微信团队发布 WeLM-Image：统一图像生成模型
WeLM-Image: A Unified Image Generation Model towards Visual Intelligence
微信团队开源的图像模型，理解编辑生成一条龙，单卡 H20 五秒出图，三项开源榜第一，做图像应用可以关注。
微信团队推出统一图像基础模型 WeLM-Image，覆盖文生图、指令编辑和多参考合成三类任务，面向单 GPU 部署场景。模型采用 Mixture-of-Transformers 骨干加 MoE 模块，存储参数 31.7B，每个目标 latent token 激活约 5.4B 生成参数，支持原生 1.5K 分辨率训练。在 PRISM-Bench、Qwen-Image-Bench 和 UnicBench 三项评测中，1536 分辨率版本在参评开源模型中排名第一。经 MeanFlow 少步蒸馏得到的 WeLM-Image-Turbo，在单张 NVIDIA H20 上用 8 步无引导采样，4.98 秒生成一张 1024×1024 图像。
WeLM-Image: A Unified Image Generation Model towards Visual Intelligence
We present \textbf{WeLM-Image}, a unified image foundation model that integrates multimodal understanding into text-to-image generation, instruction-guided editing, and multi-reference synthesis. Designed for single-GPU deployment in WeChat's large-scale consumer applications, the model processes text, reference images, and target latents as one interleaved sequence. A Mixture-of-Transformers (MoT) backbone combines shared attention with independent understanding and generation parameters to limit optimization interference. Equipping each path with Mixture-of-Experts (MoE) modules provides sparse capacity, with 31.7B stored parameters and approximately 5.4B generation parameters activated per target latent token. A generation-oriented data engine combines a knowledge-grounded visual vocabulary with large-scale visual clustering to balance semantic coverage and editing tasks, while training-time evaluation guides iterative data refinement. Bilingual annotations and verified editing supervision support progressive training up to native 1.5K resolution. We optimize generation and editing separately with rubric- and checklist-based rewards, then consolidate the specialized policies through noise-aware on-policy distillation. In the reported overall comparisons, the 1536-resolution model ranks first among the evaluated open-source models on PRISM-Bench, Qwen-Image-Bench, and UnicBench. MeanFlow-based few-step distillation yields WeLM-Image-Turbo, which generates a $1024\times1024$ image in 4.98\,s on a single NVIDIA H20 GPU using eight guidance-free steps.
