腾讯混元 Hy Image3.5 预览版上线 ComfyUI
ComfyUI ✖️ Hy Image3.5 preview
ComfyUI ✖️ Hy Image3.5 preview Hy Image3.5 预览版现已在 ComfyUI 上线。 专业级图像生成，人工评测胜率较 Hy Image3.0 提升 +30% → 文生图与图生图合一模型，最高支持 2K → 多语言文字、符号与小字均能正确渲染 → 电影感、漫画、商业摄影与插画风格 → 人物身份与产品特征在场景、服装与风格变化中保持一致
查看原帖Hy Image3.5 preview is now available in ComfyUI. Professional-grade image generation, +30% win rate in human eval vs Hy Image3.0 → Text to image and Image to image in one model, up to 2K → Multilingual text, symbols, and small print that render correctly → Cinematic, comic, commercial photography, and illustration styles → Identity and product features…
展开完整原文
Hy Image3.5 preview is now available in ComfyUI. Professional-grade image generation, +30% win rate in human eval vs Hy Image3.0 → Text to image and Image to image in one model, up to 2K → Multilingual text, symbols, and small print that render correctly → Cinematic, comic, commercial photography, and illustration styles → Identity and product features that hold through scene, outfit, and style changes
正文
当前显示原文，中文全文译文尚未就绪。
ComfyUI ✖️ Hy Image3.5 preview