EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing
High-resolution image editing is increasingly demanded in professional workflows, yet existing diffusion-based models remain constrained to resolutions below 1K due to quadratic attention complexity and prohibitive memory requirements. A prevalent workaround employs a two-stage pipeline: editing at low resolution followed by independent super-resolution. However, this approach suffers from two critical issues: information divergence, where hallucinated details contradict the original high-resolution (HR) source, and texture degradation, manifesting as over-smoothed or over-sharpened artifacts.
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): “EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolu” ≈ “Tongyi-MAI/Z-Image-Turbo””
- PossiblePossibly related (embedding) · 50%[Paper] Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling →
- PossiblePossibly related (embedding) · 49%Implementing super resolution by deploying SeedVR2 on Amazon SageMaker AI →
- PossiblePossibly related (embedding) · 46%Krea-2-Turbo Image Model - Easy to be fully uncensored, but it can also EDIT Images! →
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- LinkedLinked via arxiv author · 85%Jiayi Song →
“EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing”
- LinkedLinked via arxiv author · 85%Shijie Huang →
“EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing”
- LinkedLinked via arxiv author · 85%Fangtai Wu →
“EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing”