flux_dev_4 Q_gguf+Hyper_SD低显存、高效率出超清优质图最优解
FLUX.1-dev-gguf:这是black-forest-labs/FLUX.1-dev的直接 GGUF 转换,GGUF格式模型可以显著提升模型部署后的推理速度,同时可以有效降低模型使用时对于内存、显存的占用
Hyper-SD:超清高效出图lora
ComfyUI-GGUF:https://github.com/city96/ComfyUI-GGUF?tab=readme-ov-file
FLUX.1-dev-ggu:https://huggingface.co/city96/FLUX.1-dev-gguf/tree/main
FLUX.1-schnell-gguf:https://huggingface.co/city96/FLUX.1-schnell-gguf/tree/main
t5-v1_1-xxl-encoder-gguf:https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf/tree/main
Clip:https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main
网盘
工作流:https://pan.quark.cn/s/e76d9e972e8c
模型:https://pan.quark.cn/s/5a0ab8dfce6e
插件:https://pan.quark.cn/s/16dca69ca023