atfortes/BokehDiffusion
[SIGGRAPH Asia 2025] Official code for "Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models."
This project helps photographers, graphic designers, and digital artists create images with realistic depth-of-field effects directly from text descriptions. You provide a text prompt describing your desired image and specify a 'bokeh target' value, and it generates an image where certain areas are sharply in focus while others are artfully blurred. This is for anyone who wants to control the artistic blur (bokeh) in their AI-generated images without needing complex photography or editing software.
120 stars.
Use this if you need to generate visually rich images from text with precise control over the foreground and background blur, mimicking professional photographic bokeh.
Not ideal if you need to apply bokeh effects to existing images or videos, as this tool focuses on generating new images from scratch.
Stars
120
Forks
7
Language
Python
License
—
Category
Last pushed
Nov 12, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/atfortes/BokehDiffusion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cswry/SeeSR
[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
JJLibra/SALAD-Pan
🤗 Official implementation for "SALAD-Pan: Sensor-Agnostic Latent Adaptive Diffusion for...
open-mmlab/mmgeneration
MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.
Janspiry/Image-Super-Resolution-via-Iterative-Refinement
Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch
hanjq17/Spectrum
[CVPR 2026] Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration