[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-witheveryone-group-image-identity-grounding":3,"news-related-5ff06769-2251-40fd-a672-f394a1f68965":38},{"id":4,"title":5,"summary":6,"content":7,"original_url":8,"source_id":9,"tags":10,"translations":24,"news_slug":31,"published_at":32,"created_at":33,"modified_at":34,"is_published":35,"publish_type":36,"image_url":14,"view_count":37},"5ff06769-2251-40fd-a672-f394a1f68965","十人合影谁是谁:腾讯混元 WithEveryone 给群像生成装上身份锚点","腾讯混元团队发布 WithEveryone 群像生成框架:每个参考身份注入寻址 token,先规划身份-布局再渲染,用布局接地 ID 损失监督目标人脸。人脸相似度从 GPT-Image-2 的 0.462 提至 0.499,伪影从 0.169 降至 0.055。开源版因基模许可在重训。","十个人的合影,让 AI 凭五到十张参考照片把每个人都放对位置、长对脸——这件事直到最近仍是身份保持生成里最容易翻车的场景。腾讯混元团队在 arXiv 发布的 WithEveryone 框架([论文](https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.20336))给出了一个思路:别急着画,先把谁站在哪规划清楚。\n\n## 人一多,身份就漂\n\n论文开篇点出的核心矛盾:当场景必须包含多个指定人物时,身份保持生成的可靠性会快速下降。模型要同时做对三件事——保留每个身份、把每张参考脸绑定到特定的人、把人放到正确的位置;而训练阶段的身份损失函数,还要在多个带噪声的预测人脸之间建立对应关系。任何一环松了,结果就是张冠李戴式的串脸,或者干脆把参考图里的脸直接复制粘贴过去。\n\n## 四个组件:先规划,再渲染,监督对的脸\n\nWithEveryone 的设计可以拆成四步:\n\n- **寻址 token**:每个被选中的身份,以一个专属 token 的形式注入模型;\n- **身份-布局规划**:模型先预测一份结构化的 identity-layout plan,再把它渲染成视觉条件,相当于先排好站位图再生成图像;\n- **布局接地 ID 损失(Layout-Grounded ID Loss)**:用标注好的人脸区域直接监督应该出现在这里的那个身份,绕开不稳定的 embedding 式人脸匹配;\n- **ID 表示强制(ID Representation Forcing)**:在图像合成之前,先对每个身份各训练一个预测。\n\n这套设计的关键词是接地(grounding):身份不再是漂在提示词里的抽象概念,而是被锚定到布局中的具体区域。\n\n## 数字:相似度 0.462 到 0.499,伪影砍掉约三分之二\n\n在一个身份不相交的基准上,论文报告 WithEveryone 取得了最高的 target-context 身份相似度:人脸相似度从 GPT-Image-2 的 0.462 提升到 0.499,复制粘贴伪影从 0.169 降到 0.055——约等于砍掉三分之二。覆盖面上,它能覆盖 97.3% 的请求身份,重复率只有 2.8%。论文的结论是:显式的身份-布局接地,让身份保持生成能扩展到更大的群组,而不依赖直接复制参考脸。\n\n## 一个现实问题:权重暂时发不了\n\n值得注意的细节在 [GitHub 仓库](https:\u002F\u002Fgithub.com\u002Fdoby-xu\u002FWithEveryone)的发布计划里:论文中的研究版本建立在一个许可证条款不允许发布 checkpoint 的基座模型上;为了给社区一个开放替代,团队正在一个支持开源发布的基模上重训新版本,代码和权重将在新版本就绪后放出。也就是说,短期内你能读到方法和论文,但拿不到可跑的权重——这与当前基模许可证反向约束研究可复现性的行业现状,是同一个症候。\n\n论文登上 8 月 21 日的 Hugging Face Daily Papers 榜单,收获 39 个 upvote,GitHub 仓库已有 43 star。对做多人场景合成、虚拟合影类应用的团队来说,这篇值得放进观察列表;但要真正落地,还得等那个正在重训中的开源版本。什么时候权重能下载、开源版性能是否打折扣,才是这条技术路线从论文走向工具的关键一跃。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.20336","7437aeb9-930c-4866-a2e9-48003c1a792b",[11,15,18,21],{"id":12,"name":13,"slug":13,"description":14,"color":14},"a8002d98-9df1-4ab9-94d4-a7625af634c4","china-ai",null,{"id":16,"name":17,"slug":17,"description":14,"color":14},"7b67033c-19e6-4052-a626-e681bba64c7a","diffusion",{"id":19,"name":20,"slug":20,"description":14,"color":14},"499f4b56-819d-49a3-9609-33e775143b86","multimodal",{"id":22,"name":23,"slug":23,"description":14,"color":14},"c883fd20-1d66-4fb7-9fc7-320fa7f87023","text-to-image",[25],{"id":26,"lang":27,"title":28,"summary":29,"content":30},"815191e2-cd9c-49ff-b44d-2db5e9bc7584","en","WithEveryone: Tencent Hunyuan's Group Image Framework Grounds Identity to Layout","Tencent's Hunyuan team released WithEveryone, a framework for identity-preserving group image generation with up to ten reference identities. Each identity enters as an addressed token; the model predicts an identity-layout plan before rendering, supervised by a Layout-Grounded ID Loss. Face similarity rises from GPT-Image-2's 0.462 to 0.499 while copy-paste artifacts drop from 0.169 to 0.055. An open-source version is being retrained due to base-model licensing.","A ten-person group photo where AI must place everyone correctly and keep every face right, guided by five to ten reference shots — this has long been the most failure-prone scenario in identity-preserving generation. WithEveryone, a framework released on arXiv by Tencent's Hunyuan-affiliated team ([paper](https:\u002F\u002Farxiv.org\u002Fabs\u002F2608.20336)), takes a different tack: don't start drawing until you have planned who stands where.\n\n## Why Identity Drifts as Groups Grow\n\nThe paper opens with the core tension: identity-preserving image generation becomes increasingly unreliable when a scene must contain many specified people. The model has to do three things at once — retain each identity, bind every reference face to a distinct person, and place that person at a correct location. Meanwhile, training-time identity losses must establish correspondence among several noisy predicted faces. When any of these links slips, you get face-swapping mix-ups, or worse, reference faces copied straight into the output.\n\n## Four Components: Plan First, Render Second, Supervise the Right Face\n\nWithEveryone's design breaks into four steps:\n\n- **Addressed tokens**: each selected identity is injected as a dedicated token;\n- **Identity-layout planning**: the model first predicts a structured identity-layout plan, then renders that plan as a visual condition — a seating chart before the photo;\n- **Layout-Grounded ID Loss**: annotated face regions supervise the intended identity directly, sidestepping unstable embedding-based face matching;\n- **ID Representation Forcing**: a prediction is additionally trained for each identity before image synthesis.\n\nThe keyword here is grounding: identity stops being an abstract concept floating in the prompt and gets anchored to a concrete region in the layout.\n\n## The Numbers: Similarity 0.462 to 0.499, Artifacts Cut by About Two-Thirds\n\nOn an identity-disjoint benchmark, the paper reports WithEveryone achieving the highest target-context identity similarity: face similarity improves from GPT-Image-2's 0.462 to 0.499, while copy-paste artifacts fall from 0.169 to 0.055 — roughly a two-thirds reduction. On coverage, it spans 97.3% of requested identities with a duplicate rate of only 2.8%. The paper's conclusion: explicit identity-layout grounding lets identity-preserving generation scale to larger groups without relying on direct reference-face copying.\n\n## A Practical Catch: No Checkpoints Yet\n\nThe detail worth noticing sits in the [GitHub repository](https:\u002F\u002Fgithub.com\u002Fdoby-xu\u002FWithEveryone) release plan: the research version in the paper is built on a foundation model whose licensing terms do not allow the checkpoint to be released. To give the community an open alternative, the team is actively training a new version on a foundation model that supports open release; code and checkpoints will follow once ready. In other words, for now you can read the method but not run the weights — a symptom of how base-model licenses increasingly constrain research reproducibility.\n\nThe paper made Hugging Face's Daily Papers list on August 21 with 39 upvotes, and the GitHub repo has 43 stars. For teams building multi-person scene synthesis or virtual group-photo applications, this belongs on the watchlist; real adoption, though, waits on the retrained open version. When the weights actually land — and whether the open release trades away any performance — is the leap that separates this technique from paper to tool.","witheveryone-group-image-identity-grounding","2026-08-24T13:00:00Z","2026-08-23T19:07:46.319322Z","2026-08-23T19:07:46.319332Z",true,"agent",35,{"items":39},[40,45,50,55,60,65],{"id":41,"title":42,"news_slug":43,"published_at":44},"ba4fec9d-1a6e-49db-9669-1e4b168afca2","字节 Seedance 2.0 翻身仗：一次从 UNet 到 DiT 的架构选择","bytedance-seedance-2-unit-dit","2026-07-08T00:30:00+00:00",{"id":46,"title":47,"news_slug":48,"published_at":49},"e97b45e2-01b1-44f8-97d7-8a80765245ec","Seedream 5.0 接力 Seedance 2.5：字节把「图像→视频」拼成一条产线","seedream-5-0-bytedance-image-to-video","2026-06-23T08:00:00+00:00",{"id":51,"title":52,"news_slug":53,"published_at":54},"1e0c52a9-c802-438d-9f21-4ea7ddc3d96a","Midjourney V8.1 发布：HD模式提速3倍，图像生成进入「高效量产」时代","midjourney-v8-1-hd-3x-default","2026-05-12T05:15:00+00:00",{"id":56,"title":57,"news_slug":58,"published_at":59},"b4214f43-353e-42e3-b48e-92dd4fc64290","京东开源 EchoWM 全模态世界模型:720p 音画同步,能跟着你走","jd-echowm-omnimodal-world-model","2026-08-25T23:10:00+00:00",{"id":61,"title":62,"news_slug":63,"published_at":64},"7ef479ae-66af-463a-802f-07a84ade93b1","商汤开源 SenseNova-U1.5-8B：原生多模态通吃生成编辑，短板全写进模型卡","sensenova-u1-5-8b-open-source-multimodal","2026-08-25T19:30:00+00:00",{"id":66,"title":67,"news_slug":68,"published_at":69},"f4c705fd-47c9-481a-807f-8001820070f8","InfinityEdit:三注意力轻量适配器,把视频编辑推进无界流时代","infinityedit-infinite-video-editing-adapter","2026-08-25T13:00:00+00:00"]