[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-ltx-2-3-lightricks-4k-native-audio":3,"news-related-bf8755fc-cd4f-4bd9-9617-e70f56ddc4ac":36},{"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},"bf8755fc-cd4f-4bd9-9617-e70f56ddc4ac","LTX-2.3：开源视频生成正式进入 4K + 原生音频时代","3月5日，Lightricks 发布 LTX-2.3，一款 220 亿参数的开源视频生成模型。不同于以往开源方案只能在低分辨率下运行，LTX-2.3 支持最高 4K 分辨率、50fps 的视频输出，并首次在开源生态中实现了真正的音视频同步——这在以前只有 OpenAI Sora、Runway 等闭源模型才能做到。\n\n技术层面，LTX-2.3 有几个值得关注的突破：重建了潜空间（latent space）并重新训练了 VAE，在头发、织物边缘、文字等细节保留上明显提升；文本控制器的规模扩大了 4 倍，复杂 Prompt 的解析能力大幅增强；更重要的是音频驱动视频生成能力——模型可以基于语音、音乐的节奏来组织画面结构，这是开源视频模型此前从未真正实现的功能。\n\n产品层面，LTX-2.3 采用 Apache 2.0 许可证，支持商用、本地部署和自行微调。对于有数据隐私要求或成本敏感的企业，这意味着视频生成能力不再被少数闭源方案垄断。模型可通过 Lightricks API 调用，也支持本地部署 weights。\n\n但需要客观看到，220 亿参数规模对硬件要求依然较高，完整功能需要专业级 GPU 才能流畅运行，并非普通开发者的玩具。\n\n开源视频模型和闭源方案之间的差距，2025 年以前还是「能用 vs 好用」的差别，到 2026 年 DiT 架构全面成熟后，两者的体验差距正在快速收窄。LTX-2.3 的出现是一个信号：开源视频生成进入生产环境的时间窗口，已经比预想中更近了。","https:\u002F\u002Fltx.io\u002Fmodel\u002Fltx-2-3","234f16d5-2704-4fbf-b70a-059c5164830d",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"7b67033c-19e6-4052-a626-e681bba64c7a","diffusion",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"0ef8513a-0a26-42f0-b6f9-5b6dadded45c","efficiency",{"id":18,"name":19,"slug":19,"description":13,"color":13},"b9bd9039-fcdb-41a8-b85b-fc1587def2b9","open-source",{"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},"fa8aa746-d68a-464c-a463-5d96e7f2e819","en","LTX-2.3: open video generation enters the 4K audio era","Lightricks released LTX-2.3 on June 2, the first open-source video generation model with native 4K resolution and native audio. The model generates video and audio in the same forward pass, with audio synchronized to the visual content, marking the open-source video generation field catching up with closed-source on the \"4K + native audio\" milestone.","ltx-2-3-lightricks-4k-native-audio","2026-06-02T01:00:00Z","2026-06-02T01:07:05.950376Z","2026-08-19T02:08:40.142862Z",true,"agent",108,{"items":37},[38,43,48,53,58,63],{"id":39,"title":40,"news_slug":41,"published_at":42},"18d2aa73-7244-4b10-b611-46475e17327e","ForgeWM开源:一步去噪72FPS的可玩世界模型,8张卡复现全流程","forgewm-few-step-playable-world-model","2026-08-24T21:10:00+00:00",{"id":44,"title":45,"news_slug":46,"published_at":47},"0599b775-ac17-49d2-aebd-a16f531c7168","腾讯混元 MeanFlowNFT：把 RL 接进「平均速度生成器」，Wan 2.1 4 步反超 50 步 LongCat-Video RL","tencent-hunyuan-meanflownft","2026-07-16T12:00:00+00:00",{"id":49,"title":50,"news_slug":51,"published_at":52},"42cfc778-8f1b-4bf2-a0ae-4343a066f48d","RhymeFlow：清华提出异步去噪流调度，DiT视频生成训练免费加速1.53倍","rhymeflow-tsinghua-async-denoising-1-53x","2026-06-07T22:00:00+00:00",{"id":54,"title":55,"news_slug":56,"published_at":57},"2874a2e5-beae-4627-8f6f-a34cf2cc8d7a","一段随手拍视频直出4D人体:4DAnyone用RCP+TCR破解多视角一致性,代码权重全开源","4danyone-monocular-video-4d-human","2026-08-20T17:59:53+00:00",{"id":59,"title":60,"news_slug":61,"published_at":62},"5612d186-46ee-4509-9a93-94045ba004ae","LTX-2.5 开放权重视频模型:4K 反而在 Fast 端点,EXR 色彩管线也焊进去了","ltx-2-5-open-weights-video","2026-08-18T15:20:00+00:00",{"id":64,"title":65,"news_slug":66,"published_at":67},"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"]