koboldcpp/imgmodel：KoboldCpp 图像生成模型仓库

AI 摘要

Hugging Face 上出现 koboldcpp/imgmodel 仓库，提供若干简易图像生成模型。用户可通过 KoboldCpp 加载 Stable Diffusion 1.5、SDXL、SD3 或 Flux 模型，其中 SD3 和 Flux 还需额外 Clip 与 T5-XXL 模型。该仓库通过 --sdmodel 参数及启动器图像标签页提供加载入口，并链接 stable-diffusion.cpp 文档列出支持的模型。

正文节选

This repo contains a few simple image generation models. You can also load any Stable Diffusion 1.5, SDXL, SD3 or Flux model into KoboldCpp. For SD1.5 and SDXL, you only need the basic model (and VAE fix if no baked VAE). For SD3 and Flux you will also need a Clip and T5-XXL model (not included here) You can use `--sdmodel` to load the base model, and check `--help` for other SD settings. They are all also available in the image tab in the launcher ![image/png](https://cdn-uploads.huggingfac

发布时间：2026-10-30 18:00

抓取时间：2026-10-30 18:01

来源机构：Hugging Face