Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models
Paper • 2503.08434 • Published • 1
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("atfortes/BokehDiffusion", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Bokeh Diffusion
This is the model checkpoint of "Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models" (ACM SIGGRAPH Asia 2025).
- Project: atfortes.github.io/projects/bokeh-diffusion/
- Paper: arxiv/2503.08434
- GitHub: atfortes/BokehDiffusion
Citation
If you use this model, please cite our work:
@article{fortes2025bokeh,
title = {Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models},
author = {Fortes, Armando and Wei, Tianyi and Zhou, Shangchen and Pan, Xingang},
journal = {arXiv preprint arXiv:2503.08434},
year = {2025},
}
- Downloads last month
- 32
Model tree for atfortes/BokehDiffusion
Base model
black-forest-labs/FLUX.1-dev