Krea2 HD V1 Krea2 Turbo 高清优化版，同步微调 VAE，更多细节、更好质感 。 Krea2 Turbo HD optimized version, with synchronized fine tuned VAE, more details, better texture. ✌️✌️✌️ 0Day Support " int4 convrot " quantized format with Comfy Org, Krea2 Turbo HD V1 int4 convrot.safetensors 针对低显存的用户，推荐 smthemex/ComfyUI UniBlockSwap ，只需 4 6GB 显存，即可跑 bf16 全量模型。 Recommend smthemex/ComfyUI UniBlockSwap plugin for LOW VRAM users, it only requires 4 6GB of VRAM to run the full bf16 model. 您可以尝试一下全新的 ComfyUI GGUF 模型加载插件 smthemex/ComfyUI Dif GGUF ，它能适配更多的 GGUF 文件格式，并且将很快集成低显存(4 8GB)显卡的 GGUF 模型块卸载管理能力。 Recommend to try the new GGUF ComfyUI loader plugin, smthemex/ComfyUI Dif GGUF , it compatible with more GGUF format, and will add low VRAM (4 8GB) management for GGUF soon. 采用极致优化的分层加混合精度量化方式，确保 4bit 以上都能获得良好的输出质感，把量化损失降到最低。不同量化精度出图品质对比如下(Using an extremely optimized layered mixed precision quantization method, it ensures good output quality for 4 bit and above while minimizing quantization loss. Here's a comparison of image quality at different quantization levels:)： mxfp4 和 nvfp4 量化的 gguf 格式，目前属于试验阶段，供有试用经验的爱好者下载测试，目前 ComfyUI GGUF 插件还未提供 torch dequant 代码，跑的话会非常慢。本仓库提供的所有 gguf 格式模型，目前 ComfyUI 环境均可直接加载。(The mxfp4 and nvf…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy