I've seen in the earlier discussion that it is faster to bake models in the images thanks to runpod flashboot, in https://discordapp.com/channels/912829806415085598/1364592893867724910. Thanks to @hardy creek for explaining it!
Does that mean I have to bake comfyUI git repo and all the other custom nodes and requirements too?
And how does it make it faster then just using network volume?
#How to bake models checkpoints in docker images in ComfyUI
sudden badge
hardy bridgeBOT
crystal silo
it is faster because it uses Container Disk
instead of reading the files from Network volume / storage
Does that mean I have to bake comfyUI git repo and all the other custom nodes and requirements too? Yes sure, this is an easy way
comfyui might load abit faster than if you place the comfyui in network storage
sudden badge
comfyui might load abit faster than if you place the comfyui in network storage
Thanks for the reply! I'm a bit confused because If I bake the models in docker images, I have to place the models in /ComfyUI/models folder. So I must need a comfyUI repository before baking the models.. so I have to bake the comfyui git repo in the image too.
Or am I understanding it wrong? because it seems to me that you are saying that comfyui can be placed in network volume, without adding it to the image.
crystal silo
yes either those 2 in image or copy it to /workspace then run from there