ljleb

It's in the model name. models for v1.5 have `sd15` in their name. > I have the same problem. But what is interesting, initially, immediately after installing the extension, everything...

Do you see any output in the colab console? It would help with debugging.

To make sure I understand your request, are you referring to creating an endpoint to discover which thresholds (none, a, or a and b) are available for a given annotator?

This is a good idea in my opinion. However, if you are saying you want to update the webui unconditionally on startup, given the current periodically unstable nature of the...

Now that there is at least one release (`v1.0.0-pre`) maybe there's a way to do this in a scalable way? I'm not aware of any official release process but we...

@gsgoldma I see you are using prompt fusion. Seeing this, I'm even more certain that it's an issue caused by the extension. see https://github.com/ljleb/prompt-fusion-extension/issues/35, you may be in a similar...

This is not necessary. See https://github.com/Mikubill/sd-webui-controlnet/pull/683 for updates on the implementation of multi-cn batch.

FWIW, this is what chatGPT returned me: ```python image_path = r"C:\path\to\image.png" import torch from PIL import Image from torchvision.transforms.functional import resize from transformers import CLIPProcessor, CLIPModel import numpy as np...

I'm not sure this will ever get implemented so I'll try to make an extension in the meantime. No idea if I'll get it to work, we'll see!

> @Ehplodor This is exactly what has been done here : sd finetune with text clip replaced by img clip : https://github.com/justinpinkney/stable-diffusion see also : [#4595 (reply in thread)](https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/4595#discussioncomment-4459952) Can...