allo-

You can extend the script using the method from this notebook: https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/stable_conceptualizer_inference.ipynb Have a look at the "Load the newly learned embeddings into CLIP" section. `text_encoder` and `tokenizer` are properties...

Yes. I've got some code to load learned embeddings to continue training as well. I wonder if I should put it into the same pull requests. It's basically the load...

Later then. I also still have the use_auth_token code in my copy of the script and so on and should merge and test it with diffusers git before.

Does `repo.push_to_hub` push the full model or the embeddings only?

Closing here and leaving the pull request open.

The main change request is to add documentation, isn't it? I'm willing to do it, I think I would just add a sentence under the example command line. I should...

This may get a bit long for the documentation, maybe it should better be a second example script. The main part is simple: ```python # Load the learned embeds learned_embeds_dict...

Looks like the latest changes change quite a bit. I wonder if I should push the full script into my repo and you like to have a look at the...

   Have a look at the skin or the eyes. The esrgan from the webui introduces noise while real-esrgan looks smooth.

I think everything related to this is on default settings. Especially I did not configure fp16 anywhere.