I named my simple algorithm that generate new merging recipe near current and let user choose which is better to "learn" the best weight merging ratios with a exaggerated name "RMHF - Reinforcement Merging on Human Feedback".
https://github.com/TkskKurumi/DiffusersFastAPI/blob/main/rmhf_v2.py
Description
This is a merged model of following models. Huge thanks for the creators for these amazing models.
FAQ
Comments (1)
Is there an explanation on RMHF? Would liek to know more about how human-in-the-loop works with art