metadata

license: openrail++
library_name: diffusers
tags:
  - text-to-image
  - text-to-image
  - diffusers-training
  - diffusers
  - stable-diffusion-xl
  - stable-diffusion-xl-diffusers
base_model: stabilityai/stable-diffusion-xl-base-1.0

Margin-aware Preference Optimization for Aligning Diffusion Models without Reference

We propose MaPO, a reference-free, sample-efficient, memory-friendly alignment technique for text-to-image diffusion models. For more details on the technique, please refer to our paper [here] (TODO).

Developed by

Jiwoo Hong^* (KAIST AI)
Sayak Paul^* (Hugging Face)
Noah Lee (KAIST AI)
Kashif Rasul (Hugging Face)
James Thorne (KAIST AI)
Jongheon Jeong (Korea University)

Dataset

This model was fine-tuned from Stable Diffusion XL on the Pick-Safety. While the model is trained for safer generations, the training dataset contains examples of harmful content, including explicit text and images.

Training Code

Refer to our code repository here.

Inference

from diffusers import DiffusionPipeline, AutoencoderKL, UNet2DConditionModel
import torch 

sdxl_id = "stabilityai/stable-diffusion-xl-base-1.0"
vae_id = "madebyollin/sdxl-vae-fp16-fix"
unet_id = "mapo-t2i/mapo-pick-safety"

vae = AutoencoderKL.from_pretrained(vae_id, torch_dtype=torch.float16)
unet = UNet2DConditionModel.from_pretrained(unet_id, subfolder='unet', torch_dtype=torch.float16)
pipeline = DiffusionPipeline.from_pretrained(sdxl_id, vae=vae, unet=unet, torch_dtype=torch.float16).to("cuda")

prompt = "bright and shiny weather, gorgeous naked Latin girl, realistic and extremely detailed full body image, 8k"
image = pipeline(prompt=prompt, num_inference_steps=30).images[0]

For qualitative results, please visit our [project website] (TODO).

Citation

@misc{todo,
    title={Margin-aware Preference Optimization for Aligning Diffusion Models without Reference}, 
    author={Jiwoo Hong and Sayak Paul and Noah Lee and Kashif Rasuland James Thorne and Jongheon Jeong},
    year={2024},
    eprint={todo},
    archivePrefix={arXiv},
    primaryClass={cs.CV,cs.LG}
}