[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-veo-3-1-ingredients-to-video-fine-control":3,"topics-all":36,"news-related-7d24855e-d09e-485d-a87d-77586313da28":55},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"7d24855e-d09e-485d-a87d-77586313da28","Google Veo 3.1「Ingredients to Video」：把视频控制粒度做到最细","5月中旬，Google DeepMind 发布了 Veo 3.1 的「Ingredients to Video」功能更新。这不是一次普通的版本迭代，而是视频生成可控性问题上的一次实质性推进。\n\n此前 AI 视频生成的核心矛盾在于：模型能产出高质量画面，但创作者对镜头语言、角色行为、物理规则的控制力极为有限。「Ingredients to Video」的设计思路是将视频解构为多个可独立控制的「成分」——包括角色一致性、场景稳定性、光影逻辑、运动轨迹——每一项都可以单独调节强度或锁定。这意味着 prompt 不再是唯一的控制手段。创作者可以固定角色外观，让动作在多个镜头间保持连贯；同时独立控制运镜方式，而不受画面内容的干扰。Google 将其类比为「配方」：不同成分组合产生不同结果，但每一份原料都可以单独替换。\n\n目前视频生成领域呈现多强并立：Runway Gen-4 以原生音视频同步为卖点，Seedance 2.0 走统一音视频架构路线，Kling 3.0 强调电影感镜头与多镜头故事板能力。Veo 3.1 的差异化在于把「精细化控制」放到了台面上，而不是单纯堆叠时长或分辨率。它解决的不是「能不能生成」的问题，而是「生成的东西是否符合我的意图」的问题。\n\n这轮视频生成竞争里，可控性正在成为下一个分水岭。当各家都能生成几秒流畅画面时，谁能让创作者真正「指挥」镜头语言，谁就掌握了商业化落地的钥匙。Veo 3.1 没有试图用更大的模型解决一切，而是选择了把控制粒度做细——这可能也是未来视频生成的主线：不是更炫，而是更准。","https:\u002F\u002Fblog.google\u002Finnovation-and-ai\u002Ftechnology\u002Fai\u002Fveo-3-1-ingredients-to-video\u002F","35ce748f-48b7-4638-88ef-effa57a7e749",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"8cf7490f-2449-4ba7-be19-61befa0d92b4","google",{"id":18,"name":19,"slug":19,"description":13,"color":13},"499f4b56-819d-49a3-9609-33e775143b86","multimodal",{"id":21,"name":22,"slug":22,"description":13,"color":13},"ebe5dcd1-46b1-4298-b8c2-8e0e2f456e56","video-generation",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"e00a5bd0-80a4-4abe-ba71-745fbc4f22f5","en","Veo 3.1 Ingredients to Video: the finest control granularity","Google DeepMind released Veo 3.1's \"Ingredients to Video\" feature, allowing fine-grained control over video generation by specifying \"ingredients\" — objects, characters, scenes, styles. The user can mix and match ingredients, with the model composing them into a coherent video.","veo-3-1-ingredients-to-video-fine-control","2026-05-28T07:01:00Z","2026-05-28T07:08:45.429351Z","2026-08-19T02:08:40.142862Z",true,"agent",219,[37,46],{"slug":38,"tag_slug":38,"title_zh":39,"title_en":40,"intro_zh":41,"intro_en":42,"id":43,"is_active":33,"created_at":44,"modified_at":45},"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":47,"tag_slug":47,"title_zh":48,"title_en":49,"intro_zh":50,"intro_en":51,"id":52,"is_active":33,"created_at":53,"modified_at":54},"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":56},[57,62,67,72,77,82],{"id":58,"title":59,"news_slug":60,"published_at":61},"52e9955f-50fe-4ea1-98cc-a7a442d57b71","MilliVid：MIT 把「分层潜变量」装进视频扩散，长程一致性首次跑通长镜头","millivid-mit-hierarchical-latent-long","2026-06-11T02:00:00+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"25eeddf5-b3d7-45b4-9725-387f60955252","智象未来提出多模态模型Token利润率远超语言模型：世界模型的技术路径与商业化前景","zhixiang-multimodal-token-margin-world-model","2026-05-28T10:00:00+00:00",{"id":68,"title":69,"news_slug":70,"published_at":71},"a33fff56-d6b1-47b4-a65e-2250d73c8875","Gemini Omni Flash 体验：多模态视频生成正在越过令人不安的边界","gemini-omni-flash-deepfake-uncomfortable","2026-05-23T08:10:00+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"9e0dd6e3-920b-4802-9b8d-23b118c371a1","Gemini Omni 落地 YouTube Shorts：多模态 AI 从技术秀场走向大众创作工具","gemini-omni-youtube-shorts-remix-mass","2026-05-21T01:01:00+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"f76fc8eb-1cd0-4577-aca8-db98018194ae","Mamoda2.5：DiT-MoE 架构统一多模态生成，推理速度提升 95 倍","mamoda-2-5-dit-moe-multimodal-95x","2026-05-18T13:10:00+00:00",{"id":83,"title":84,"news_slug":85,"published_at":86},"2b76a3ac-58f3-4fd1-9d99-c5c7f51b3a7d","Google I\u002FO 前夕泄密：Gemini Omni 或将统一多模态生成","gemini-omni-leak-google-io-video","2026-05-06T02:10:00+00:00"]