"updated_at":"2026-06-24T10:35:06.936Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f91b4/QzoZAeoc-h1TLhttOaE7K_jZHvV4ZG.png","model_url":"https://fal.run/fal-ai/elevenlabs/tts/multilingual-v2","license_type":"commercial","date":"2025-02-27T00:00:00.000Z","group":{"key":"elevenlabs-audio","label":"TTS Multilingual v2"},"highlighted":false,"kind":"inference","stream_url":"https://fal.run/fal-ai/elevenlabs/tts/multilingual-v2/stream","pinned":false}},{"endpoint_id":"fal-ai/flux-2-pro/edit","metadata":{"display_name":"FLUX 2 Pro Edit","category":"image-to-image","description":"Text-to-image generation with FLUX.2 [pro] from Black Forest Labs. Optimized for maximum quality, exceptional photorealism and artistic images.","status":"active","tags":[],"updated_at":"2026-10-20T22:19:33.767Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/penguin/eZetcrsZI6AQLCD3f5gaI_b173ae004bdd4108bd1be54eb6e49c7a.jpg","model_url":"https://fal.run/fal-ai/flux-2-pro/edit","license_type":"commercial","date":"2025-11-23T00:13:41.404Z","group":{"key":"Flux2-Pro","label":"Image Editing"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/esrgan","metadata":{"display_name":"Upscale Images","category":"image-to-image","description":"Upscale images by a given factor.","status":"active","tags":["upscaling","high-res"],"updated_at":"2026-04-21T17:45:19.095Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/esrgan.webp?v=2","thumbnail_animated_url":"https://storage.googleapis.com/falserverless/gallery/esrgan-animated.webp?v=2","model_url":"https://fal.run/fal-ai/esrgan","github_url":"https://github.com/xinntao/Real-ESRGAN/blob/master/LICENSE","license_type":"commercial","date":"2023-10-30T00:00:00.000Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"elevenlabs/music/v2.5","metadata":{"display_name":"Elevenlabs Music v2.5","category":"text-to-audio","description":"Generate high quality, realistic music with fine controls using Elevenlabs Music v2.5!","status":"active","tags":["music","text-to-music"],"updated_at":"2026-10-02T19:10:00.967Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaa6adb/-Z3Ays503mRIC-atq70g8.jpg","model_url":"https://fal.run/elevenlabs/music/v2.5","license_type":"commercial","date":"2026-09-14T17:20:06.936Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/z-image/turbo","metadata":{"display_name":"Z Image Turbo","category":"text-to-image","description":"Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.","status":"active","tags":["turbo","z-image","fast"],"updated_at":"2026-07-09T03:35:06.702Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/koala/Pvji5sM6n6oNIo-p0Xsn__245f3d4eb5df4952aa80ec74f4afd7f2.jpg","model_url":"https://fal.run/fal-ai/z-image/turbo","license_type":"commercial","date":"2025-11-26T14:38:10.381Z","group":{"key":"z-image-turbo","label":"Text to Image"},"highlighted":false,"kind":"inference","pinned":false,"training_endpoint_ids":["fal-ai/z-image-trainer","fal-ai/z-image-turbo-trainer-v2"]}},{"endpoint_id":"minimax/h3-max/text-to-video","metadata":{"display_name":"MiniMax H3 Max Text to Video","category":"text-to-video","description":"fal's H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-10-30T18:44:30.635Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa7657e/LlavC7cCdZ_GGyvyglA82.jpg","model_url":"https://fal.run/minimax/h3-max/text-to-video","license_type":"commercial","date":"2026-08-23T17:56:01.222Z","group":{"key":"hailuo-03-new-turbo","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"bytedance/seedance-2.5/us/reference-to-video","metadata":{"display_name":"Seedance 2.5 US Reference to Video","category":"image-to-video","description":"US-hosted ByteDance Seedance 2.5 generates video with native audio from up to 30 images, 10 videos, and 10 audio references. Supports reference-guided generation, video editing, and extension at 480p, 720p or 1080p.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-10-29T22:02:47.829Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaafd55/ogacIYGKhsmZQEk3gCfK-.jpg","model_url":"https://fal.run/bytedance/seedance-2.5/us/reference-to-video","license_type":"commercial","date":"2026-09-19T01:18:10.313Z","group":{"key":"seedance-2.5-us","label":"Reference to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"alibaba/wan-3.0/reference-to-video","metadata":{"display_name":"Wan 3.0","category":"video-to-video","description":"Wan 3.0 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-10-20T22:08:25.620Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa4e980/FY0Yw0B-_KVknj6qtv5sp.jpg","model_url":"https://fal.run/alibaba/wan-3.0/reference-to-video","license_type":"commercial","date":"2026-08-03T23:56:31.060Z","group":{"key":"Wan30","label":"Reference to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"blackforestlabs/flux-3/edit-image","metadata":{"display_name":"Flux 3 Image","category":"image-to-image","description":"FLUX 3 Image Edit from Black Forest Labs makes precise local edits without changing the rest of the image, and combines up to 10 references into one balanced, well-composed result.","status":"active","tags":["flux-3-image","black-forest-labs","multi-reference"],"updated_at":"2026-10-20T22:18:29.352Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aacace0/cuYCs5EDeB5znT34LrInr.jpg","model_url":"https://fal.run/blackforestlabs/flux-3/edit-image","license_type":"commercial","date":"2026-10-01T09:42:05.751Z","group":{"key":"flux-3-image","label":"Edit"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/minimax/speech-2.8-hd","metadata":{"display_name":"MiniMax Speech 2.8 [HD]","category":"text-to-speech","description":"Generate speech from text prompts and different voices using the MiniMax Speech-2.8 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.","status":"active","tags":[],"updated_at":"2026-05-07T21:20:34.572Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8d0e4a/5FhhsQ0BicVC_DZ_BDLGL_895a8e6af34848f8844c20244c3e4672.jpg","model_url":"https://fal.run/fal-ai/minimax/speech-2.8-hd","license_type":"commercial","date":"2026-02-04T00:13:29.621Z","group":{"key":"minimax-speech","label":"Text To Speech 2.8 HD"},"highlighted":false,"kind":"inference","stream_url":"https://fal.run/fal-ai/minimax/speech-2.8-hd/stream","pinned":false}},{"endpoint_id":"fal-ai/bytedance/seedream/v4/edit","metadata":{"display_name":"Bytedance Seedream V4 Edit","category":"image-to-image","description":"A new-generation image creation model ByteDance, Seedream 4.0 integrates image generation and image editing capabilities into a single, unified architecture.","status":"active","tags":["stylized","transform","editing"],"updated_at":"2026-04-26T21:58:12.077Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/elephant/lBQrYkMMpOYBrsUc7T56n_3f3e07d132b742eda53bb80c0647c768.jpg","model_url":"https://fal.run/fal-ai/bytedance/seedream/v4/edit","license_type":"commercial","date":"2025-09-09T08:30:47.714Z","group":{"key":"bytedance-image","label":"Seedream 4.0 Edit"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/v2.6/pro/image-to-video","metadata":{"display_name":"Kling Video v2.6 Image to Video","category":"image-to-video","description":"Kling 2.6 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation.","status":"active","tags":[],"updated_at":"2026-10-20T22:32:26.498Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a84aa9c/tRb6fibztV71jrhSPfdqP_3359db6ee74a4e4e9fb408a00b02e114.jpg","model_url":"https://fal.run/fal-ai/kling-video/v2.6/pro/image-to-video","license_type":"commercial","date":"2025-12-02T09:01:46.898Z","group":{"key":"kling-video/v2.6","label":"Image to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"kling/v4/reference-to-video","metadata":{"display_name":"Kling 4.0 Reference to Video","category":"video-to-video","description":"Kling 4.0 generates videos from text prompts and image or video references at 720p or 1080p, with durations from 3 to 30 seconds and per-shot prompts.  ","status":"active","tags":["reference-to-video","multi-shot","image-reference","video-reference","kling"],"updated_at":"2026-10-23T16:50:56.400Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaea014/-781kCHOSCW9vaMcaPfMS.jpg","model_url":"https://fal.run/kling/v4/reference-to-video","license_type":"commercial","date":"2026-10-16T15:21:08.011Z","group":{"key":"kling-v4","label":"Reference to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"alibaba/wan-3.0/image-to-video","metadata":{"display_name":"Wan 3.0","category":"image-to-video","description":"Wan 3.0 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-10-20T22:08:22.709Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa4eab2/NRKAFB7Ix6zejRmcdJ4ZM.jpg","model_url":"https://fal.run/alibaba/wan-3.0/image-to-video","license_type":"commercial","date":"2026-08-03T23:59:45.555Z","group":{"key":"Wan30","label":"Image to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"meta/muse-image/edit","metadata":{"display_name":"Meta Muse Image Edit","category":"image-to-image","description":"Meta's Muse Image model does precise edits that change only what you ask, stay coherent across turns, and compose from multiple reference images.","status":"active","tags":["realism","typography","stylized","editing"],"updated_at":"2026-08-26T23:18:56.367Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa743e9/p2RjYTFPCviexLZ_6oYmv.jpg","model_url":"https://fal.run/meta/muse-image/edit","license_type":"commercial","date":"2026-08-21T19:14:53.788Z","group":{"key":"meta-muse-image","label":"Image Editing"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"minimax/h3/image-to-video","metadata":{"display_name":"MiniMax H3 Image to Video","category":"image-to-video","description":"MiniMax H3 is a frontier video model. This endpoint animates a supplied image into 2K video, using it as the opening frame or pairs a first and last frame to control a transition between two images with the aspect ratio following the input.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-08-25T17:41:07.462Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa42dac/wjm-S2eWgG8vU2uJoRwPx.jpg","model_url":"https://fal.run/minimax/h3/image-to-video","license_type":"commercial","date":"2026-07-31T05:54:55.532Z","group":{"key":"hailuo-03-new","label":"Image to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/sync-lipsync/v3","metadata":{"display_name":"sync-3 Lipsync","category":"video-to-video","description":"sync-3 most powerful lipsync model yet, featuring native visual intelligence for professional-quality video.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-06-22T17:36:40.628Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9460ff/hUjOvIu-6_JSEZr9SeFN5_8f82f538ee3246f3942ba081b0e28d3c.jpg","model_url":"https://fal.run/fal-ai/sync-lipsync/v3","license_type":"commercial","date":"2026-04-06T11:59:40.659Z","group":{"key":"sync-3","label":"Video to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/bytedance/seedream/v4.5/text-to-image","metadata":{"display_name":"Bytedance Seedream V4.5 Text To Image","category":"text-to-image","description":"A new-generation image creation model ByteDance, Seedream 4.5 integrates image generation and image editing capabilities into a single, unified architecture.","status":"active","tags":["stylized","transform"],"updated_at":"2026-04-26T21:58:12.077Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a84c771/1bdm3n1K8bRK-TzYjLF04_57edae699adf457a8a66ae6665a17e3a.jpg","model_url":"https://fal.run/fal-ai/bytedance/seedream/v4.5/text-to-image","license_type":"commercial","date":"2025-12-03T10:46:15.916Z","group":{"key":"Seedream45","label":"Text to Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/birefnet","metadata":{"display_name":"Birefnet Background Removal","category":"image-to-image","description":"bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS)","status":"active","tags":["background removal","segmentation","high-res","utility"],"updated_at":"2026-05-13T20:07:10.362Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/birefnet.webp","thumbnail_animated_url":"https://storage.googleapis.com/falserverless/gallery/birefnet-animated.webp","model_url":"https://fal.run/fal-ai/birefnet","license_type":"commercial","date":"2024-02-27T00:00:00.000Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/wizper","metadata":{"display_name":"Wizper (Whisper v3 -- fal.ai edition)","category":"speech-to-text","description":"[Experimental] Whisper v3 Large -- but optimized by our inference wizards. Same WER, double the performance!","status":"active","tags":["transcription","speech"],"updated_at":"2026-04-21T17:56:32.256Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/wizper.webp","thumbnail_animated_url":"https://storage.googleapis.com/falserverless/gallery/wizper-animated.webp","model_url":"https://fal.run/fal-ai/wizper","github_url":"https://github.com/openai/whisper/blob/main/LICENSE","date":"2024-04-08T00:00:00.000Z","highlighted":false,"pinned":false}},{"endpoint_id":"google/gemini-omni-flash/v1.1/image-to-video","metadata":{"display_name":"Gemini Omni Flash 1.1 Image to Video","category":"image-to-video","description":"Gemini Omni Flash 1.1 is Google's multimodal video model. This endpoint animates a still image into video with synchronized audio, extending a single frame into coherent motion that reflects the logic of the real world.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-10-20T22:39:01.452Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa7d026/PJ7ZGzXOLHWc0V7C2aN9r.jpg","model_url":"https://fal.run/google/gemini-omni-flash/v1.1/image-to-video","license_type":"commercial","date":"2026-08-25T23:13:54.630Z","group":{"key":"gemini-omni-11","label":"Image to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/bytedance/seedream/v4/text-to-image","metadata":{"display_name":"Bytedance Seedream V4 Text To Image","category":"text-to-image","description":"A new-generation image creation model ByteDance, Seedream 4.0 integrates image generation and image editing capabilities into a single, unified architecture.","status":"active","tags":["stylized","transform"],"updated_at":"2026-06-24T10:33:46.501Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f91a9/M7ElK8gRPRsRHnAOcaujK_lpIjpXxA.png","model_url":"https://fal.run/fal-ai/bytedance/seedream/v4/text-to-image","license_type":"commercial","date":"2025-09-09T08:27:00.849Z","group":{"key":"bytedance-image","label":"Seedream 4.0 Text to Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/flux-2/klein/9b","metadata":{"display_name":"FLUX.2 [klein] 9B","category":"text-to-image","description":"Text-to-image generation with FLUX.2 [klein] 9B from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities.","status":"active","tags":[],"updated_at":"2026-07-09T03:35:23.028Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8a7f3c/90FKDpwtSCZTqOu0jUI-V_64c1a6ec0f9343908d9efa61b7f2444b.jpg","model_url":"https://fal.run/fal-ai/flux-2/klein/9b","license_type":"commercial","date":"2026-01-15T12:24:18.909Z","group":{"key":"klein","label":"9B Text to Image"},"highlighted":false,"kind":"inference","stream_url":"https://fal.ai/models/fal-ai/flux-2/klein/9b/stream","pinned":false}},{"endpoint_id":"fal-ai/kling-video/ai-avatar/v2/standard","metadata":{"display_name":"Kling AI Avatar v2 Standard","category":"image-to-video","description":"Kling AI Avatar v2 Standard:  Endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters","status":"active","tags":[],"updated_at":"2026-04-26T22:25:17.147Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a84f39a/V_Zy58fLpOlS1jN3balTm_bf4c62c984b34a1597340c007fac8fe8.jpg","model_url":"https://fal.run/fal-ai/kling-video/ai-avatar/v2/standard","license_type":"commercial","date":"2025-12-04T12:58:33.998Z","group":{"key":"Kling-Avatar","label":"Kling AI Avatar v2 Standard"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"minimax/h3/reference-to-video","metadata":{"display_name":"MiniMax H3 Reference to Video","category":"image-to-video","description":"MiniMax H3 is a frontier video model. This endpoint generates 2K video from multimodal references up to 9 images for subject and style, 3 video clips for motion, and 3 audio clips each cited in the prompt by order, keeping subjects consistent while following the referenced motion and audio.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-08-25T17:41:07.462Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa42dcf/3VDKabd7ifjCezrQpdfEI.jpg","model_url":"https://fal.run/minimax/h3/reference-to-video","license_type":"commercial","date":"2026-07-31T05:55:07.987Z","group":{"key":"hailuo-03-new","label":"Reference to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/flux-lora","metadata":{"display_name":"FLUX.1 [dev] with LoRAs","category":"text-to-image","description":"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.","status":"active","tags":["lora","personalization"],"updated_at":"2026-06-24T10:31:43.297Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f91af/UMrx6t6mc59z33d20WIQP_iBIZYKKq.png","model_url":"https://fal.run/fal-ai/flux-lora","license_type":"commercial","date":"2024-08-01T00:00:00.000Z","group":{"key":"flux-lora","label":"Text to Image"},"highlighted":false,"kind":"inference","pinned":false,"training_endpoint_ids":["fal-ai/flux-lora-fast-training","fal-ai/turbo-flux-trainer","fal-ai/flux-lora-portrait-trainer"]}},{"endpoint_id":"fal-ai/minimax/speech-02-hd","metadata":{"display_name":"MiniMax Speech-02 HD","category":"text-to-speech","description":"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.","status":"active","tags":["speech"],"updated_at":"2026-06-24T10:36:41.475Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f91b5/Li_VoZtaOd5__F9GMv1O4_yPTcO4eQ.png","model_url":"https://fal.run/fal-ai/minimax/speech-02-hd","license_type":"commercial","date":"2025-05-06T16:17:49.560Z","group":{"key":"minimax-speech","label":"Text To Speech 2.0 HD"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"google/gemini-3.8-flash-tts","metadata":{"display_name":"Gemini 3.8 Flash TTS","category":"text-to-speech","description":"Generate expressive speech with Gemini 3.8 Flash TTS. Choose from 30 voices, direct delivery with style instructions, and create single-speaker narration or two-speaker dialogue.","status":"active","tags":["text-to-speech","audio","dialogue","voiceover"],"updated_at":"2026-09-30T01:19:34.727Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aabd875/3gAgS2GOPVAkwRanZZpN7.jpg","model_url":"https://fal.run/google/gemini-3.8-flash-tts","license_type":"commercial","date":"2026-09-25T12:38:25.540Z","group":{"key":"gemini-38","label":"Flash"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"minimax/h3-max-turbo/text-to-video","metadata":{"display_name":"H3 Max Turbo Text to Video","category":"text-to-video","description":"fal's H3 Max Turbo is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-10-30T18:46:09.233Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa8d50b/vj4BiCoQwOlmK7ku4KBZq.jpg","model_url":"https://fal.run/minimax/h3-max-turbo/text-to-video","license_type":"commercial","date":"2026-09-02T16:44:59.129Z","group":{"key":"hailuo-03-new-max-turbo","label":"Text to Video Max Turbo"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"minimax/h3-max/lip-sync/image-to-video","metadata":{"display_name":"H3 Max Lip Sync Image to Video","category":"image-to-video","description":"H3 Max Lip Sync generates a video from an image and supplied audio, synchronizing mouth movements to the soundtrack. It supports optional transcription guidance and output resolutions from 480p to 2K.","status":"active","tags":["lipsync","animation","audio"],"updated_at":"2026-10-20T22:39:43.329Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaac3b8/AFRNL61Lm2CQntBtg88Hv.jpg","model_url":"https://fal.run/minimax/h3-max/lip-sync/image-to-video","license_type":"commercial","date":"2026-09-17T08:31:16.184Z","group":{"key":"hailuo-03-new-turbo","label":"Lip Sync"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"xai/grok-imagine-image/edit","metadata":{"display_name":"Grok Imagine Image","category":"image-to-image","description":"Edit images precisely with xAI's Grok Imagine model","status":"active","tags":["grok","xai","image-editing"],"updated_at":"2026-04-26T22:32:05.599Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8a0dc7/kv2XmZ5em8Kb2-7oXZndp_b897f79cbc564e1d8f4e5d5c71710c2b.jpg","model_url":"https://fal.run/xai/grok-imagine-image/edit","license_type":"commercial","date":"2026-01-29T00:29:41.002Z","group":{"key":"grok-imagine-image","label":"Edit Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/o3/pro/video-to-video/edit","metadata":{"display_name":"Kling O3 Edit Video [Pro]","category":"video-to-video","description":"Edit videos using Kling O3 from Kling Team!","status":"active","tags":["video-to-video"],"updated_at":"2026-10-20T22:31:55.808Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8cfcd0/jgn9feXep4nJXWf0tg1cf_6867c6921b6a4015a1906c8e02a7ef9d.jpg","model_url":"https://fal.run/fal-ai/kling-video/o3/pro/video-to-video/edit","license_type":"commercial","date":"2026-02-04T15:48:44.935Z","group":{"key":"kling-o3","label":"Edit Video (pro)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"bytedance/seedance-2.5/us/image-to-video","metadata":{"display_name":"Seedance 2.5 US Image to Video","category":"image-to-video","description":"US-hosted ByteDance Seedance 2.5 animates still images with synchronized audio and optional end-frame control. Generate videos up to 30 seconds at 480p, 720p or 1080p.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-10-29T22:02:47.829Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaafd55/0c84v0HjbaufuRK6VuCFC.jpg","model_url":"https://fal.run/bytedance/seedance-2.5/us/image-to-video","license_type":"commercial","date":"2026-09-19T01:16:54.572Z","group":{"key":"seedance-2.5-us","label":"Image to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/flux-2","metadata":{"display_name":"FLUX 2","category":"text-to-image","description":"Text-to-image generation with FLUX.2 [dev] from Black Forest Labs. Enhanced realism, crisper text generation, and native editing capabilities.","status":"active","tags":[],"updated_at":"2026-05-27T00:51:44.726Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/penguin/zSBCJtPpeIQwR5AC_IamX_b1e1137961754e4d851907c21f8c20cd.jpg","model_url":"https://fal.run/fal-ai/flux-2","license_type":"commercial","date":"2025-11-23T00:15:07.672Z","group":{"key":"Flux2","label":"Text to Image"},"highlighted":false,"kind":"inference","stream_url":"https://fal.ai/models/fal-ai/flux-2/stream","pinned":false}},{"endpoint_id":"fal-ai/bytedance/seedance/v1.5/pro/image-to-video","metadata":{"display_name":"Bytedance Seedance V1.5 Pro Image To Video","category":"image-to-video","description":"Generate videos with audio with Seedance 1.5 (supports start & end frame) ","status":"active","tags":["bytedance","seedance","audio"],"updated_at":"2026-10-20T22:09:01.679Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a876c74/q6J8OsmO08A3zCFGCtsUj_cb48562eeef345b29269689dd4f95671.jpg","model_url":"https://fal.run/fal-ai/bytedance/seedance/v1.5/pro/image-to-video","license_type":"commercial","date":"2025-12-23T06:56:11.614Z","group":{"key":"seedance-v15","label":"Image to Video Pro v1.5"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/flux-pro/v1/fill","metadata":{"display_name":"FLUX.1 [pro] Fill","category":"image-to-image","description":"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.","status":"active","tags":["editing"],"updated_at":"2026-04-21T17:47:29.481Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/fluxpro.jpg","model_url":"https://fal.run/fal-ai/flux-pro/v1/fill","license_type":"commercial","date":"2024-11-21T00:00:00.000Z","group":{"key":"flux-pro","label":"FLUX.1 [pro] Fill"},"highlighted":false,"pinned":false}},{"endpoint_id":"fal-ai/bria/expand","metadata":{"display_name":"Bria Expand Image","category":"image-to-image","description":"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","status":"active","tags":["outpainting"],"updated_at":"2026-07-25T00:34:11.218Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa39a0b/u8UzBIeqFp9gmGGgwbbEi.jpg","model_url":"https://fal.run/fal-ai/bria/expand","license_type":"commercial","date":"2024-12-19T00:00:00.000Z","group":{"key":"bria","label":"Expand Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/elevenlabs/speech-to-text","metadata":{"display_name":"ElevenLabs Speech to Text","category":"speech-to-text","description":"Generate text from speech using ElevenLabs advanced speech-to-text model.","status":"active","tags":["speech"],"updated_at":"2026-10-14T20:51:02.384Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/web-examples/elevenlabs/elevenlabs_thumbnail.webp","model_url":"https://fal.run/fal-ai/elevenlabs/speech-to-text","license_type":"commercial","date":"2025-02-27T00:00:00.000Z","group":{"key":"e11-speech-to-text","label":"Scribe V1"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/hunyuan-3d/v3.1/pro/image-to-3d","metadata":{"display_name":"Hunyuan 3D Pro Image to 3D","category":"image-to-3d","description":"Generate 3D models from images with Hunyuan 3D Pro","status":"active","tags":["3d","hunyuan","image-to-3d"],"updated_at":"2026-10-20T22:15:06.339Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8c1eed/a9u-FinZ2o0AGqcGFlRoD_5c16e7c0e1ae412cacc53893cae95698.jpg","model_url":"https://fal.run/fal-ai/hunyuan-3d/v3.1/pro/image-to-3d","license_type":"commercial","date":"2026-01-27T22:01:04.639Z","group":{"key":"hunyuan-3d","label":"Hunyuan 3D Pro Image to 3D"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/ai-avatar/v2/pro","metadata":{"display_name":"Kling AI Avatar v2 Pro","category":"image-to-video","description":"Kling AI Avatar v2 Pro: The premium endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters","status":"active","tags":[],"updated_at":"2026-04-26T22:25:17.147Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a84f36f/CYuWetfKsuQC0MR6G4EG8_cd62fa685e9844aaaf086c293eddb2ee.jpg","model_url":"https://fal.run/fal-ai/kling-video/ai-avatar/v2/pro","license_type":"commercial","date":"2025-12-04T12:58:48.770Z","group":{"key":"Kling-Avatar","label":"Kling AI Avatar v2 Pro"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/demucs","metadata":{"display_name":"Demucs","category":"audio-to-audio","description":"SOTA stemming model for voice, drums, bass, guitar and more.","status":"active","tags":["audio"],"updated_at":"2026-04-21T17:44:58.841Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/tiger/WAcACXLL5-atiw1MGvH4g_7cb10ff246844b9c9298bbe98e431df7.jpg","model_url":"https://fal.run/fal-ai/demucs","license_type":"commercial","date":"2025-10-27T21:40:53.677Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/stable-audio-25/text-to-audio","metadata":{"display_name":"Stable Audio 2.5","category":"text-to-audio","description":"Generate high quality music and sound effects using Stable Audio 2.5 from StabilityAI","status":"active","tags":["audio"],"updated_at":"2026-06-24T10:39:31.754Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f91ae/mtqDUea-jzlnWg_odMe1j_bB5cIBlf.png","model_url":"https://fal.run/fal-ai/stable-audio-25/text-to-audio","license_type":"commercial","date":"2025-09-10T11:50:27.666Z","group":{"key":"stable-audio-25","label":"Text to Audio"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/sync-lipsync/v2","metadata":{"display_name":"Sync Lipsync 2.0","category":"video-to-video","description":"Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization with Sync Lipsync 2.0 model","status":"active","tags":["animation","lip sync"],"updated_at":"2026-10-07T21:54:13.785Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f9a45/-kfzjmJkk91iujX9QQTT3_nAfB0uuc.png","model_url":"https://fal.run/fal-ai/sync-lipsync/v2","license_type":"commercial","date":"2025-04-01T18:57:06.699Z","group":{"key":"sync-lipsync","label":"Lipsync 2.0"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"blackforestlabs/flux-3/text-to-image","metadata":{"display_name":"Flux 3 Image","category":"text-to-image","description":"FLUX 3 Image is Black Forest Labs' newest image model. Generate detailed, well-composed images in native 2K and 4K with precise layout control and improved text rendering.","status":"active","tags":["flux-3-image","black-forest-labs","typography","4k"],"updated_at":"2026-10-20T22:18:32.379Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aacace0/ZQ6bVh40FVDtOdqeEYIt7.jpg","model_url":"https://fal.run/blackforestlabs/flux-3/text-to-image","license_type":"commercial","date":"2026-10-01T09:42:01.969Z","group":{"key":"flux-3-image","label":"Text to Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/clarity-upscaler","metadata":{"display_name":"Clarity Upscaler","category":"image-to-image","description":"Clarity upscaler for upscaling images with high very fidelity.","status":"active","tags":["upscaling"],"updated_at":"2026-05-06T21:22:23.372Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/controlnet-tile-upscaler.webp","thumbnail_animated_url":"https://storage.googleapis.com/falserverless/gallery/controlnet-tile-upscaler-animated.webp","model_url":"https://fal.run/fal-ai/clarity-upscaler","license_type":"commercial","date":"2024-02-04T00:00:00.000Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"topaz/upscale/image/precision","metadata":{"display_name":"Topaz Upscale Image Precision","category":"image-to-image","description":"Professional photo upscaling powered by Topaz Labs. Gigapixel precision models (Standard V2, High Fidelity, Low Resolution, CGI, Text Refine) enlarge images faithfully up to 4x. Best for photos that must stay true to the original.","status":"active","tags":["upscale","image"],"updated_at":"2026-08-31T17:55:19.832Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa5f4d2/jP4o7RDGaEMhvRaykFtct.jpg","model_url":"https://fal.run/topaz/upscale/image/precision","license_type":"commercial","date":"2026-08-11T21:18:29.191Z","group":{"key":"topaz-upscale-image","label":"Upscale Image Precision"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/bytedance/omnihuman/v1.5","metadata":{"display_name":"Bytedance Omnihuman V1.5","category":"image-to-video","description":"Omnihuman v1.5 is a new and improved version of Omnihuman. It generates video using an image of a human figure paired with an audio file. It produces vivid, high-quality videos where the character’s emotions and movements maintain a strong correlation with the audio.","status":"active","tags":["image-to-video","lipsync",""],"updated_at":"2026-04-21T17:44:32.423Z","is_favorited":null,"thumbnail_url":"https://v3.fal.media/files/penguin/E4JFEyBXM1DccJUOvp5_e_6414b61bc2e141edb34671e5308addef.jpg","model_url":"https://fal.run/fal-ai/bytedance/omnihuman/v1.5","license_type":"commercial","date":"2025-09-23T14:00:56.925Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/bytedance-upscaler/upscale/video","metadata":{"display_name":"Bytedance Upscaler Upscale Video","category":"video-to-video","description":"Upscale videos with Bytedance's video upscaler.","status":"active","tags":["upscaler","video","bytedance"],"updated_at":"2026-10-20T22:30:18.854Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/kangaroo/LorVpq4fAORdnn1YHRM-A_d801feeaa1764cefb7de0c3381ecaf84.jpg","model_url":"https://fal.run/fal-ai/bytedance-upscaler/upscale/video","license_type":"commercial","date":"2025-10-31T16:15:01.762Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"kling/v4/video-to-video/edit","metadata":{"display_name":"Kling 4.0 Video Editing","category":"video-to-video","description":"Kling 4.0 edits an input video using text instructions and optional image references, producing 3 to 30-second videos at 720p or 1080p.  ","status":"active","tags":["video-to-video","video-editing","image-reference","kling"],"updated_at":"2026-10-23T16:50:29.059Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaea01a/b-K4ZK92VhCWa6fE4LMS9.jpg","model_url":"https://fal.run/kling/v4/video-to-video/edit","license_type":"commercial","date":"2026-10-16T15:21:55.287Z","group":{"key":"kling-v4","label":"Video Editing"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"tripo3d/h3.1/image-to-3d","metadata":{"display_name":"Tripo H3.1 Image to 3D","category":"image-to-3d","description":"Generate high-quality 3D models from a single image using Tripo H3.1.","status":"active","tags":["3d","image-to-3d","3d-generation","tripo"],"updated_at":"2026-10-20T22:17:05.091Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a95559a/DXp1uAfHvZsXt-GJ9-Bp-_47060336be0749d5bd751ca6359cd2f9.jpg","model_url":"https://fal.run/tripo3d/h3.1/image-to-3d","license_type":"commercial","date":"2026-04-07T19:19:14.338Z","group":{"key":"tripo-h3.1","label":"Image to 3D"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"meta/muse-image/text-to-image","metadata":{"display_name":"Meta Muse Image Text to Image","category":"text-to-image","description":"Meta's Muse Image model has faithful instruction-following and exceptional visual fidelity, with fine details like text, plots, and QR codes rendered accurately.","status":"active","tags":["realism","typography","stylized"],"updated_at":"2026-08-26T23:18:31.609Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa743db/nScihj1tWzLbmaEA3mKE2.jpg","model_url":"https://fal.run/meta/muse-image/text-to-image","license_type":"commercial","date":"2026-08-21T19:14:59.559Z","group":{"key":"meta-muse-image","label":"Text to Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"xai/grok-imagine-image/v2.0/edit","metadata":{"display_name":"Grok Imagine Image 2.0","category":"image-to-image","description":"Edit images with xAi's Grok Imagine 2.0 model.","status":"active","tags":["xai","grok","image-editing"],"updated_at":"2026-08-20T23:47:27.128Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa53f9f/NPxHgnCK_ldUc0dOfNe1q.jpg","model_url":"https://fal.run/xai/grok-imagine-image/v2.0/edit","license_type":"commercial","date":"2026-08-06T12:22:53.411Z","group":{"key":"imagine20","label":"Edit Image"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/elevenlabs/tts/turbo-v2.5","metadata":{"display_name":"ElevenLabs TTS Turbo v2.5","category":"text-to-speech","description":"Generate high-speed text-to-speech audio using ElevenLabs TTS Turbo v2.5.","status":"active","tags":["audio"],"updated_at":"2026-04-21T17:45:15.737Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/web-examples/elevenlabs/elevenlabs_thumbnail.webp","model_url":"https://fal.run/fal-ai/elevenlabs/tts/turbo-v2.5","license_type":"commercial","date":"2025-02-27T00:00:00.000Z","group":{"key":"elevenlabs-audio","label":"TTS Turbo v2.5"},"highlighted":false,"kind":"inference","stream_url":"https://fal.run/fal-ai/elevenlabs/tts/turbo-v2.5/stream","pinned":false}},{"endpoint_id":"alibaba/wan-3.0-prime/reference-to-video","metadata":{"display_name":"Wan 3.0 Prime","category":"video-to-video","description":"Wan 3.0 Prime Reference-to-Video combines reference images, videos, and audio into a unified video with fast generation and strong multimodal coherence. It follows character identity, visual style, movement, and sound cues across references to create controlled, consistent, and production-ready results.","status":"active","tags":["reference","video"],"updated_at":"2026-10-20T22:54:59.893Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa79464/AfVcXUCY_wyxlQVsAGpx2.jpg","model_url":"https://fal.run/alibaba/wan-3.0-prime/reference-to-video","license_type":"commercial","date":"2026-08-24T04:43:49.156Z","group":{"key":"Wan30prime","label":"Reference to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"blackforestlabs/flux-3/klein/edit-image","metadata":{"display_name":"FLUX.3 Klein Image Editing","category":"image-to-image","description":"Edits and composes images from text instructions and up to ten references with FLUX.3 Klein, with optional bounding-box controls for object placement and transformation.","status":"active","tags":["image editing","image to image","reference images","typography","graphic design","flux"],"updated_at":"2026-10-28T16:29:20.834Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aae6141/RHrU_CVUIV0D1xwgnu0Dk.jpg","model_url":"https://fal.run/blackforestlabs/flux-3/klein/edit-image","license_type":"commercial","date":"2026-10-14T18:40:57.255Z","group":{"key":"flux-3-klein","label":"Image Editing"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/flux-2/klein/9b/edit","metadata":{"display_name":"FLUX.2 [klein] 9B","category":"image-to-image","description":"Image-to-image editing with FLUX.2 [klein] 9B from Black Forest Labs. Precise modifications using natural language descriptions and hex color control.","status":"active","tags":[],"updated_at":"2026-10-20T22:19:47.483Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8a7f50/X8ffS5h55gcigsNZoNC7O_52e6b383ac214d2abe0a2e023f03de88.jpg","model_url":"https://fal.run/fal-ai/flux-2/klein/9b/edit","license_type":"commercial","date":"2026-01-15T12:25:09.939Z","group":{"key":"klein","label":"9B Image Edit"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"topaz/upscale/video/precision","metadata":{"display_name":"Topaz Upscale Video Precision","category":"video-to-video","description":"Professional video upscaling powered by Topaz Labs. Precision models (Proteus, Artemis, Iris, Dione, Theia, Gaia, Rhea) enhance footage up to 4x while staying faithful to the source. Best for clean, natural upscales of real-world footage.","status":"active","tags":["upscale","video"],"updated_at":"2026-10-20T21:56:47.299Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa5f1ec/6RruEcb1mzuNDFal3KsPz.jpg","model_url":"https://fal.run/topaz/upscale/video/precision","license_type":"commercial","date":"2026-08-11T19:10:25.098Z","group":{"key":"topaz-upscale","label":"Upscale Video Precision"},"highlighted":false,"kind":"inference","pinned":false}}],"next_cursor":"Mg","has_more":true}