Diffusion Self-Distillation for Zero-Shot Customized Image Generation
Paper • 2411.18616 • Published • 16
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("primecai/dsd_model")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Diffusion Self-Distillation Model Card
This is a model card for the diffusion self-distillation model for personalized/subject-driven generation from a single image.
The model is fine-tuned from the FLUX.1-dev model as
described in our CVPR'2025 paper titled "Diffusion Self-Distillation for Zero-Shot Customized Image Generation".
Model Details
- Developed by: Shengqu Cai, Eric Ryan Chan, Yunzhi Zhang, Leonidas Guibas, Jiajun Wu, Gordon Wetzstein.
- License: Apache License License Version 2.0.
- Resources for more information: Project Website, Paper, Code.
- Cite as:
@inproceedings{cai2024dsd,
author={Cai, Shengqu and Chan, Eric and Zhang, Yunzhi and Guibas, Leonidas and Wu, Jiajun and Wetzstein, Gordon.},
title={Diffusion Self-Distillation for Zero-Shot Customized Image Generation},
booktitle={CVPR},
year={2025}
}
- Downloads last month
- 15
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support