{"models":[{"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":"2026-10-02T18:53:14.384Z","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 Max"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"bytedance/seedance-2.5/text-to-video","metadata":{"display_name":"Seedance 2.5 Text to Video","category":"text-to-video","description":"Dreamina Seedance 2.5 generates native 30-second single-shot video at up to 720p from a single text prompt, reasoning about the whole shot at once so motion, lighting, and subject identity stay coherent from first frame to last.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-08-28T18:45:54.815Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa30edb/Ckq9fPYW5fP_nqcCC-SHh.jpg","model_url":"https://fal.run/bytedance/seedance-2.5/text-to-video","license_type":"commercial","date":"2026-07-20T21:03:22.667Z","group":{"key":"Seedance-25","label":"Text to Video"},"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":"2026-10-02T18:53:14.384Z","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":"fal-ai/kling-video/v3/pro/text-to-video","metadata":{"display_name":"Kling Video v3 Text to Video [Pro]","category":"text-to-video","description":"Kling 3.0 Pro: Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation, with multi-shot support.","status":"active","tags":["text-to-video"],"updated_at":"2026-04-26T22:25:17.147Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8cfd13/t6TSkWzl6cFAzvO1PCdDu_f38263f637d245929f03881454951540.jpg","model_url":"https://fal.run/fal-ai/kling-video/v3/pro/text-to-video","license_type":"commercial","date":"2026-02-04T15:48:44.935Z","group":{"key":"kling-v3","label":"Text to Video (pro)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/veo3.1/fast","metadata":{"display_name":"Veo 3.1 Fast","category":"text-to-video","description":"Faster and more cost effective version of Google's Veo 3.1! ","status":"active","tags":[],"updated_at":"2026-04-28T16:29:09.509Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/lion/o5x4rjXr3fAEwQgr4Y5vp_69ee214c658e428ba2f8f8b054d70a0e.jpg","model_url":"https://fal.run/fal-ai/veo3.1/fast","license_type":"commercial","date":"2025-10-08T17:05:11.177Z","group":{"key":"veo3.1","label":"Text to Video (Fast)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/v3/standard/text-to-video","metadata":{"display_name":"Kling Video v3 Text to Video [Standard]","category":"text-to-video","description":"Kling 3.0 Standard: Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation, with multi-shot support.","status":"active","tags":["text-to-video"],"updated_at":"2026-04-26T22:25:17.147Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8cfc9f/dei5OqFRB9HK8AgSHwk8f_9a5eea197b3045d1be55aedb0213f6f9.jpg","model_url":"https://fal.run/fal-ai/kling-video/v3/standard/text-to-video","license_type":"commercial","date":"2026-02-04T15:48:44.935Z","group":{"key":"kling-v3","label":"Text To Video (standard)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"bytedance/seedance-2.0/text-to-video","metadata":{"display_name":"Seedance 2.0 Text to Video API","category":"text-to-video","description":"ByteDance's most advanced text-to-video model. Cinematic output with native audio, multi-shot editing, real-world physics, and director-level camera control.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-07-10T18:12:05.187Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9c2f13/XcRHMX9gZIMSYL7ImArbn_ed7636768b1f41d286c66ed5ebc0521d.jpg","model_url":"https://fal.run/bytedance/seedance-2.0/text-to-video","license_type":"commercial","date":"2026-04-01T18:49:18.123Z","group":{"key":"seedance-2.0-fal","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"alibaba/wan-3.0/text-to-video","metadata":{"display_name":"Wan Text to Video","category":"text-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":"2026-08-26T04:29:40.594Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa4e92e/GZJ8RhOR3CRLj5vpHI2ah.jpg","model_url":"https://fal.run/alibaba/wan-3.0/text-to-video","license_type":"commercial","date":"2026-08-03T22:57:05.176Z","group":{"key":"Wan30","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/lipsync/audio-to-video","metadata":{"display_name":"Kling LipSync Audio-to-Video","category":"text-to-video","description":"Kling LipSync is an audio-to-video model that generates realistic lip movements from audio input.","status":"active","tags":["audio to video","lipsync"],"updated_at":"2026-04-26T22:25:17.147Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/elephant/njNipNC0TkA9fJguiS1NB_c75b090e2ebb4d9581d21d66cfc4a0d3.jpg","model_url":"https://fal.run/fal-ai/kling-video/lipsync/audio-to-video","license_type":"commercial","date":"2025-03-27T00:00:00.000Z","group":{"key":"kling-video-lipsync","label":"LipSync (Audio to Video)"},"highlighted":false,"kind":"inference","duration_estimate":12,"pinned":false}},{"endpoint_id":"fal-ai/veo3.1","metadata":{"display_name":"Veo 3.1","category":"text-to-video","description":"Veo 3.1 by Google, the most advanced AI video generation model in the world. With sound on!","status":"active","tags":[],"updated_at":"2026-04-28T16:29:09.509Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/tiger/TGTZBJyLk9HdwjB6SB90e.png","model_url":"https://fal.run/fal-ai/veo3.1","license_type":"commercial","date":"2025-10-08T17:01:21.561Z","group":{"key":"veo3.1","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/v2.5-turbo/pro/text-to-video","metadata":{"display_name":"Kling v2.5 Text to Video","category":"text-to-video","description":"Kling 2.5 Turbo Pro: Top-tier text-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.","status":"active","tags":["animation","stylized"],"updated_at":"2026-04-26T22:25:17.147Z","is_favorited":null,"thumbnail_url":"https://v3.fal.media/files/panda/6YaK9lV7ySsUA9I3dUp5r_8a807b0c8e2641db9e345107ab8a809e.jpg","model_url":"https://fal.run/fal-ai/kling-video/v2.5-turbo/pro/text-to-video","license_type":"commercial","date":"2025-09-22T22:48:44.637Z","group":{"key":"kling-video-v25","label":"2.5 Turbo (Text to Video) Pro"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"minimax/h3/text-to-video","metadata":{"display_name":"MiniMax H3 Text to Video","category":"text-to-video","description":"MiniMax H3 is a frontier video model. This endpoint generates video from a text prompt alone, rendering at 2K in durations from 5 to 15 seconds across seven aspect ratios.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-08-26T06:41:51.586Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa42d8c/uJC3CQO20PyPi5iM7eu3a.jpg","model_url":"https://fal.run/minimax/h3/text-to-video","license_type":"commercial","date":"2026-07-31T05:56:07.158Z","group":{"key":"hailuo-03-new","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"google/gemini-omni-flash/v1.1/text-to-video","metadata":{"display_name":"Gemini Omni Flash 1.1 Text to Video","category":"text-to-video","description":"Gemini Omni Flash 1.1 is Google's multimodal video model. This endpoint generates video with synchronized native audio from a text prompt, grounded in Gemini's real-world knowledge and physics understanding, with cinematic camera control expressed in natural language.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-09-01T21:51:13.659Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa7d019/qS1ezqi3w1fIQVwJCCw-r.jpg","model_url":"https://fal.run/google/gemini-omni-flash/v1.1/text-to-video","license_type":"commercial","date":"2026-08-25T23:11:57.494Z","group":{"key":"gemini-omni-11","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/veo3.1/lite","metadata":{"display_name":"Veo3.1 Lite Text to Video","category":"text-to-video","description":"Veo 3.1 Lite balances practical utility with professional capabilities, supporting Text-to-Video and Image-to-Video","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-04-28T16:29:09.509Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a946102/2xgttJeG8mvXo4sZCyUWG_d59c1e8028224e278f47fb7cb3f8d878.jpg","model_url":"https://fal.run/fal-ai/veo3.1/lite","license_type":"commercial","date":"2026-03-31T18:33:44.437Z","group":{"key":"veo3.1","label":"Text to Video (Lite)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"bytedance/seedance-2.0/fast/text-to-video","metadata":{"display_name":"Seedance 2.0 Fast Text to Video","category":"text-to-video","description":"ByteDance's most advanced text-to-video model, fast tier. Lower latency and cost with cinematic output, native audio, multi-shot editing, and director-level camera control.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-05-29T18:20:56.533Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9c2f1c/JJWaVP5VEiyeEiqaEXWli_321bd6ab4d3f4ee8bf0003a332814416.jpg","model_url":"https://fal.run/bytedance/seedance-2.0/fast/text-to-video","license_type":"commercial","date":"2026-04-01T18:47:38.648Z","group":{"key":"seedance-2.0-fal","label":"Text to Video Fast"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"xai/grok-imagine-video/text-to-video","metadata":{"display_name":"Grok Imagine Video","category":"text-to-video","description":"Generate videos with audio from text using Grok Imagine Video.","status":"active","tags":["xai","grok","t2v","text-to-video"],"updated_at":"2026-04-26T22:32:05.599Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8a0dd6/EDbXLIstjumsrgtGfV4NA_b75e853d42ea45f695d07e434331bdfb.jpg","model_url":"https://fal.run/xai/grok-imagine-video/text-to-video","license_type":"commercial","date":"2026-01-29T00:26:17.072Z","group":{"key":"grok-imagine-video","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/v2.6/pro/text-to-video","metadata":{"display_name":"Kling Video v2.6 Text to Video","category":"text-to-video","description":"Kling 2.6 Pro: Top-tier text-to-video with cinematic visuals, fluid motion, and native audio generation.","status":"active","tags":[],"updated_at":"2026-07-21T18:22:20.463Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a84aab6/uMErfUYxq7gJBJ0-MOKS7_2640fde44b6049a59bc34adf72e38ed7.jpg","model_url":"https://fal.run/fal-ai/kling-video/v2.6/pro/text-to-video","license_type":"commercial","date":"2025-12-02T09:03:38.171Z","group":{"key":"kling-video/v2.6","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"blackforestlabs/flux-3/text-to-video","metadata":{"display_name":"Flux 3 Text to Video","category":"text-to-video","description":"FLUX 3 is Black Forest Labs' frontier video model. This endpoint generates video directly from a text prompt, translating a written description into motion, composition, and scene.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-08-18T16:52:44.888Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa2a1ba/d-iPMFNVrztnc6ysi2tPQ.jpg","model_url":"https://fal.run/blackforestlabs/flux-3/text-to-video","license_type":"commercial","date":"2026-07-17T15:59:29.756Z","group":{"key":"flux-3-new","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/bytedance/seedance/v1.5/pro/text-to-video","metadata":{"display_name":"Bytedance Seedance V1.5 Pro Text To Video","category":"text-to-video","description":"Generate videos with audio with Seedance 1.5","status":"active","tags":["bytedance","seedance","audio"],"updated_at":"2026-04-21T17:44:34.169Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a876c8c/7ieGsrCnzZmiES-uDGNXs_d16568d7e335443fb7a8dece1f9a9b0d.jpg","model_url":"https://fal.run/fal-ai/bytedance/seedance/v1.5/pro/text-to-video","license_type":"commercial","date":"2025-12-23T06:59:34.673Z","group":{"key":"seedance-v15","label":"Text to Video Pro v1.5"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"google/gemini-omni-flash","metadata":{"display_name":"Gemini Omni Flash","category":"text-to-video","description":"Creates video with synchronized audio from text input. Grounded in Gemini's real-world knowledge, with improved physics understanding for more coherent motion and interaction.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-07-09T23:22:29.670Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa0649d/TFqtIbw6p_p4rMT-44N8X.jpg","model_url":"https://fal.run/google/gemini-omni-flash","license_type":"commercial","date":"2026-06-30T16:35:19.139Z","group":{"key":"gemini-omni-flash","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/pixverse/v6/text-to-video","metadata":{"display_name":"PixVerse V6 Text To Video","category":"text-to-video","description":"Pixverse's latest v6 Model.","status":"active","tags":["text-to-video"],"updated_at":"2026-06-17T18:20:01.178Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a940489/sEtg0Kth_fWhHMR5MS664_222abe748d96461ba565ba860c3061d8.jpg","model_url":"https://fal.run/fal-ai/pixverse/v6/text-to-video","license_type":"commercial","date":"2026-03-29T09:43:09.635Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"alibaba/wan-3.0-prime/text-to-video","metadata":{"display_name":"Wan 3.0 Prime","category":"text-to-video","description":"Wan 3.0 Prime Text-to-Video transforms written prompts into polished videos with accelerated generation, fluid motion, strong scene fidelity, and coherent visual storytelling. Built for fast creative iteration, it brings complex ideas to life while preserving visual detail and cinematic consistency throughout each shot.","status":"active","tags":["text","video"],"updated_at":"2026-08-24T06:03:26.646Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa793dd/pgwWiHzdAkUN08U5j8_6f.jpg","model_url":"https://fal.run/alibaba/wan-3.0-prime/text-to-video","license_type":"commercial","date":"2026-08-24T04:26:21.187Z","group":{"key":"Wan30prime","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"bytedance/seedance-2.0/mini/text-to-video","metadata":{"display_name":"Seedance 2.0 Mini Text to Video","category":"text-to-video","description":"Seedance 2.0 Mini is a faster version of Seedance 2.0 that brings great performance and high generation speed at a lower cost.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-07-17T03:48:03.287Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f7e59/QR4fszdxC1WKHff7uSfwK_027c3c79ba7b49ab855976d21fc1171b.jpg","model_url":"https://fal.run/bytedance/seedance-2.0/mini/text-to-video","license_type":"commercial","date":"2026-06-23T18:05:01.397Z","group":{"key":"seedance-2.0-fal","label":"Text to Video mini"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/o3/pro/text-to-video","metadata":{"display_name":"Kling O3 Text to Video [Pro]","category":"text-to-video","description":"Generate realistic videos using Kling O3 from Kling Team!","status":"active","tags":["text-to-video"],"updated_at":"2026-04-26T22:25:17.147Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8c3ad2/Z4ZRnSwVTn1ZsiXuSVpE-_ee73b123ab38450684f4902430914242.jpg","model_url":"https://fal.run/fal-ai/kling-video/o3/pro/text-to-video","license_type":"commercial","date":"2026-02-04T15:48:44.935Z","group":{"key":"kling-o3","label":"Text To Video (pro)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"bytedance/seedance-2.5/us/text-to-video","metadata":{"display_name":"Seedance 2.5 US Text to Video","category":"text-to-video","description":"US-hosted ByteDance Seedance 2.5 generates cinematic video from text with synchronized audio, up to 30-second duration, and 480p, 720p or 1080p output.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-09-30T01:19:34.727Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaafd52/5TgJyrglFwBoFB-lx_IZg.jpg","model_url":"https://fal.run/bytedance/seedance-2.5/us/text-to-video","license_type":"commercial","date":"2026-09-19T01:16:28.104Z","group":{"key":"seedance-2.5-us","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"xai/grok-imagine-video/v1.5/text-to-video","metadata":{"display_name":"Grok Imagine Video 1.5 Text to Video","category":"text-to-video","description":"Generate videos from prompts with audio using xAI's Grok Imagine 1.5 Video model.\n","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-08-31T17:51:41.474Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa44035/2zU-0vqvgLDc1B_n0vut0.jpg","model_url":"https://fal.run/xai/grok-imagine-video/v1.5/text-to-video","license_type":"commercial","date":"2026-07-29T22:44:13.415Z","group":{"key":"imagine15","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/v3/turbo/standard/text-to-video","metadata":{"display_name":"Kling Video V3 Standard Turbo Text to Video","category":"text-to-video","description":"Kling 3.0 Turbo Standard is a fast, cost-efficient video generation model that turns text prompts directly into 720P video with native audio, optimized for rapid iteration and high-volume production","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-06-24T00:21:44.881Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9e8d89/LDScfQJoDfPCdVK2OWRky_c8428cc1efc84391b93c08e4a2529c35.jpg","model_url":"https://fal.run/fal-ai/kling-video/v3/turbo/standard/text-to-video","license_type":"commercial","date":"2026-06-16T17:29:22.634Z","group":{"key":"kling-v3-turbo","label":"Text to Video (Standard)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/o3/standard/text-to-video","metadata":{"display_name":"Kling O3 Text to Video [Standard]","category":"text-to-video","description":"Generate realistic videos using Kling O3 from Kling Team!","status":"active","tags":["text-to-video"],"updated_at":"2026-04-26T22:25:17.147Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8cfce0/-uK5wEuvOst_sCRKg3PqO_0e1bf50a5a624877b395523e43c3fcc0.jpg","model_url":"https://fal.run/fal-ai/kling-video/o3/standard/text-to-video","license_type":"commercial","date":"2026-02-04T15:48:44.935Z","group":{"key":"kling-o3","label":"Text to Video (standard)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kandinsky6-pro/text-to-video","metadata":{"display_name":"Kandinsky 6.0 Pro","category":"text-to-video","description":"Kandinsky 6.0 Pro is Kandinsky Lab's flagship text-to-video model, generating high-resolution clips with cinematic motion and precise prompt adherence.","status":"active","tags":["text-to-video","kandinsky","lightweight"],"updated_at":"2026-10-06T10:34:35.248Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aad2929/Z9eM0SNw8Gulk3vXDU5K8.jpg","model_url":"https://fal.run/fal-ai/kandinsky6-pro/text-to-video","license_type":"commercial","date":"2026-10-05T12:44:36.136Z","group":{"key":"kandinsky6-pro","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"xai/grok-imagine-video/v1.5/lite/text-to-video","metadata":{"display_name":"Grok Imagine Video 1.5 Lite Text to Video","category":"text-to-video","description":"Generate videos from text prompts using xAI's Grok Imagine Video 1.5 Lite model.","status":"active","tags":["text-to-video"],"updated_at":"2026-10-02T22:48:46.859Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aac8c97/q0dnsNb5Wra4NzkWywH-S.jpg","model_url":"https://fal.run/xai/grok-imagine-video/v1.5/lite/text-to-video","license_type":"commercial","date":"2026-10-01T20:22:24.341Z","group":{"key":"grok-imagine15-lite","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/minimax/hailuo-02/standard/text-to-video","metadata":{"display_name":"MiniMax Hailuo 02 [Standard] (Text to Video)","category":"text-to-video","description":"MiniMax Hailuo-02 Text To Video API (Standard, 768p): Advanced video generation model with 768p resolution","status":"active","tags":[],"updated_at":"2026-04-21T17:52:01.991Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-1.jpg","model_url":"https://fal.run/fal-ai/minimax/hailuo-02/standard/text-to-video","license_type":"commercial","date":"2025-06-18T00:40:08.840Z","group":{"key":"hailuo-02","label":"Text to Video (standard) "},"highlighted":false,"kind":"inference","duration_estimate":4,"pinned":false}},{"endpoint_id":"fal-ai/kling-video/v3/turbo/pro/text-to-video","metadata":{"display_name":"Kling Video V3 Turbo Pro Text to Video","category":"text-to-video","description":"Generate high quality 1080p videos using Kling's Turbo 3.0 model, with improved lipsync and multishot generation capabilities.","status":"active","tags":["kling","v3","1080p","turbo"],"updated_at":"2026-06-24T00:21:44.881Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9e8d77/SDWDZwZ_Rz7vgKlPopK8x_be12e85845f242deb7a652ef22831bfa.jpg","model_url":"https://fal.run/fal-ai/kling-video/v3/turbo/pro/text-to-video","license_type":"commercial","date":"2026-06-16T17:24:27.367Z","group":{"key":"kling-v3-turbo","label":"Text to Video (Pro)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/wan-25-preview/text-to-video","metadata":{"display_name":"Wan 2.5 Text to Video","category":"text-to-video","description":"Wan 2.5 text-to-video model.","status":"active","tags":[],"updated_at":"2026-04-27T18:04:43.973Z","is_favorited":null,"thumbnail_url":"https://v3.fal.media/files/koala/yojKCMBipiqJvLr9a3sLC_deec1d2b5b2c4019bc353f6060ec0c09.jpg","model_url":"https://fal.run/fal-ai/wan-25-preview/text-to-video","license_type":"commercial","date":"2025-09-24T02:07:33.047Z","group":{"key":"wan-25-preview","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kandinsky6-lite/text-to-video","metadata":{"display_name":"Kandinsky 6.0 Lite","category":"text-to-video","description":"Kandinsky 6.0 Lite is a lightweight, high-speed text-to-video model from Kandinsky Lab, built for fast, efficient generation with strong prompt adherence.","status":"active","tags":["text-to-video","kandinsky","lightweight"],"updated_at":"2026-10-06T10:33:47.878Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aad28fa/A2SiDGpqWJmGTm_X2yuqg.jpg","model_url":"https://fal.run/fal-ai/kandinsky6-lite/text-to-video","license_type":"commercial","date":"2026-10-05T12:39:15.388Z","group":{"key":"kandinsky6-lite","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/ltx-2.3/text-to-video/fast","metadata":{"display_name":"LTX 2.3 Video Fast","category":"text-to-video","description":"LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-07-13T19:05:24.786Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a90df05/Q8IcsF5FX1zYHwG048tqT_320cb845b0c74f44920f1c6520981b9e.jpg","model_url":"https://fal.run/fal-ai/ltx-2.3/text-to-video/fast","license_type":"commercial","date":"2026-03-05T15:32:51.533Z","group":{"key":"ltx-2-3","label":"Text to Video (Fast)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/wan/v2.2-a14b/text-to-video","metadata":{"display_name":"Wan-2.2 Text-to-Video A14B","category":"text-to-video","description":"Wan-2.2 text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts. ","status":"active","tags":["text to video","motion"],"updated_at":"2026-04-21T17:56:29.422Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-4.jpg","model_url":"https://fal.run/fal-ai/wan/v2.2-a14b/text-to-video","license_type":"commercial","date":"2025-07-28T16:14:33.355Z","group":{"key":"wan-v22-large","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/bytedance/seedance/v1/pro/fast/text-to-video","metadata":{"display_name":"Bytedance Seedance V1 Pro Fast Text To Video","category":"text-to-video","description":"Text to Video endpoint for Seedance 1.0 Pro Fast, a next-generation video model designed to deliver maximum performance at minimal cost","status":"active","tags":["bytedance","fast","motion"],"updated_at":"2026-04-21T17:44:37.016Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/monkey/vuOJvxcEA4z0fsRkw3r4Y_4930420a08f045c9ae3c401e3a6d20fc.jpg","model_url":"https://fal.run/fal-ai/bytedance/seedance/v1/pro/fast/text-to-video","license_type":"commercial","date":"2025-10-24T11:54:23.140Z","group":{"key":"seedance-v1","label":"Seedance 1.0 Pro Fast --Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/wan/v2.7/text-to-video","metadata":{"display_name":"Wan Text to Video","category":"text-to-video","description":"Wan 2.7 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":"2026-04-26T23:07:28.840Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a94047b/ktfxD5Hs3lGJdXwk7FurU_856b1abaad064b23bb2ae7dee66cf2f3.jpg","model_url":"https://fal.run/fal-ai/wan/v2.7/text-to-video","license_type":"commercial","date":"2026-03-28T20:45:33.782Z","group":{"key":"Wan27","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/minimax/hailuo-2.3/standard/text-to-video","metadata":{"display_name":"MiniMax Hailuo 2.3 [Standard] (Text to Video)","category":"text-to-video","description":"MiniMax Hailuo-2.3 Text To Video API (Standard, 768p): Advanced text-to-video generation model with 768p resolution","status":"active","tags":["text-to-video"],"updated_at":"2026-04-21T17:52:05.453Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/elephant/j3hSIKLqmWT7NXmIwTUQ0_1ec8fc1d7a53473fac7c2892ff459693.jpg","model_url":"https://fal.run/fal-ai/minimax/hailuo-2.3/standard/text-to-video","license_type":"commercial","date":"2025-10-27T13:06:48.176Z","group":{"key":"hailuo-23","label":"Text To Video (standard)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/bytedance/seedance/v1/pro/text-to-video","metadata":{"display_name":"Seedance 1.0 Pro","category":"text-to-video","description":"Seedance 1.0 Pro, a high quality video generation model developed by Bytedance.","status":"active","tags":[],"updated_at":"2026-04-21T17:44:38.216Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-1.jpg","model_url":"https://fal.run/fal-ai/bytedance/seedance/v1/pro/text-to-video","license_type":"commercial","date":"2025-06-16T16:22:01.447Z","group":{"key":"seedance-v1","label":"Seedance 1.0 Pro -- Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"blackforestlabs/flux-3/text-to-video/draft","metadata":{"display_name":"Flux 3 Text To Video Draft","category":"text-to-video","description":"FLUX.3 is Black Forest Labs' frontier audio/video model. Generate fast, low-cost draft previews from a text prompt, with a reusable draft cache for full-quality enhancement.\n","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-08-13T17:29:01.019Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa4eec9/YRkVDI1WNJNET3ET9H26M.jpg","model_url":"https://fal.run/blackforestlabs/flux-3/text-to-video/draft","license_type":"commercial","date":"2026-08-04T02:53:20.458Z","group":{"key":"flux-3-new-draft","label":"Text to Video Draft"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"alibaba/happy-horse/text-to-video","metadata":{"display_name":"Happy Horse","category":"text-to-video","description":"Generate 1080p video with synchronized native audio from a text prompt. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.","status":"active","tags":["happy-horse",""],"updated_at":"2026-04-28T16:30:33.940Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a975556/O6OH_JWwjWGMR4ujnmQPC_b3d0863dc24748e28b1e44880d861185.jpg","model_url":"https://fal.run/alibaba/happy-horse/text-to-video","license_type":"commercial","date":"2026-04-24T18:10:56.231Z","group":{"key":"happy-horse","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/wan/v2.2-a14b/text-to-video/turbo","metadata":{"display_name":"Wan","category":"text-to-video","description":"Wan-2.2 turbo text-to-video is a video model that generates high-quality videos with high visual quality and motion diversity from text prompts. ","status":"active","tags":["text to video","motion"],"updated_at":"2026-04-21T17:56:30.547Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/fal_cdn/fal/for%20videos-4.jpg","model_url":"https://fal.run/fal-ai/wan/v2.2-a14b/text-to-video/turbo","license_type":"commercial","date":"2025-07-31T18:01:55.359Z","group":{"key":"wan-v22-turbo","label":"Text to Video (Turbo)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/ltx-video","metadata":{"display_name":"LTX Video (preview)","category":"text-to-video","description":"Generate videos from prompts using LTX Video","status":"active","tags":[],"updated_at":"2026-07-13T19:05:24.786Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/model_tests/cogvideox/panda.gif.gif","model_url":"https://fal.run/fal-ai/ltx-video","license_type":"research","date":"2024-10-04T00:00:00.000Z","group":{"key":"ltx-video","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/ltx-2.3/text-to-video","metadata":{"display_name":"LTX Video 2.3 Pro","category":"text-to-video","description":"LTX-2.3 is a high-quality, fast AI video model available in Pro and Fast variants for text-to-video, image-to-video, and audio-to-video.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-07-13T19:05:24.786Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a90def0/4BRBakcGh2ZvP4Nw02RJl_aec88be7e2714348b2195104cff18dfd.jpg","model_url":"https://fal.run/fal-ai/ltx-2.3/text-to-video","license_type":"commercial","date":"2026-03-05T15:30:04.535Z","group":{"key":"ltx-2-3","label":"Text to Video (Pro)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"wan/v2.6/text-to-video","metadata":{"display_name":"Wan v2.6 Text to Video","category":"text-to-video","description":"Wan 2.6 text-to-video model.","status":"active","tags":["text-to-video"],"updated_at":"2026-04-26T23:07:28.840Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a86d2d7/3WTDnIgc5z_RVh24RgF-D.png","model_url":"https://fal.run/wan/v2.6/text-to-video","license_type":"commercial","date":"2025-12-16T05:12:22.693Z","group":{"key":"v2.6","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/v3/4k/text-to-video","metadata":{"display_name":"Kling Video V3 Text to Video 4K","category":"text-to-video","description":"Kling's Native 4K is a video generation model that directly outputs professional-grade 4K video in one step, eliminating the need for post-production upscaling","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-07-17T19:12:30.157Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a970c17/m0f2ooX6jkF2UDw8yeU7w_0478d228dd9b4f58b26d5c833644465d.jpg","model_url":"https://fal.run/fal-ai/kling-video/v3/4k/text-to-video","license_type":"commercial","date":"2026-04-22T08:23:16.624Z","group":{"key":"kling-v3","label":"Text to Video (4K)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"alibaba/happy-horse/v1.1/text-to-video","metadata":{"display_name":"Happy Horse 1.1 Text to Video","category":"text-to-video","description":"Happy Horse 1.1 is Alibaba's #1-ranked video model. This text-to-video endpoint generates 1080p video with synchronized native audio and multilingual lip-sync from a text prompt alone.","status":"active","tags":["happy-horse","video","text"],"updated_at":"2026-07-01T05:09:20.564Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f395f/8hP5jLvVFWOWXKzo9BWRv_1b09aff553b045fb98313142db068d58.jpg","model_url":"https://fal.run/alibaba/happy-horse/v1.1/text-to-video","license_type":"commercial","date":"2026-06-21T19:48:05.751Z","group":{"key":"happy-horse-1.1","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"lightricks/ltx-2.5/text-to-video/fast","metadata":{"display_name":"Ltx 2.5 Text to Video Fast","category":"text-to-video","description":"LTX-2.5 is Lightricks' open-source audio-video model. This endpoint generates synchronized video and audio from a text prompt in a single pass, in a speed-optimized mode built for rapid iteration and previews.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-08-14T23:11:35.262Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa5ebb1/szS8gNC3Szq_suLVnrwmV.jpg","model_url":"https://fal.run/lightricks/ltx-2.5/text-to-video/fast","license_type":"commercial","date":"2026-08-11T14:35:56.314Z","group":{"key":"ltx-2.5-api","label":"Text to Video (Fast)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"lightricks/ltx-2.5/text-to-video/pro","metadata":{"display_name":"Ltx 2.5 Text to Video Fast","category":"text-to-video","description":"LTX-2.5 is Lightricks' open-source audio-video model. This endpoint generates synchronized video and audio from a text prompt in a single pass, in a quality-optimized mode for final, high-fidelity output.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-08-14T23:11:35.262Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa5eb39/hd2sKCSz-CxI-omfTEXYi.jpg","model_url":"https://fal.run/lightricks/ltx-2.5/text-to-video/pro","license_type":"commercial","date":"2026-08-11T14:24:06.314Z","group":{"key":"ltx-2.5-api","label":"Text to Video (Pro)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/pika/v2.2/text-to-video","metadata":{"display_name":"Pika Text to Video (v2.2)","category":"text-to-video","description":"Start with a simple text input to create dynamic generations that defy expectations in up to 1080p. Experience better image clarity and crisper, sharper visuals.","status":"active","tags":["editing","effects","animation"],"updated_at":"2026-04-21T17:52:43.976Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/panda/d7bGY17P07W2dKiNoWXfQ_fb8e23d259a44c5a893f04ae7a710b95.jpg","model_url":"https://fal.run/fal-ai/pika/v2.2/text-to-video","license_type":"commercial","date":"2025-03-14T00:00:00.000Z","group":{"key":"pika","label":"Text to Video (v2.2)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"luma/agent/ray/v3.2/text-to-video","metadata":{"display_name":"Luma Ray 3.2 Text to Video","category":"text-to-video","description":"Luma Ray 3.2 generates cinematic video from a text prompt, with control over resolution, duration, and seamless looping, plus reference images to lock in subject and style.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-06-15T21:36:15.554Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9d98a0/DwsmVaf6M6SVp2KIN3bId_321b3394d9f243de98b9f6295b4c48b5.jpg","model_url":"https://fal.run/luma/agent/ray/v3.2/text-to-video","license_type":"commercial","date":"2026-06-09T11:19:52.469Z","group":{"key":"ray-32","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/minimax/hailuo-2.3/pro/text-to-video","metadata":{"display_name":"MiniMax Hailuo 2.3 [Pro] (Text to Video)","category":"text-to-video","description":"MiniMax Hailuo-2.3 Text To Video API (Pro, 1080p): Advanced text-to-video generation model with 1080p resolution","status":"active","tags":["text-to-video"],"updated_at":"2026-04-21T17:52:04.297Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/kangaroo/x_n_LT1ApmpYZnZw8sdNq_0147471d0d7e4bbba8780820dee6a3da.jpg","model_url":"https://fal.run/fal-ai/minimax/hailuo-2.3/pro/text-to-video","license_type":"commercial","date":"2025-10-27T13:05:46.983Z","group":{"key":"hailuo-23","label":"Text To Video (pro)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/wan/v2.2-5b/text-to-video","metadata":{"display_name":"Wan v2.2 5B","category":"text-to-video","description":"Wan 2.2's 5B model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding","status":"active","tags":[],"updated_at":"2026-04-21T17:56:23.721Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/fal_cdn/fal/Sound-2.jpg","model_url":"https://fal.run/fal-ai/wan/v2.2-5b/text-to-video","license_type":"commercial","date":"2025-07-28T20:48:02.539Z","group":{"key":"wan-v22","label":"Text to Video (5B)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/wan-t2v","metadata":{"display_name":"Wan-2.1 Text-to-Video","category":"text-to-video","description":"Wan-2.1 is a text-to-video model that generates high-quality videos with high visual quality and motion diversity from text prompts","status":"active","tags":["text to video","motion"],"updated_at":"2026-04-21T17:56:08.038Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/fal_cdn/Fal_Visuals_V1_02.jpg","model_url":"https://fal.run/fal-ai/wan-t2v","license_type":"commercial","date":"2025-02-25T00:00:00.000Z","group":{"key":"wan-2.1","label":"Text-to-Video"},"highlighted":false,"kind":"inference","duration_estimate":1,"pinned":false}},{"endpoint_id":"fal-ai/kling-video/o3/4k/text-to-video","metadata":{"display_name":"Kling Video","category":"text-to-video","description":"Kling's Native 4K is a video generation model that directly outputs professional-grade 4K video in one step, eliminating the need for post-production upscaling","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-04-26T22:25:17.147Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9740a0/uJcikAkIJZE8L06x0HY5R_78d7451cfa254ef7bbd247305bc1b84c.jpg","model_url":"https://fal.run/fal-ai/kling-video/o3/4k/text-to-video","license_type":"commercial","date":"2026-04-22T08:27:30.591Z","group":{"key":"kling-o3","label":"Text to Video (4K)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/vidu/q3/text-to-video","metadata":{"display_name":"Vidu","category":"text-to-video","description":"Vidu's latest Q3 pro models","status":"active","tags":["text-to-video"],"updated_at":"2026-07-01T04:18:34.353Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8c9162/vH4Zl7noFCQBFqWM-eu9I_802e7d65387f44f0ae3eb0587b38422f.jpg","model_url":"https://fal.run/fal-ai/vidu/q3/text-to-video","license_type":"commercial","date":"2026-01-31T07:32:31.870Z","group":{"key":"Vidu Q3","label":"Text to Video "},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/pixverse/v5/text-to-video","metadata":{"display_name":"PixVerse V5 Text To Video","category":"text-to-video","description":"Generate high quality video clips from text and image prompts using PixVerse v5","status":"active","tags":[],"updated_at":"2026-06-17T18:20:01.178Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","model_url":"https://fal.run/fal-ai/pixverse/v5/text-to-video","license_type":"commercial","date":"2025-08-23T10:50:22.733Z","group":{"key":"pixverse-5","label":"Text to Video v5"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/minimax/video-01","metadata":{"display_name":"MiniMax (Hailuo AI) Video 01","category":"text-to-video","description":"Generate video clips from your prompts using MiniMax model","status":"active","tags":["motion","transformation"],"updated_at":"2026-04-21T17:52:13.503Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/red_clouds.jpg","model_url":"https://fal.run/fal-ai/minimax/video-01","date":"2024-02-13T00:00:00.000Z","group":{"key":"minimax-video","label":"Text to Video"},"highlighted":false,"pinned":false}},{"endpoint_id":"fal-ai/hunyuan-video","metadata":{"display_name":"Hunyuan Video","category":"text-to-video","description":"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.","status":"active","tags":["motion"],"updated_at":"2026-04-21T17:48:21.606Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/hunyuan-video.webp?v=1","model_url":"https://fal.run/fal-ai/hunyuan-video","license_type":"commercial","date":"2024-10-22T00:00:00.000Z","group":{"key":"hunyuan-text-to-video","label":"Text-to-Video"},"highlighted":false,"kind":"inference","duration_estimate":4,"pinned":false}},{"endpoint_id":"fal-ai/wan/v2.2-5b/text-to-video/fast-wan","metadata":{"display_name":"Wan","category":"text-to-video","description":"Wan 2.2's 5B FastVideo model produces up to 5 seconds of video 720p at 24FPS with fluid motion and powerful prompt understanding","status":"active","tags":["text to video","motion"],"updated_at":"2026-06-24T11:33:51.381Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f92cc/Y-jQHC5zfMnRI6aiLIxIw_ePJVrFgh.png","model_url":"https://fal.run/fal-ai/wan/v2.2-5b/text-to-video/fast-wan","license_type":"commercial","date":"2025-08-05T23:59:17.192Z","group":{"key":"wan-v22-fastwan","label":"Text to Video (FastWan 5B)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/pixverse/c1/text-to-video","metadata":{"display_name":"PixVerse C1 Text To Video","category":"text-to-video","description":"Generate film-grade videos from text prompts with native audio, up to 1080p and 15 seconds, using PixVerse C1.","status":"active","tags":["video-generation","text-to-video","pixverse","cinematic","film","1080p","audio"],"updated_at":"2026-06-17T18:20:01.178Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a957a29/F9h26mxs4zndIlypwPTV5_c4d0e69c4b514f5cb70075b8a5a6987c.jpg","model_url":"https://fal.run/fal-ai/pixverse/c1/text-to-video","license_type":"commercial","date":"2026-04-08T21:02:06.348Z","group":{"key":"pixverse-c1","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"creatify/boreal","metadata":{"display_name":"Boreal","category":"text-to-video","description":"Create product, UGC, and presenter videos with synchronized native audio from text, with optional image and audio inputs.","status":"active","tags":["native-audio","text-to-video","image-to-video","audio-to-video","advertising","product-video","ugc","presenter"],"updated_at":"2026-09-15T17:32:02.091Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaa89d0/IBrRMet9rPV0j4cgTurKs_boreal-thumbnail-v4.png","model_url":"https://fal.run/creatify/boreal","license_type":"commercial","date":"2026-09-15T14:51:22.917Z","group":{"key":"creatify-boreal","label":"Boreal"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/heygen/avatar5/digital-twin","metadata":{"display_name":"Heygen v5 Digital Twin","category":"text-to-video","description":"Create natural HeyGen Avatar V digital twin videos from text or audio, with lip-sync, optional backgrounds, captions, and MP4/WebM output.","status":"active","tags":["avatar","digital-twin","talking-avatar","text-to-video","lip-sync","heygen","video-generation"],"updated_at":"2026-07-01T05:00:07.079Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9aa011/vdGl5om9jDtRhB8kiH8LS_70badfd7deb047e1a3d8c0bf65609406.jpg","model_url":"https://fal.run/fal-ai/heygen/avatar5/digital-twin","license_type":"commercial","date":"2026-05-17T23:23:57.673Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"bytedance/seedance-2.0/us/text-to-video","metadata":{"display_name":"Seedance 2.0 US Text to Video","category":"text-to-video","description":"US hosted version of ByteDance's most advanced text-to-video model. Cinematic output with native audio, multi-shot editing, real-world physics, and director-level camera control.","status":"active","tags":["stylized","transform","lipsync"],"updated_at":"2026-09-30T01:20:17.001Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaa8c18/G-pLPV2kcuJH5WkGAe6od.jpg","model_url":"https://fal.run/bytedance/seedance-2.0/us/text-to-video","license_type":"commercial","date":"2026-09-15T16:58:14.090Z","group":{"key":"seedance-us","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/minimax/hailuo-02/pro/text-to-video","metadata":{"display_name":"MiniMax Hailuo 02 [Pro] (Text to Video)","category":"text-to-video","description":"MiniMax Hailuo-02 Text To Video API (Pro, 1080p): Advanced video generation model with 1080p resolution","status":"active","tags":[],"updated_at":"2026-04-21T17:52:00.824Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/fal_cdn/fal/Upscale-2.jpg","model_url":"https://fal.run/fal-ai/minimax/hailuo-02/pro/text-to-video","license_type":"commercial","date":"2025-06-18T00:41:11.159Z","group":{"key":"hailuo-02","label":"Text to Video (pro) "},"highlighted":false,"kind":"inference","duration_estimate":8,"pinned":false}},{"endpoint_id":"fal-ai/ltx-video-13b-distilled","metadata":{"display_name":"LTX Video-0.9.7 13B Distilled","category":"text-to-video","description":"Generate videos from prompts using LTX Video-0.9.7 13B Distilled and custom LoRA","status":"active","tags":["video","ltx-video","text-to-video"],"updated_at":"2026-07-13T19:05:24.786Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/fal_cdn/fal/Training-4.jpg","model_url":"https://fal.run/fal-ai/ltx-video-13b-distilled","license_type":"commercial","date":"2025-05-17T01:49:06.775Z","group":{"key":"ltx-video-13b-distilled","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false,"training_endpoint_ids":["fal-ai/ltx-video-trainer"],"inference_endpoint_ids":["fal-ai/ltx-video-trainer"]}},{"endpoint_id":"fal-ai/pixverse/v4.5/text-to-video","metadata":{"display_name":"PixVerse V4.5 Text To Video","category":"text-to-video","description":"Generate high quality video clips from text and image prompts using PixVerse v4.5","status":"active","tags":["stylized","transform"],"updated_at":"2026-06-17T18:20:01.178Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/pixverse-v3.5.webp","model_url":"https://fal.run/fal-ai/pixverse/v4.5/text-to-video","license_type":"commercial","date":"2025-05-15T15:48:45.845Z","group":{"key":"pixverse-45","label":"Text to Video v4.5"},"highlighted":false,"kind":"inference","duration_estimate":1,"pinned":false}},{"endpoint_id":"fal-ai/pixverse/v5.5/text-to-video","metadata":{"display_name":"PixVerse V5.5 Text To Video","category":"text-to-video","description":"Generate high quality video clips from text and image prompts using PixVerse v5.5","status":"active","tags":["text-to-video"],"updated_at":"2026-06-24T11:34:03.822Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f92cc/poyvEi1p-X7BvVUUq5ZdG_qMPjpi2n.png","model_url":"https://fal.run/fal-ai/pixverse/v5.5/text-to-video","license_type":"commercial","date":"2025-12-01T16:59:49.183Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/heygen/v3/video-agent","metadata":{"display_name":"Heygen Video Agent","category":"text-to-video","description":"Generate videos with a single prompt. Describe what you want in plain text, and the agent handles avatar selection, scripting, scene composition - all in one. \n","status":"active","tags":[],"updated_at":"2026-04-26T23:11:58.879Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a967e3d/nTk59cJwBYo_fP1nr7be0_580a3501e6ab43e3854f054f865c3642.jpg","model_url":"https://fal.run/fal-ai/heygen/v3/video-agent","license_type":"commercial","date":"2026-04-16T14:17:14.120Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/v1.6/standard/effects","metadata":{"display_name":"Kling 1.6","category":"text-to-video","description":"Generate video clips from your prompts using Kling 1.6 (std)","status":"active","tags":[],"updated_at":"2026-06-24T11:45:17.018Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f92d5/yDlKh1ALP5JpLxc3GNe_T_VNGQo4Bj.png","model_url":"https://fal.run/fal-ai/kling-video/v1.6/standard/effects","license_type":"commercial","date":"2025-03-06T00:00:00.000Z","group":{"key":"kling-video-effects","label":"v1.6 Effects (std)"},"highlighted":false,"kind":"inference","duration_estimate":6,"pinned":false}},{"endpoint_id":"minimax/h3-max/styles/vhs","metadata":{"display_name":"H3 Max VHS","category":"text-to-video","description":"Generates 768p VHS-style video with audio from text prompts or an optional first-frame image. Supports 5–15 second clips and adjustable tape damage, from subtle analog noise to strong tracking distortion.","status":"active","tags":["vhs","analog","retro","tape-damage"],"updated_at":"2026-10-02T18:53:14.384Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaad605/J4zSNIgmNAoArcg4BwPNp.jpg","model_url":"https://fal.run/minimax/h3-max/styles/vhs","license_type":"commercial","date":"2026-09-17T21:32:21.470Z","group":{"key":"hailuo-03-new-turbo-lora","label":"VHS"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"minimax/h3-max/styles/retro-toon-70s","metadata":{"display_name":"H3 Max Retro Toon 70s","category":"text-to-video","description":"Generates 768p video with audio in a retro 1970s hand-painted animation style from text prompts or an optional first-frame image. Supports durations of 5–15 seconds.","status":"active","tags":["retro","1970s","hand-painted","animation"],"updated_at":"2026-10-02T18:53:14.384Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaad5fe/vIqC2SSPOPaR305av-iHV.jpg","model_url":"https://fal.run/minimax/h3-max/styles/retro-toon-70s","license_type":"commercial","date":"2026-09-17T21:31:46.115Z","group":{"key":"hailuo-03-new-turbo-lora","label":"Retro Toon 70s"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"minimax/h3/text-to-video/lora","metadata":{"display_name":"MiniMax H3 Text to Video LoRA","category":"text-to-video","description":"Generate video with synchronized audio from a text prompt using MiniMax H3; load a trained LoRA at adjustable strength to lock in style, character, or motion.","status":"active","tags":["utility","editing"],"updated_at":"2026-09-01T21:35:15.577Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aa4c826/eJSEtWE-CowTbabIAcO5f.jpg","model_url":"https://fal.run/minimax/h3/text-to-video/lora","license_type":"commercial","date":"2026-08-02T23:26:20.888Z","group":{"key":"hailuo-03-lora","label":"Text to Video LoRA"},"highlighted":false,"kind":"inference","pinned":false,"training_endpoint_ids":["minimax/h3/t2v/trainer"]}},{"endpoint_id":"fal-ai/vidu/q3/text-to-video/turbo","metadata":{"display_name":"Vidu","category":"text-to-video","description":"Vidu's Q3 Turbo Model.","status":"active","tags":["text-to-video"],"updated_at":"2026-07-01T04:17:28.592Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8d6e01/BMufnODRfLxM62qPgxeYS_fe39c8df0dd848f1bfc25a0710be1c1e.jpg","model_url":"https://fal.run/fal-ai/vidu/q3/text-to-video/turbo","license_type":"commercial","date":"2026-02-06T20:22:55.043Z","group":{"key":"Vidu Q3","label":"Text to Video (Turbo)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"minimax/h3-max/styles/hand-drawn","metadata":{"display_name":"H3 Max Hand Drawn","category":"text-to-video","description":"Generates 768p video with audio in a hand-drawn animation style from text prompts or an optional first-frame image. Supports durations of 5–15 seconds.","status":"active","tags":["hand-drawn","pencil","animation","stylized"],"updated_at":"2026-10-02T18:53:14.384Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaad5f2/3kPTumERGySlFQrvJdc-5.jpg","model_url":"https://fal.run/minimax/h3-max/styles/hand-drawn","license_type":"commercial","date":"2026-09-17T21:29:26.890Z","group":{"key":"hailuo-03-new-turbo-lora","label":"Hand Drawn"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/minimax/video-01-live","metadata":{"display_name":"MiniMax (Hailuo AI) Video 01 Live","category":"text-to-video","description":"Generate video clips from your prompts using MiniMax model","status":"active","tags":["motion","transformation"],"updated_at":"2026-04-21T17:52:15.277Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/fal_cdn/Fal_Visuals_V1_016.jpg","model_url":"https://fal.run/fal-ai/minimax/video-01-live","date":"2024-12-16T00:00:00.000Z","group":{"key":"minimax-video","label":"Text to Video (Live)"},"highlighted":false,"pinned":false}},{"endpoint_id":"veed/fabric-1.0/text","metadata":{"display_name":"Fabric 1.0","category":"text-to-video","description":"VEED Fabric 1.0 text-to-video API","status":"active","tags":["lipsync","avatar","text-to-video"],"updated_at":"2026-04-23T16:51:02.559Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a860513/IhQfhGTiM994lkg1kPlOX_4836a8df5844488399dc1205ef3cc083.jpg","model_url":"https://fal.run/veed/fabric-1.0/text","license_type":"commercial","date":"2025-12-12T15:22:12.764Z","group":{"key":"fabric-1.0","label":"Text To Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/ltx-2.3-22b/distilled/text-to-video","metadata":{"display_name":"LTX-2.3 22B Distilled","category":"text-to-video","description":"Generate video with audio from text using LTX-2.3 Distilled","status":"active","tags":[],"updated_at":"2026-07-13T19:05:24.786Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9289be/bEbjXj3FMaublu4e4WsLD__tmp_b006-ice--samurai-helm.jpg","model_url":"https://fal.run/fal-ai/ltx-2.3-22b/distilled/text-to-video","license_type":"commercial","date":"2026-03-14T02:08:28.493Z","group":{"key":"ltx-2.3-22b-distilled","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false,"training_endpoint_ids":["fal-ai/ltx23-video-trainer"]}},{"endpoint_id":"fal-ai/ltx-2.3-22b/text-to-video","metadata":{"display_name":"LTX-2.3 22B","category":"text-to-video","description":"Generate video with audio from text using LTX-2.3","status":"active","tags":[],"updated_at":"2026-07-13T19:05:24.786Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9289be/SGtOOBIRqFPtmKPSmoNzE__tmp_avatar-v2.jpg","model_url":"https://fal.run/fal-ai/ltx-2.3-22b/text-to-video","license_type":"commercial","date":"2026-03-14T01:49:44.949Z","group":{"key":"ltx-2.3-22b","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false,"training_endpoint_ids":["fal-ai/ltx23-video-trainer"]}},{"endpoint_id":"fal-ai/hunyuan-video-v1.5/text-to-video","metadata":{"display_name":"Hunyuan Video V1.5","category":"text-to-video","description":"Hunyuan Video 1.5 is Tencent's latest and best video model","status":"active","tags":["hunyuan-video","text-to-video"],"updated_at":"2026-04-21T17:48:26.406Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/panda/yRuXc12ZmJxhXiGcd_1jW_9ebc91f64d1a44b7995e66b3410547e9.jpg","model_url":"https://fal.run/fal-ai/hunyuan-video-v1.5/text-to-video","license_type":"commercial","date":"2025-11-21T12:19:44.185Z","highlighted":false,"kind":"inference","duration_estimate":3,"pinned":false}},{"endpoint_id":"minimax/h3-max/styles/16bit-pixel","metadata":{"display_name":"H3 Max 16-bit Pixel","category":"text-to-video","description":"Generates 768p video with audio in a 16-bit pixel-art style from text prompts or an optional first-frame image. Supports durations of 5–15 seconds.","status":"active","tags":["pixel-art","16-bit","animation","stylized"],"updated_at":"2026-10-02T18:53:14.384Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaad5e9/M4QpbIMC5EcjkbBo4AW33.jpg","model_url":"https://fal.run/minimax/h3-max/styles/16bit-pixel","license_type":"commercial","date":"2026-09-17T21:28:00.908Z","group":{"key":"hailuo-03-new-turbo-lora","label":"16-bit Pixel"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"veed/avatars/text-to-video","metadata":{"display_name":"Avatars","category":"text-to-video","description":"Generate high-quality videos with UGC-like avatars from text","status":"active","tags":["lipsync","text-to-video"],"updated_at":"2026-01-26T21:43:38.259Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/veed_logo.webp","model_url":"https://fal.run/veed/avatars/text-to-video","license_type":"commercial","date":"2025-05-28T14:20:10.759Z","group":{"key":"veed-avatars-1","label":"Text To Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/ltxv-13b-098-distilled","metadata":{"display_name":"LTX-Video 13B 0.9.8 Distilled","category":"text-to-video","description":"Generate long videos from prompts using LTX Video-0.9.8 13B Distilled and custom LoRA","status":"active","tags":["video","ltx-video","text-to-video"],"updated_at":"2026-07-13T19:05:24.786Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/fal_cdn/fal/Training-4.jpg","model_url":"https://fal.run/fal-ai/ltxv-13b-098-distilled","license_type":"commercial","date":"2025-07-17T03:01:15.578Z","group":{"key":"ltx-video-13b-098","label":"Text to Video"},"highlighted":false,"kind":"inference","duration_estimate":1,"pinned":false}},{"endpoint_id":"fal-ai/cogvideox-5b","metadata":{"display_name":"CogVideoX-5B","category":"text-to-video","description":"Generate videos from prompts using CogVideoX-5B","status":"active","tags":[],"updated_at":"2026-04-21T17:44:50.269Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/model_tests/cogvideox/panda.gif.gif","model_url":"https://fal.run/fal-ai/cogvideox-5b","github_url":"https://huggingface.co/THUDM/CogVideoX-5b/blob/main/LICENSE","date":"2025-01-14T00:00:00.000Z","group":{"key":"cogvideox-5b","label":"Text to Video"},"highlighted":false,"pinned":false}},{"endpoint_id":"minimax/h3-max/styles/low-poly","metadata":{"display_name":"H3 Max Low Poly","category":"text-to-video","description":"Generates 768p video with audio in a retro low-poly 3D style from text prompts or an optional first-frame image. Supports durations of 5–15 seconds.","status":"active","tags":["low-poly","retro","3d-animation","stylized"],"updated_at":"2026-10-02T18:53:14.384Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0aaad5f8/7YH1svyhRf42Itvh-gQ4T.jpg","model_url":"https://fal.run/minimax/h3-max/styles/low-poly","license_type":"commercial","date":"2026-09-17T21:30:25.689Z","group":{"key":"hailuo-03-new-turbo-lora","label":"Low Poly"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/vidu/q2/text-to-video","metadata":{"display_name":"Vidu","category":"text-to-video","description":"Use the latest Vidu Q2 models which much more better quality and control on your videos.","status":"active","tags":[],"updated_at":"2026-04-27T03:35:06.506Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/kangaroo/ui3mJj8_Fmxg22mCDuesY_38c8acb860cf4072899ec0c062efcf9e.jpg","model_url":"https://fal.run/fal-ai/vidu/q2/text-to-video","license_type":"commercial","date":"2025-10-22T16:40:07.242Z","highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kandinsky5-pro/text-to-video","metadata":{"display_name":"Kandinsky5 Pro","category":"text-to-video","description":"Kandinsky 5.0 Pro is a diffusion model for fast, high-quality text-to-video generation.","status":"active","tags":[],"updated_at":"2026-04-21T17:49:44.869Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8775f2/Z3ul8R1t-mF0RUH6Z36v9_ae12c69d675b4a1794890ce3cb7b6b49.jpg","model_url":"https://fal.run/fal-ai/kandinsky5-pro/text-to-video","license_type":"commercial","date":"2025-12-23T13:40:22.639Z","group":{"key":"kandinsky5-pro","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/longcat-video/distilled/text-to-video/720p","metadata":{"display_name":"LongCat Video Distilled","category":"text-to-video","description":"Generate long videos in 720p/30fps from text using LongCat Video Distilled","status":"active","tags":[],"updated_at":"2026-01-26T21:42:29.849Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/rabbit/Xh3L9IfiYFQpDx1WpQH8T_e0057041856c45b1ab31a267f8132455.jpg","model_url":"https://fal.run/fal-ai/longcat-video/distilled/text-to-video/720p","license_type":"commercial","date":"2025-10-30T14:41:43.380Z","group":{"key":"longcat-distilled","label":"Text to Video (720p)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/ltx-video-v095","metadata":{"display_name":"LTX Video-0.9.5","category":"text-to-video","description":"Generate videos from prompts using LTX Video-0.9.5","status":"active","tags":["video","text-video"],"updated_at":"2026-07-13T19:05:24.786Z","is_favorited":null,"thumbnail_url":"https://storage.googleapis.com/falserverless/gallery/ltx-0.9.5.webp","model_url":"https://fal.run/fal-ai/ltx-video-v095","date":"2025-03-05T00:00:00.000Z","group":{"key":"ltx-video-v0.9.5","label":"Text to Video"},"highlighted":false,"pinned":false}},{"endpoint_id":"fal-ai/kandinsky5/text-to-video","metadata":{"display_name":"Kandinsky5","category":"text-to-video","description":"Kandinsky 5.0 is a diffusion model for fast, high-quality text-to-video  generation.","status":"active","tags":[],"updated_at":"2026-04-21T17:49:46.362Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/panda/F-LagExgsZASG2uyIcj6X_093dccc7417c47e593e245767017f251.jpg","model_url":"https://fal.run/fal-ai/kandinsky5/text-to-video","license_type":"commercial","date":"2025-10-13T14:43:38.479Z","group":{"key":"kandinsky5","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kandinsky5/text-to-video/distill","metadata":{"display_name":"Kandinsky5","category":"text-to-video","description":"Kandinsky 5.0 Distilled is a lightweight diffusion model for fast, high-quality text-to-video generation.","status":"active","tags":[],"updated_at":"2026-04-21T17:49:46.930Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/kangaroo/TyHaKAdxHRg3VIjUlKZPI_674ee5ee1f2d467e9f3806531f85dee2.jpg","model_url":"https://fal.run/fal-ai/kandinsky5/text-to-video/distill","license_type":"commercial","date":"2025-10-13T14:45:27.847Z","group":{"key":"kandinsky5","label":"Text to Video (Distill)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/infinitalk/single-text","metadata":{"display_name":"Infinitalk","category":"text-to-video","description":"Infinitalk model generates a talking avatar video from a text and audio file. The avatar lip-syncs to the provided audio with natural facial expressions.","status":"active","tags":[],"updated_at":"2026-06-24T13:05:50.174Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f9396/AGHkC8dUm_lsDNufhenrc_Z0Oiaeje.png","model_url":"https://fal.run/fal-ai/infinitalk/single-text","license_type":"commercial","date":"2025-08-22T15:48:52.311Z","group":{"key":"Infinitalk","label":"Text"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/longcat-video/distilled/text-to-video/480p","metadata":{"display_name":"LongCat Video Distilled","category":"text-to-video","description":"Generate long videos from text using LongCat Video Distilled","status":"active","tags":[],"updated_at":"2026-01-26T21:42:31.218Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/zebra/wjjJyktF2Y8GLxCDR9XsW_11eea2cee7e94b67aa89b3fc28ee55e1.jpg","model_url":"https://fal.run/fal-ai/longcat-video/distilled/text-to-video/480p","license_type":"commercial","date":"2025-10-28T23:29:22.398Z","group":{"key":"longcat-distilled","label":"Text to Video (480p)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/longcat-video/text-to-video/480p","metadata":{"display_name":"LongCat Video","category":"text-to-video","description":"Generate long videos from text using LongCat Video","status":"active","tags":[],"updated_at":"2026-01-26T21:42:29.531Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/penguin/rYYa2jpouP8HP5sofxQjq_194c767959414548bff2c3f04fedbe0f.jpg","model_url":"https://fal.run/fal-ai/longcat-video/text-to-video/480p","license_type":"commercial","date":"2025-10-30T14:50:01.405Z","group":{"key":"longcat","label":"Text to Video (480p)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/ovi","metadata":{"display_name":"Ovi Text to Video","category":"text-to-video","description":"A unified paradigm for audio-video generation","status":"active","tags":[],"updated_at":"2026-04-21T17:52:37.338Z","is_favorited":null,"thumbnail_url":"https://v3.fal.media/files/lion/yU9aRgq2QMYK4eGH5mohA_2822a9b5892d46699e218791b207ae5c.jpg","model_url":"https://fal.run/fal-ai/ovi","license_type":"commercial","date":"2025-10-03T12:43:15.945Z","group":{"key":"ovi","label":"Text to video"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/longcat-video/text-to-video/720p","metadata":{"display_name":"LongCat Video","category":"text-to-video","description":"Generate long videos in 720p/30fps from text using LongCat Video","status":"active","tags":[],"updated_at":"2026-01-26T21:42:29.128Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/panda/yE1r-CAPmdJnlspqz6rJf_520c6560105249e1a1720c47f830c299.jpg","model_url":"https://fal.run/fal-ai/longcat-video/text-to-video/720p","license_type":"commercial","date":"2025-10-30T16:24:45.138Z","group":{"key":"longcat","label":"Text to Video (720p)"},"highlighted":false,"kind":"inference","pinned":false}},{"endpoint_id":"fal-ai/kling-video/v1.6/pro/effects","metadata":{"display_name":"Kling 1.6","category":"text-to-video","description":"Generate video clips from your prompts using Kling 1.6 (pro)","status":"active","tags":[],"updated_at":"2026-06-24T11:42:39.441Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9f92d3/mVFKfkp_tpskWA8TMobUu_I1nGUw87.png","model_url":"https://fal.run/fal-ai/kling-video/v1.6/pro/effects","license_type":"commercial","date":"2025-03-06T00:00:00.000Z","group":{"key":"kling-video-effects","label":"v1.6 Effects (pro)"},"highlighted":false,"kind":"inference","duration_estimate":4,"pinned":false}},{"endpoint_id":"fal-ai/ltx-2.3-quality/text-to-video","metadata":{"display_name":"Ltx 2.3 Quality","category":"text-to-video","description":"Generate high-quality video with audio from text using LTX-2.3","status":"active","tags":["text-to-video","video"],"updated_at":"2026-07-13T19:05:24.786Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a9c9702/fmggLmMmNhdfHCd7l0GpE_QYCC91lB.png","model_url":"https://fal.run/fal-ai/ltx-2.3-quality/text-to-video","license_type":"commercial","date":"2026-06-01T20:24:08.222Z","group":{"key":"ltx-2.3-quality","label":"Text to Video"},"highlighted":false,"kind":"inference","pinned":false,"training_endpoint_ids":["fal-ai/ltx23-video-trainer"]}},{"endpoint_id":"fal-ai/cosmos-predict-2.5/text-to-video","metadata":{"display_name":"Cosmos Predict 2.5 2B","category":"text-to-video","description":"Generate video from text using NVIDIA's 2B Cosmos Post-Trained Model","status":"active","tags":[],"updated_at":"2026-04-28T16:38:35.130Z","is_favorited":null,"thumbnail_url":"https://v3b.fal.media/files/b/0a8fccfa/eYc-U5ezUgUhzx9Bw5rTM_8167b40fbaa04a2594d281b7fffcea68.jpg","model_url":"https://fal.run/fal-ai/cosmos-predict-2.5/text-to-video","license_type":"commercial","date":"2026-02-24T19:58:26.642Z","group":{"key":"cosmos-2.5","label":"Text to Video"},"highlighted":false,"kind":"inference","duration_estimate":7,"pinned":false}}],"next_cursor":"Mg","has_more":true}