Adobe Lightroom 移动版新增一键睁眼功能，用生成式 AI 修复闭眼照片
Adobe 宣布 iOS、iPadOS 和 Android 版 Lightroom 移动端新增 Open Eyes 快捷操作，检测到照片中人物闭眼时可一键用生成式 AI 睁开双眼。
#图像生成
The Verge · AIAI 评分4040 极客公园AI 评分6262 Lovart 2.0 推出个人设计 Agent Arti
Lovart 迭代到 2.0 后推出个人设计 Agent Arti，通过记忆功能记录设计师的行业、身份与审美偏好，并主动承担调研、找参考和画布检查。Arti 会把反复出现的设计流程沉淀为可复用 Skill，还支持设定时间与频率的设计委托，按快速、均衡、专家三档模式批量执行。作者实测用 Arti 完成攀岩品牌电商物料调研，并发现它提示海报比例不符可一键调整。
量子位AI 评分6262 Meshy 推出局部编辑功能 Meshy Edit，一句话指令修改 3D 模型局部
Meshy 发布局部编辑功能 Meshy Edit，用户圈选 3D 模型区域并用一句话描述改动，约一分钟生成新模型，未选中区域保持原样。该功能已向全部注册用户开放，每次编辑消耗 20 积分，目前支持 Meshy 6 和 Meshy 7.1 生成的高精度模型，带贴图模型会自动切换至未贴图版本编辑。
AK@_akhaliqAI 评分3838
Emad@EMostaqueAI 评分3838初代Stable Diffusion的FID分数为12.63
引用Liang Zheng@LiangZheng_06(1/n) people used to think that pretraining a T2I model requires expensive A100/H100 GPUs. it is a barrier for beginners and educators. we break the barrier. we introduce MiniDog (NeurIPS Education Track): you can pretrain a T2I model on 3090s in 55 minutes. FID = 8.32. 👇
- AK@_akhaliqAI 评分3030
BudgetPix 面向像素空间图像扩散的计算自适应分词 论文：https://huggingface.co/papers/2610.12307
Qwen@Alibaba_Qwen精选AI 评分7070Qwen 发布 Qwen-Image-2.1-Turbo，在同样的 7B 视觉生成架构上做加速，仅需 8 步去噪即可生成和编辑图像，权重已在 ModelScope 和 Hugging Face 开放。
引用Qwen@Alibaba_QwenMeet Qwen-Image-2.1, the most balanced and cost-effective image generation model in the Qwen-Image series! Now open weights! 🎨 A unified model for both generation and editing, delivering top-tier quality in a lightweight package. Highlights: 👀 - Compact & exceptionally fast: A lightweight 7B architecture that outperforms most closed-source models, with drastically accelerated inference for multi-image inputs. - Native transparency: Natively generates and edits RGBA layers, enabling seamless compositing and text editing within transparent images. - Versatile, high-fidelity editing: Supports up to 10 reference images and precise local control while preserving strict fidelity for portraits and products. - Broad coverage & stunning aesthetics: Excels at panoramas, infographics, and virtual try-ons, delivering realistic textures and elegant typography. Start to create your next masterpiece with Qwen-Image-2.1! 🖼️ - Blog: https://qwen.ai/blog?id=qwen-image-2.1 - GitHub: https://github.com/QwenLM/Qwen-Image-2.1 - Model Scope: https://www.modelscope.cn/models/Qwen/Qwen-Image-2.1 - Hugging Face: https://huggingface.co/Qwen/Qwen-Image-2.1
推荐理由：官方给出 Turbo 加速版在 8 步去噪下仍能生成 2K 图像，并同步开放权重与 API，便于判断落地成本。
- AK@_akhaliqAI 评分3838
Iris-3B 超越潜在空间：像素空间扩散训练、转换与微调 论文：https://huggingface.co/papers/2610.09450
- Qwen@Alibaba_QwenAI 评分5858引用Arena.ai@arena
Qwen-Image-2.1 by @Alibaba_Qwen just landed as the #1 open source model in the Image Edit Arena and Text-to-Image Arena! With 1367 pts in the Image Edit Arena, Qwen-Image-2.1 took the #1 spot among open. It landed #16 overall, just 3 pts from GPT-Image-1.5-high-fidelity at #15. See the leaderboard for the Text-to-Image arena below. Congrats to the @Alibaba_Qwen team on this contribution to the open source ecosystem!
- Qwen@Alibaba_QwenAI 评分3333
来自 @inteldevs 的 Day-0 OpenVINO 支持！🥳 Qwen-Image-2.1 已可在 Intel 硬件上优化运行。一个开放权重 checkpoint，同时支持生成与编辑。👇
引用Intel Devs@inteldevsWe're excited to offer Day0 OpenVINO support for Qwen-Image-2.1 Read more about what you can accomplish here: https://ms.spr.ly/6019a5nm5
- Qwen@Alibaba_QwenAI 评分4242
感谢 @sgl_project 的 day-0 支持！🙌 SGLang-Diffusion 现已支持 Qwen-Image-2.1：文生图、多图编辑和透明 RGBA 输出。快来试试！🎨
引用SGLang@sgl_projectDay-0 support for @Alibaba_Qwen’s Qwen-Image 2.1 is here in SGLang-Diffusion! 🖥️ Native precision on a single RTX 4090 24GB with CPU offload - 1024×1024 generation in 18.7s and image editing in 21.7s with 22.7 GiB peak GPU memory during requests. - On an RTX PRO 6000 96GB: 8.0s generation and 9.6s editing. 🎨 Text-to-image, multi-image editing, and transparent RGBA output—all with one checkpoint. ⚡ Native inference with TP/SP, LoRA, and OpenAI-compatible APIs. 40 denoising steps, one image per request, warmed HTTP latency including PNG output. No quantization. Cookbook and GPU-specific commands below 👇
- Qwen@Alibaba_Qwen精选AI 评分6767引用Hugging Apps@HuggingApps
Qwen Image 2.1 is here! 🖼️ A 7B params native image generation and editing model, with up to 10 image references The model comes with it's own prompt enhancement LLMs, integrated with diffusers 🧨 and ComfyUI ▶️ on Spaces https://huggingface.co/spaces/hugging-apps/qwen-image-2-1
推荐理由：Qwen-Image-2.1 在 Hugging Face Spaces 上线可直接试用的在线 demo，读者无需配置环境即可体验生成与编辑共用一个 checkpoint 的效果。
- Qwen@Alibaba_QwenAI 评分4242
Qwen-Image-2.1 现已在 ComfyUI 中支持！立即试用并分享你的创作！🖼️
引用ComfyUI@ComfyUIQwen-Image-2.1 is now supported in ComfyUI! Open weights. One 7B checkpoint that generates and edits. → Image generation at native 2K → Instruction editing from up to 10 reference images in a single pass → RGBA output, alpha included
- Qwen@Alibaba_QwenAI 评分5858引用vLLM@vllm_project
Qwen-Image-2.1 from @Alibaba_Qwen has day-0 support in vLLM-Omni. 🎉 Generate, edit, and create transparent images with one model: a 7.1B DiT paired with Qwen3-VL-8B. Setup and supported combinations 👇 https://recipes.vllm.ai/Qwen/Qwen-Image-2.1
- Qwen@Alibaba_Qwen精选AI 评分7575
推荐理由：官方给出 7B 轻量架构、原生 RGBA 透明图层与最多 10 张参考图编辑等能力，可据此判断开源图像模型的实际可用边界。
Google AI@GoogleAI精选AI 评分7070
推荐理由：官方给出 Google Pics 的图像编辑能力与订阅、Workspace 开放范围，可据此判断可用性。
Berkeley AI ResearchAI 评分3838 Berkeley AI Research 提出基于信息量的成像系统设计框架
Berkeley AI Research 提出一种直接以互信息评估和优化成像系统的框架，无需任务专用解码器。该信息指标在彩色摄影、射电天文、无透镜成像和显微镜四个领域预测了系统性能，优化后的设计达到与端到端方法相当的水平，且内存和算力需求更低。方法利用已知噪声物理直接计算噪声项，仅需从测量数据中学习测量分布，并给出真实信息量的上界。