Alexpan
Alexpan
等着吧,我一定要实现它
This because a bug of git version, when i use git version 1.8.3.1 it`s not support git -C "path_dir", while it shoud be git -c change the code launch.py "-C"...
try the final ultra :!!! `pip3 install --prefer-binary accelerate transformers diffusers einops pytorch-lightning torchsde safetensors torch torchvision --extra-index-url https://download.pytorch.org/whl/nightly/cpu --pre torch `
经过微调训练后,能够出真实摄影风格的照片了
same on diffusers 0.19.0 0.20.0
same question ,how!!!!
i had impliment multicontrol , may need more tranning, conditions mix result
i had same problem , and i found /opt/anaconda3/envs/llm/lib/python3.10/site-packages/FlagEmbedding/visual/eva_clip/ not had any dir of /FlagEmbedding/visual/eva_clip/model_configs i copy it to the site-packeges dir , it run succ!
modify the code anaconda3/envs/webui2/lib/python3.12/site-packages/ultralytics/nn/tasks.py:1237 ckpt = torch.load(file, map_location="cpu", weights_only=False) will solve this problem in pytorch 2.6
accoding to the paper and the Comfyui will impliment below: 1. SUPIR MODEL_LOADER -> SUPIR_MODEL, SUPIR_vae - SUPIR_VAE = vae.from_config and load conveted state_dict - -- 2. SUPIR_FIRSTSTAGE Denoiser :...