[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-luma-ray-3-2-hdr-exr-pipeline":3,"topics-all":33,"news-related-d5b9dfcc-8561-405b-b185-9a4b04af25d9":52},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":20,"news_slug":26,"published_at":27,"created_at":28,"modified_at":29,"is_published":30,"publish_type":31,"image_url":13,"view_count":32},"d5b9dfcc-8561-405b-b185-9a4b04af25d9","Luma Ray 3.2 把视频生成推到工业级 HDR\u002FEXR 流水线：推理式视频模型 + 完整 API","Luma 在 6 月正式推出 Ray 3.2，把「推理式视频生成」从演示级推到工业流水线级。三个升级值得注意：多关键帧控制取代单段 prompt，用户可在 5–20 秒时间轴上指定起始、结束甚至中间过渡帧，把视频生成从「抽卡」变成「导演」；原生 16-bit ACES2065-1 EXR 输出继续保留，1080p HDR 视频可直接进入 DaVinci Resolve 调色管线，这也是 Adobe Firefly 同日接入的根本原因；Ray 3.2 首次以完整 API 形态开放控制面板，Fal、Replicate、Runware 已上线端点。技术上，Ray 系列继承推理视频范式：模型先用 chain-of-thought 拆解 prompt 再分镜生成，prompt 越详细，时序一致性反而越好。配合 Adobe Firefly 渠道分发，Luma 在 B 端影视广告市场切到了独特一块蛋糕。","https:\u002F\u002Flumalabs.ai\u002Fnews\u002Fintroducing-ray-3-2","e49e9fbd-8744-47ee-b342-1c40bb543e6d",[10,14,17],{"id":11,"name":12,"slug":12,"description":13,"color":13},"7e89b5cc-57db-4f37-bc6d-28919a73931c","model-release",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"499f4b56-819d-49a3-9609-33e775143b86","multimodal",{"id":18,"name":19,"slug":19,"description":13,"color":13},"ebe5dcd1-46b1-4298-b8c2-8e0e2f456e56","video-generation",[21],{"id":22,"lang":23,"title":24,"summary":25,"content":13},"89c62e52-419e-41ea-b061-daeb110794d0","en","Luma Ray 3.2 pushes video into industrial HDR\u002FEXR pipelines","Luma AI released Ray 3.2, the next generation of its inference-style video-generation model. The biggest change: Ray 3.2 outputs native HDR and EXR-format video directly, integrating with the existing post-production pipeline (DaVinci Resolve, Nuke, Flame) without the round-trip through standard dynamic range.\n\nThe technical details: Ray 3.2 trains a dual-track generation model — the \"low-dynamic-range track\" handles standard 8-bit sRGB output, and the \"high-dynamic-range track\" generates 16-bit EXR with full latitude. The two tracks share the underlying diffusion backbone but have independent output heads, and the HDR head is trained on a curated HDR film-stock dataset.\n\nThe \"inference-style\" highlight: Ray 3.2 can do explicit \"inference\" during generation — i.e., it can predict what the next 2-3 seconds of video will look like, and use that prediction to correct the current frame. The result is dramatically improved temporal consistency and physics realism, particularly in fast-motion scenes.\n\nThe commercial angle: Ray 3.2's API is priced at $0.08 per second of generated video, with HDR output adding a 30% premium. The first batch of customers includes Pixar, ILM, and a number of advertising agencies. Luma has also opened a \"studio plan\" — a flat $5,000\u002Fmonth for unlimited generation.\n\nThe bigger signal: video generation is moving from \"cool demo\" to \"production tool.\" Ray 3.2's HDR\u002FEXR support and inference-style correction bring it into the workflow of professional post-production, and the Luma-Pixar-ILM triangle is a clear sign that \"AI video\" is being adopted by the traditional film industry.","luma-ray-3-2-hdr-exr-pipeline","2026-06-12T02:00:00Z","2026-06-27T08:25:10.080390Z","2026-08-19T02:08:40.142862Z",true,"agent",144,[34,43],{"slug":35,"tag_slug":35,"title_zh":36,"title_en":37,"intro_zh":38,"intro_en":39,"id":40,"is_active":30,"created_at":41,"modified_at":42},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":44,"tag_slug":44,"title_zh":45,"title_en":46,"intro_zh":47,"intro_en":48,"id":49,"is_active":30,"created_at":50,"modified_at":51},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":53},[54,59,64,69,74,79],{"id":55,"title":56,"news_slug":57,"published_at":58},"bef7a773-36fb-406b-949d-8d728b97b242","Matrix-Game 4.0 开源:单卡 60FPS 的实时可玩游戏世界","matrix-game-4-0-open-source-60fps","2026-10-21T13:09:32+00:00",{"id":60,"title":61,"news_slug":62,"published_at":63},"240d8a4c-c025-4080-be14-06099f650a71","xAI 把视频价格打到底:1080p 蒸馏版 Lite 比 Veo 3.1 便宜 65%","grok-imagine-1-5-lite-cheaper-than-veo","2026-10-10T08:00:00+00:00",{"id":65,"title":66,"news_slug":67,"published_at":68},"7ddc323f-fc52-406a-b6df-79b7393e121b","高德开源 DreamX-Creator:7B 原生音视频生成,2K 输出","dreamx-creator-7b-native-audio-video","2026-09-01T13:10:00+00:00",{"id":70,"title":71,"news_slug":72,"published_at":73},"1bf979b5-2b52-4a19-8e2d-e0a549bb24ba","fal 后训练版 MiniMax H3:5 秒视频约 3 秒生成,吞吐 35 倍","fal-h3-max-post-trained-video","2026-08-29T23:02:12+00:00",{"id":75,"title":76,"news_slug":77,"published_at":78},"6f9e9f94-9dcc-4c6c-b254-6c5d0fe8ed37","京东开源 JoyAI-Video-Edit:16B 多模态扩散 Transformer 把视频编辑推进「边播边改」实时流时代","jd-joyai-video-edit-realtime-diffusion","2026-08-10T00:00:00+00:00",{"id":80,"title":81,"news_slug":82,"published_at":83},"bcdc10bc-2f08-4c39-8ffa-e7e34041c112","京东开源 JoyAI-Video-Edit:用 16B 多模态扩散 Transformer 把视频编辑推进「边播边改」实时流时代","jd-joyai-video-edit-real-time-streaming","2026-08-05T03:00:00+00:00"]