{"rewrite":{"id":"r_d69aa12a6c65e7da33bfdb77","clusterId":"c_f9cd90e5180070bd8d4e5c75","slug":"ltx-releases-ltx-2-5-video-generation-ai-as-open-model","model":"deepseek-v4-flash:free","headline":"LTX Releases LTX-2.5 Video Generation AI as Open Model","summary":"LTX released LTX-2.5, an open video generation AI model, on August 12, 2026. It supports text, image, and video inputs, generates videos with audio, and natively handles multi-shot generation. The model uses a Gemma 4-based custom LLM for prompt adherence and includes Diffusion fidelity rendering for quality. Commercial use is allowed for companies with annual revenue under $10 million.","whyItMatters":"LTX-2.5 extends the company's open-model approach with multi-shot and HDR capabilities, positioning it against proprietary rivals while keeping local and API-based generation accessible.","webCardHtml":"\u003cp\u003eLTX has released LTX-2.5, its latest video generation AI, as an open model. The model generates videos with audio from text, image, or video inputs, and natively supports multi-shot generation, preserving face and voice continuity across multiple shots in a single pass.\u003c/p\u003e\u003cp\u003eThe company says the model follows complex instructions for motion, lighting, text, and composition, thanks to a custom LLM based on Gemma 4. A technique called Diffusion fidelity rendering allocates compute based on scene complexity, and the model supports 16-bit HDR output.\u003c/p\u003e\u003cp\u003eLTX-2.5 is available on Hugging Face, and ComfyUI supports it. The company says it can run on a GPU with 16GB of VRAM, and LoRAs trained for LTX-2.3 remain usable.\u003c/p\u003e","blueskyPost":"LTX-2.5 is out as an open model. It generates video with audio, handles multi-shot, and supports HDR. Runs on 16GB VRAM, works in ComfyUI, and LTX-2.3 LoRAs carry over. Commercial use allowed under $10M annual revenue.","twitterPost":"LTX released LTX-2.5, an open video AI model. It generates audio-synced video, supports multi-shot and HDR, and runs on 16GB VRAM. ComfyUI support included, LTX-2.3 LoRAs work. Commercial use under $10M revenue.","threadsPost":null,"newsletterBlurb":"LTX released LTX-2.5 as an open model, adding multi-shot generation, HDR output, and a Gemma 4-based text encoder. It runs locally on 16GB VRAM and works with ComfyUI, with commercial use allowed for companies under $10 million in annual revenue.","attributionJson":"[{\"source\":\"GIGAZINE\",\"url\":\"https://gigazine.net/news/20260812-ltx-2-5-video-generation-ai/\",\"title\":\"動画生成AI「LTX-2.5」がオープンモデルとして公開される、マルチショット対応＆プロンプト追従性が向上＆HDR対応などなど\"}]","lintFlagsJson":null,"lintHits":0,"costUsd":0,"inputTokens":5328,"outputTokens":665,"status":"published","repairAttempts":0,"nextRepairAt":null,"factsAttemptedAt":1786509108,"createdAt":"2026-08-12T04:20:06.000Z","publishedAt":"2026-08-12T04:21:44.000Z","updatedAt":"2026-08-12T04:20:06.000Z"},"cluster":{"id":"c_f9cd90e5180070bd8d4e5c75","canonicalTitle":"動画生成AI「LTX-2.5」がオープンモデルとして公開される、マルチショット対応＆プロンプト追従性が向上＆HDR対応などなど","representativeArticleId":"a_435d97872eb8b380aa58bc95","sourceCount":1,"writtenSourceCount":1,"writeAttempts":0,"isSolo":true,"entitiesJson":"{\"anime_titles\":[],\"manga_titles\":[],\"work_titles\":[\"LTX-2.5\"],\"studios\":[\"LTX\"],\"people\":[],\"type\":\"announcement\",\"domain\":\"other\",\"is_roundup\":false}","contentType":"news","status":"published","firstSeenAt":"2026-08-12T03:32:00.000Z","lastSeenAt":"2026-08-12T03:32:00.000Z","updatedAt":"2026-08-12T04:21:46.000Z"},"attribution":[{"source":"GIGAZINE","url":"https://gigazine.net/news/20260812-ltx-2-5-video-generation-ai/","title":"動画生成AI「LTX-2.5」がオープンモデルとして公開される、マルチショット対応＆プロンプト追従性が向上＆HDR対応などなど"}],"entities":{"anime_titles":[],"manga_titles":[],"work_titles":["LTX-2.5"],"studios":["LTX"],"people":[],"type":"announcement","domain":"other","is_roundup":false},"keyFacts":null}