Sign in

Nodes Browser

ComfyDeploy: How ComfyUI-Load-Diffusion-Model-to-Muti-GPUs works in ComfyUI?

What is ComfyUI-Load-Diffusion-Model-to-Muti-GPUs?

NODES: OverrideLoadedDiffusionDevice. I happen to have two graphics cards, and I want to load models into another graphics card in Comfyui, so I designed this small node.

How to install it in ComfyDeploy?

Head over to the machine page

  1. Click on the "Create a new machine" button
  2. Select the Edit build steps
  3. Add a new step -> Custom Node
  4. Search for ComfyUI-Load-Diffusion-Model-to-Muti-GPUs and select it
  5. Close the build step dialig and then click on the "Save" button to rebuild the machine

ComfyUI-Load-Diffusion-Model-to-Muti-GPUs

I happen to have two graphics cards, and I want to load models into another graphics card in Comfyui, so I designed this small node. Put the .py file into custom_nodes,in comfyui,seach "Force/Set Loaded Diffusion Model Device" node. For exsample: You can start your comfyui with GPU 0,and send hunyuan model to pure empty GPU 1 to get the Max frame. 6b605d39eb47b3322af1ec0b9f2b9dc2