ComfyUI
ComfyUI copied to clipboard
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Similar to SaveImage node, images generated get dumped into it, not save the images, but images be selectable or droplist to select etc, with the selected going to an image...
As a Comfy user, I would like to clearly understand which step of the flow is currently executing in the UI so I dont have to check the command window...
is there a way to import an image sequence? something like (file.####.png)?? Loving this!!
I often use UE4 as a production tool, using ComfyUI Afterwards, I felt that the operating habits were not very consistent, and I was very annoyed. The main reason here...
i tried to open the ui and got this error 
Like loadimage/loadimagemask nodes has mask output, but that requires loading an image when prior processing has an image, we don't need to load, but need a path to create mask...
After python main.py, 127.0.0.1:8188 didn't display anything but blank with no errors reported.  
Add ability to turn the flow into a python script that can be executed stand-alone
I've found that ComfyUI is capable of workflows that aren't possible in Auto1111 or InvokeAI, and I think it can be even further improved by number and math nodes. A...
This node will create transparent paddings to existed image and generate correct mask. Now, users can do outpaint in pipeline directly