ControlNet
ControlNet copied to clipboard
lllyasviel
Let us control diffusion models!
Do you plan to make it available? I read it's trained with SD2.1 on your paper
For now, pose2image requires an image of a real person. If the skeleton cannot be manipulated due to a problem with the Gradion UI, I wonder if it is possible...
Hi Love this looks fantastic. I knew there must be a way of combining open pose with diffusion. Had it working great on a previous commit. Rebuilt environment and a...
There are a lot of scripts in this repo, so a way to keep track of all of them is needed. Each script should save outputs to it's own folder...
RuntimeError: CUDA out of memory. Tried to allocate 58.00 MiB (GPU 0; 8.00 GiB total capacity; 7.14 GiB already allocated; 0 bytes free; 7.26 GiB reserved in total by PyTorch)...
As the subject says. Is it possible to install this in venv instead of using Conda? I don't like all the virtual environments that is created on C: all the...
We really need batch size or infinite generation with save output in a folder i wish they were ready now :/ i need to generate hundreds of images asap to...
### Discussed in https://github.com/lllyasviel/ControlNet/discussions/30 Originally posted by **lllyasviel** February 12, 2023 We plan to train some models with "double controls", use two concat control maps and we are considering using...
It seems that I already used many tricks but training still OOM for 8GB gpu. But inference is good now. This is strange because I know some textural inversion or...