Implementation of ReFL StableDiffusionXL with LoRA

THUDM / ImageReward

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

Apache License 2.0

1.18k stars 65 forks source link

Closed alirezadizaji closed 2 months ago

alirezadizaji commented 2 months ago

Hi, This PR implements training ReFL with LoRA using SDXL, which enables faster fine-tuning with higher batch size.

xujz18 commented 2 months ago

Cool! Thanks a lot!