Make PaperCut and VoxelArt models load again
This corrects a regression in loading of these models due to a change of the embedding_manager parameter num_vectors_per_token
Reverting to the original version (1) does not seem to affect concept embeddings.
Fixes #1718
@damian0815 I do not recall why we changed num_vectors_per_token from 1 to 8. If there is a good reason for it to be 8, I will make a new inference configuration file and use it when the PaperCut and VoxelArt models are configured. Please let me know.
also fixes #1657
after setting this back to 1, please test if https://huggingface.co/datasets/Nerfgun3/bad_prompt/blob/main/bad_prompt_version2.pt loads (it has a vector length of 8)
i do not know how to verify if it's actually working but @blessedcoolant has a prompt created in a similar way.
also fixes #1657
after setting this back to 1, please test if https://huggingface.co/datasets/Nerfgun3/bad_prompt/blob/main/bad_prompt_version2.pt loads (it has a vector length of 8)
i do not know how to verify if it's actually working but @blessedcoolant has a prompt created in a similar way.
Both bad_prompt.pt and bad_prompt_version2.pt load as embeddings without any obvious problems. I don't understand what this negative prompt is supposed to do, but using it created images that looked OK.
I don't understand what this negative prompt is supposed to do
IIUC, it's a "stock" negative prompt which one would use for all generations by including 'bad_prompt' or some such in every prompt (as opposed to copy-pasting a long list every time). Impossible to tell what it actually does without knowing what terms are included in the negation list.
a bunch of the ones we make fun of for being pointless. nevertheless, commonly used.
right, it's just that not knowing what it does makes it hard to know if it's being loaded correctly (all 8 vectors) or if it's being truncated (just the 1st vector is loaded/used and it "seems" ok but actually isnt).
I've just updated main using Git and running the latest, and I see Papercut and voxel_art are not currently loading. Do we need to run any update scripts to get these to work?