Diffusion DPO LoRA - a radames Collection

radames 's Collections

Candle Wasm Examples

WebML

Gradio Examples / Hacks

Diffusion DPO LoRA

Gradio Custom Components

Diffusion DPO LoRA

updated Jan 12, 2024

How to train: https://github.com/huggingface/diffusers/tree/main/examples/research_projects/diffusion_dpo

radames/sdxl-DPO-LoRA

Text-to-Image • Updated Feb 9, 2024 • 57 • 17
radames/sd-21-DPO-LoRA

Text-to-Image • Updated Jan 16, 2024 • 73 • 6
radames/sdxl-turbo-DPO-LoRA

Text-to-Image • Updated Feb 11, 2024 • 75 • 12
Diffusion Model Alignment Using Direct Preference Optimization

Paper • 2311.12908 • Published Nov 21, 2023 • 50

Note