[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-welm-image-wechat-unified-model":3,"topics-all":38,"news-related-e7fe0809-52d0-4889-b73d-31bdf58bc8c3":66},{"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},"e7fe0809-52d0-4889-b73d-31bdf58bc8c3","微信WeLM-Image:看图生图改图一体,Turbo版单卡4.98秒出图","腾讯微信团队发布统一图像基座 WeLM-Image:理解、文生图、编辑、多参考合成一体,MoT+MoE,31.7B 存储、约 5.4B 激活,按消费级单卡设计。论文口径三项开源评测第一,Turbo 单张 H20 4.98 秒出 1024 图,权重未放。","图像模型圈过去两年的默认分工是:理解归 VLM,生成归扩散模型,编辑再单独训一个。腾讯微信团队 11 月 5 日挂在 arXiv 的 WeLM-Image 选择了另一条路——把多模态理解、文生图、指令引导编辑、多参考图合成四件事装进同一个基座模型,而且整个设计都围绕一个约束展开:要能在微信这种月活十亿级的消费应用里单卡跑起来。\n\n## 一条序列,两套参数\n\nWeLM-Image 把文本、参考图和目标 latent 当成一条交错序列处理;骨干用的是 Mixture-of-Transformers(MoT):注意力共享,理解和生成各持一套独立参数,目的是压住两条任务互相干扰的老问题。再往每条路径里加 MoE 模块做稀疏扩容,总存储 31.7B,每个目标 latent token 只激活约 5.4B 生成参数——大容量与低推理成本同时要。\n\n## 数据引擎与训练配方\n\n训练侧是一个「面向生成的数据引擎」:知识接地的视觉词表配大规模视觉聚类,平衡语义覆盖与编辑任务,训练中的评测反向指导数据迭代。双语标注加可验证的编辑监督,把训练逐步推到原生 1.5K(1536)分辨率。后训练分两步:生成与编辑各自用 rubric、清单式奖励优化,再用噪声感知的 on-policy 蒸馏把两套专门策略收拢回一个模型。\n\n## 论文口径的成绩单\n\n按论文报告的整体对比,1536 分辨率版在 PRISM-Bench、Qwen-Image-Bench、UnicBench 三项评测的开源模型对比中排名第一。速度上,基于 MeanFlow 少步蒸馏出的 Turbo 版,用 8 个无引导步在单张 NVIDIA H20 上 4.98 秒生成一张 1024×1024 图。论文 16 位作者署名,属 cs.CV 方向。\n\n## 单卡哲学,以及一个悬念\n\n对比上周 Mistral Large 4 权重落地时「4-bit 仍要约 631.7GB、数据中心多机才跑得动」的旗舰排场,WeLM-Image 反着走:微信的消费级场景等不起集群,模型设计从第一天起就为单卡让路。这也不是微信团队第一次押注开放研究——视觉团队此前已开源过 WeVisOne-VL、WeMM 等模型。悬念在交付:截至发稿,Hugging Face 论文页尚无关联模型仓库,权重未放出,论文先行。对做图像应用的人来说,值得盯的不是跑分,而是「统一基座+单卡部署」这条路线能不能在真实 App 里兑现。","https:\u002F\u002Farxiv.org\u002Fabs\u002F2611.07392","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},"7e89b5cc-57db-4f37-bc6d-28919a73931c","model-release",{"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},"886ce088-1a6c-412e-92bf-d7d7a39e16bb","en","WeChat's WeLM-Image: See, Draw, Edit in One 31.7B Model","WeChat's WeLM-Image unifies seeing, drawing and editing: 31.7B stored, 5.4B active per token; Turbo renders 1024px in 4.98s on one H20.","The default division of labor in image AI has long been: understanding belongs to VLMs, generation to diffusion models, and editing gets its own fine-tuned model. WeLM-Image, which Tencent's WeChat team posted to arXiv on November 5, takes the other road — folding multimodal understanding, text-to-image generation, instruction-guided editing, and multi-reference synthesis into one foundation model, with every design choice bent around a single constraint: it has to run on a single GPU inside WeChat's large-scale consumer applications.\n\n## One sequence, two parameter sets\n\nWeLM-Image processes text, reference images, and target latents as one interleaved sequence. The backbone is a Mixture-of-Transformers (MoT): attention is shared, while understanding and generation each keep independent parameters — a direct attack on the old problem of two tasks interfering with each other. MoE modules on each path add sparse capacity: 31.7B stored parameters in total, with only about 5.4B generation parameters activated per target latent token. Large capacity and low inference cost, demanded at once.\n\n## Data engine and training recipe\n\nTraining relies on a generation-oriented data engine: a knowledge-grounded visual vocabulary paired with large-scale visual clustering to balance semantic coverage and editing tasks, while training-time evaluation steers iterative data refinement. Bilingual annotations and verified editing supervision support progressive training up to native 1536 resolution. Post-training runs in two stages: generation and editing are each optimized with rubric- and checklist-based rewards, then noise-aware on-policy distillation consolidates the two specialized policies back into one model.\n\n## The scorecard, in the paper's own framing\n\nIn the reported overall comparisons, the 1536-resolution model ranks first among the evaluated open-source models on PRISM-Bench, Qwen-Image-Bench, and UnicBench. On speed, the Turbo variant — distilled via MeanFlow few-step training — generates a 1024x1024 image in 4.98 seconds on a single NVIDIA H20 using eight guidance-free steps. The paper lists 16 authors under cs.CV.\n\n## The single-GPU philosophy, and one open question\n\nContrast that with last week's Mistral Large 4 weights landing, where even the 4-bit build still needs about 631.7 GB and a datacenter multi-node setup. WeLM-Image walks the opposite direction: consumer applications at WeChat's scale cannot wait for clusters, so the model yields to a single GPU from day one. This is not the team's first open-research bet — the WeChat vision group previously open-sourced models such as WeVisOne-VL and WeMM. The open question is delivery: as of publishing, the Hugging Face paper page lists no linked model repo, so weights are not out yet — paper first. For anyone building image applications, the thing to watch is not the benchmark scores but whether the unified-base-model-plus-single-GPU route can hold up inside a real app.","welm-image-wechat-unified-model","2026-11-06T13:30:00Z","2026-11-06T13:11:03.041831Z","2026-11-06T13:11:03.041852Z",true,"agent",589,[39,48,57],{"slug":40,"tag_slug":23,"title_zh":41,"title_en":42,"intro_zh":43,"intro_en":44,"id":45,"is_active":35,"created_at":46,"modified_at":47},"image-generation","图像生成：从文生图到逐框编辑的模型竞赛","Image Generation: from text-to-image to frame-level editing","文生图已是红海，战场正转向编辑与可控性：FLUX.2\u002F3 用开源和量化把生图搬进消费级显卡，Qwen-Image、Seedream 等国产模型紧咬不放，GPT Image 2 则把推理能力带进像素。本专题追踪图像生成与编辑模型的发布、架构演进、加速量化与商业化数据，看「好图」如何变成「可用的图」。","Text-to-image is a crowded race, and the frontier has moved to editing and control: FLUX.2\u002F3 push open weights and quantization onto consumer GPUs, Qwen-Image and Seedream close in from China, and GPT Image 2 brings reasoning into pixels. This topic tracks model releases, architecture shifts, acceleration work, and the business numbers behind \"pretty\" becoming \"usable\".","52de7c59-7864-4569-8ae7-3d656d26a1a1","2026-11-20T07:20:23.534506Z","2026-11-20T07:20:23.534527Z",{"slug":49,"tag_slug":49,"title_zh":50,"title_en":51,"intro_zh":52,"intro_en":53,"id":54,"is_active":35,"created_at":55,"modified_at":56},"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":58,"tag_slug":58,"title_zh":59,"title_en":60,"intro_zh":61,"intro_en":62,"id":63,"is_active":35,"created_at":64,"modified_at":65},"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":67},[68,73,78,83,88,93],{"id":69,"title":70,"news_slug":71,"published_at":72},"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":74,"title":75,"news_slug":76,"published_at":77},"3719a369-508f-4fbe-96df-15f6fbb49f3b","Unlimited-OCR 2:把无限长文档塞进有限上下文","baidu-unlimited-ocr-2-sr-swa","2026-10-27T15:11:27+00:00",{"id":79,"title":80,"news_slug":81,"published_at":82},"a9912456-9f4f-4a4c-b564-83a339402ced","达摩院开源RynnUnify:16B具身大脑先想象再动手","rynnunify-16b-unified-embodied-brain","2026-10-26T13:16:55+00:00",{"id":84,"title":85,"news_slug":86,"published_at":87},"2e705005-bc15-4f79-861e-8409799d7ddb","京东LayerEditor:图像编辑直接输出可复用图层","layereditor-rgba-image-editing-layers","2026-10-24T13:10:00+00:00",{"id":89,"title":90,"news_slug":91,"published_at":92},"bbbda7ff-b1c7-4142-b37f-2b3fd0547e02","Fibo 2.0 开源:生成编辑合一,登顶开源编辑榜","bria-fibo-2-0-unified-editing-generation","2026-10-21T21:08:11+00:00",{"id":94,"title":95,"news_slug":96,"published_at":97},"473ca44d-b179-4c19-a7a6-916dd8b90e4a","FLUX 3 Image 发布:画框控图,逐框编辑","flux-3-image-bounding-boxes","2026-10-02T23:06:31+00:00"]