Post
444
USO 🎨 Unified customization model released by Bytedance research
Demo
bytedance-research/USO
Model
bytedance-research/USO
Paper
USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning (2508.18966)
✨ Large-scale triplet dataset (content, style, stylized)
✨ Disentangled learning: style alignment + content preservation
✨ Style Reward Learning (SRL) for higher fidelity
✨ USO-Bench: 1st benchmark for style & subject jointly
✨ SOTA results on subject consistency & style similarity
Demo
bytedance-research/USO
Model
bytedance-research/USO
Paper
USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning (2508.18966)
✨ Large-scale triplet dataset (content, style, stylized)
✨ Disentangled learning: style alignment + content preservation
✨ Style Reward Learning (SRL) for higher fidelity
✨ USO-Bench: 1st benchmark for style & subject jointly
✨ SOTA results on subject consistency & style similarity