OneTrainer is a one-stop solution for all your stable diffusion training needs.
GNU Affero General Public License v3.0
1.34k
stars
110
forks
source link
[Bug]: unexpected difference between latent image and latent conditioning image #363
Open
seniorsolt opened 4 days ago
What happened?
I'm training finetune inpaint stable diffusion 1.5 with masking.![Без названия](https://github.com/Nerogar/OneTrainer/assets/102902511/814699c7-5b44-42c4-ae25-faac563dbcc1)
I think it's because there are two different modes for latent in SampleVAEDistribution.py from mgds:
What did you expect would happen?
I expect to see difference between latent image and latent conditioning image only within masked area.
Relevant log output
No response
Output of
pip freeze
No response