Swift-Image: Exploring the Performance Frontier of Compact Unified Image Generation Models
We present Swift-Image, a compact unified model for text-to-image generation, single-image editing, and multi-image editing. Our goal is to explore how far a relatively small visual generator can be pushed through systematic training engineering under a constrained computational budget. Swift-Image adopts an efficient 6B single-stream DiT and a progressive training pipeline that evolves from broad semantic coverage to higher resolution, stronger visual quality, and unified generation-editing supervision. For post-training, we employ parallel expert reinforcement learning followed by multi-teac
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%Tongyi-MAI/Z-Image-Turbo →
“Fuzzy title match (0.73): “Swift-Image: Exploring the Performance Frontier of Compact U” ≈ “Tongyi-MAI/Z-Image-Turbo””
- FuzzySimilar title/name (fuzzy) · 87%modelscope/ms-swift →
“Fuzzy title match (0.94): “Swift-Image: Exploring the Performance Frontier of Compact U” ≈ “modelscope/ms-swift””
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%sgl-project/sglang →
“Shared author/contributor keys: zhou”
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- LinkedLinked via arxiv author · 85%Taihang Hu →
“Swift-Image: Exploring the Performance Frontier of Compact Unified Image Generation Models”
- LinkedLinked via arxiv author · 85%Mianzhao Wang →
“Swift-Image: Exploring the Performance Frontier of Compact Unified Image Generation Models”