Spaces:
Running
on
T4
What's needed to load the model into stable-diffusion webui?
Hello im trying to load the model into google colab and get the error:
size mismatch for model.diffusion_model.input_blocks.0.0.weight: copying a param with shape torch.Size([320, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([320, 4, 3, 3]).
Any help is appreciated
You have to modify the sd_config to use the settings found in generate.yaml
Check the code for in-painting hijack and do something similar.
https://github.com/Klace/stable-diffusion-webui-pix2pix
Here you go. Just need to download the model yourself and place in the StableDiffusion model directory and make sure you switch before using it
It's in the "Extensions" tab of the web UI
There is a new tab there you got to click "Apply and restart UI" to get it
I loaded this model into webUI and it works but I can't get it to produce results even remotely as good as this webapp does. What settings are people using for it to come out roughly the same?
Follow this video guide https://www.youtube.com/watch?v=0fkGd9wIhrA