-
Notifications
You must be signed in to change notification settings - Fork 317
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
windows下跑的很慢,但跑起来了,记录一下安装过程 #108
Comments
SDXL_CLIP2_CKPT_PTH = './models/open_clip_pytorch_model.bin' |
您好,请教下,现存这个,您是怎么控制在8G内呢 |
你好,请问下你的电脑是什么配置?这个4090能跑吗,我看硬件要求60G的显存 |
You guys can't use ComfyUI-SUPIR? |
那里面太多实现错误了 |
好像只能添加 --no_llava,看#65 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
先按照#11中MatthewK78的说明修改requirements.txt,然后根据存放模型的路径修改CKPT_PTH.py和SUPIR_v0.yaml文件,例如我要将模型存放在项目根目录下新建的models文件夹内:
修改CKPT_PTH.py:
修改./option/SUPIR_v0.yaml(约152行开始):
models文件夹如下:
clip-vit-large-patch14、clip-vit-large-patch14-336和llava-v1.5-13b如果已经安装过git lfs可以从huggingface上直接git clone,然后下载open_clip_pytorch_model.bin和sd_xl_base_1.0_0.9vae.safetensors,最后从Google drive下载SUPIR-v0F.ckpt和SUPIR-v0Q.ckpt,总共3个文件夹和4个文件放入models下。
The text was updated successfully, but these errors were encountered: