Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Object/Vision AI/Image to Image/
AI Image Editing
Search

AI Image Editing

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2023 Jun 14 6:24
Editor
Editor
Seonglae ChoSeonglae Cho
Edited
Edited
2025 Dec 3 10:29
Refs
Refs
Face Embedding

Style transfer

AI Image Editing Models
Qwen-Image-Edit
EditBench
MGIE
TurboEdit
BAGEL
 
 
 

USO

USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning
We announce USO, a unified style-subject optimized customization model and the latest addition to the UXO family. USO can freely combine any subjects with any styles in any scenarios, delivering outputs with high subject/identity consistency and strong style fidelity while ensuring natural, non-plastic portraits. In line with our past practice, we will open-source the full project, including training code, inference scripts, model weights, and datasets, to advance research and empower the open-source community.
USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning
https://bytedance.github.io/USO/

Lighting, Illumination harmonization

Scaling In-the-Wild Training for Diffusion-based Illumination...
Diffusion-based image generators are becoming unique methods for illumination harmonization and editing. The current bottleneck in scaling up the training of diffusion-based illumination editing...
Scaling In-the-Wild Training for Diffusion-based Illumination...
https://openreview.net/forum?id=u1cQYxRI1H
 
 

Table of Contents
Style transferUSOLighting, Illumination harmonization

Backlinks

Face AI

Recommendations

Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Object/Vision AI/Image to Image/
AI Image Editing
Copyright Seonglae Cho