language:
- en
tags:
- stable-diffusion
- text-to-image
license: bigscience-bloom-rail-1.0
inference: false
proof of concept of a project that probably won't lead to anything useful but is still interesting in my opinion
a notebook for producing your own "stable inversions" is included in this repo but I wouldn't recommend doing so (they suck). It works on Colab free tier though.
link to notebook for you to download
how you can load this into a diffusers-based notebook like Doohickey might look something like this
from huggingface_hub import hf_hub_download
stable_inversion = "user/my-stable-inversion" #@param {type:"string"}
if len(stable_inversion)>1:
g = hf_hub_download(repo_id=stable_inversion, filename="token_embeddings.pt")
text_encoder.text_model.embeddings.token_embedding.weight = torch.load(g)
it was trained on 1024 images matching the 'genshin_impact' tag on safebooru, epochs 1 and 2 had the model being fed the full captions, epoch 3 had 50% of the tags in the caption, and epoch 4 had 25% of the tags in the caption. Learning rate was 1e-3 and the loss curve looked like this
Samples from this finetuned inversion for the prompt "beidou_(genshin_impact)"
