#ComfyUI Template Trouble

13 messages · Page 1 of 1 (latest)

kind yew
#

I cant seem to figure out whats going on when I am trying to use the comfui template from RunPod.

I am running a basic 4090 with no extra storage so I am going off of the 50GB included in thr workspace. I am supposed to be able to upload my own models I thought if I add them to the /workspace/comfyui/models/checkpoints/ directory (as stated in the extra info tab), but whenever I add my safetensors file it will never appear ComfyUI when I try to use it.

Is there something simple I am missing here to get this to work? I have watched so many videos and talked to Grok and chat gpt and they both give me no answers. Any help is appreciated !

maiden edge
#

Refresh? Press r when you are on comfyui

maiden edge
#

And if it's checkpoint it should be inside the checkpoints dir(folder) inside the ..../model/

kind yew
kind yew
# maiden edge It is not the exact path, I think some letters are capitalized in the comfyui

not sure if I follow, but if I go to the root there is a ComfyUI folder that has its own assets and thats all the stuff that I see right away. When i go into the workspace folder and get to the checkpoints folder thats where I was uploading my checkpoint since thats the pod volume. But according to the readme from the template it should be already looking for checkpoints added to that folder

maiden edge
#

Only /workspace if you use ns or volume disk won't be cleared

kind yew
#

Custom Models
You can add your own models by placing them in the appropriate directories under /workspace/comfyui/models/:

Checkpoints: /workspace/comfyui/models/checkpoints/
VAE: /workspace/comfyui/models/vae/
LoRA: /workspace/comfyui/models/loras/
Controlnet: /workspace/comfyui/models/controlnet/
Upscalers: /workspace/comfyui/models/upscale_models/
Embeddings: /workspace/comfyui/models/embeddings/
CLIP: /workspace/comfyui/models/clip/
CLIP Vision: /workspace/comfyui/models/clip_vision/
These paths are configured in ComfyUI's extra_model_paths.yml file, so models placed in these directories will be automatically detected by ComfyUI.

#

So thats what the readme says on the official comfyui template they made, I feel like its pretty straightforward as it says they will be recognized if models are dropped in any of those locations. I dont know if im really just misunderstanding all of this but it seems like it should be pretty straightforward but its not

maiden edge
#

Ohh right the path seems correct

maiden edge
kind yew
#

Yea not sure whats good i ended up just switching to a community template for comfyui and it works. Deff feels like something is wrong with runpod's official one. I made a support ticket with them just to be safe and bring it to their attention