Casey Parker

I believe the code you're looking for is in the `README.MD` file: ```python from stable_diffusion_videos import StableDiffusionWalkPipeline, Interface import torch pipeline = StableDiffusionWalkPipeline.from_pretrained( "CompVis/stable-diffusion-v1-4", torch_dtype=torch.float16, revision="fp16", ).to("cuda") interface = Interface(pipeline)...

This is only intended to keep the version numbers above the given versions, so we could also use >= probably. The reason for them is that both are requirements for...

Something along the lines of ```negative_prompt=['missing limbs, missing fingers, extra limbs, nsfw, bad anatomy, extra fingers, fewer fingers, face'],``` in with your seeds and audio and such should do it

Have you tried ```pip install -U -e .``` in a clone of this repo? That might shed some light on where things are going off.

Can you give your environment? It looks like you're on python 3.8, which could have to do with it in some way. If you can, it's best to set up...