UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios
Paper
•
2511.18050
•
Published
•
38
amineleung
matrixgame
·
AI & ML interests
None yet
Organizations
upvoted
a
paper
2 months ago
upvoted
2
papers
4 months ago
Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
Paper
•
2510.12276
•
Published
•
147
Hyperparameters are all you need: Using five-step inference for an original diffusion model to generate images comparable to the latest distillation model
Paper
•
2510.02390
•
Published
•
3
upvoted
a
paper
11 months ago