ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation Paper • 2510.11000 • Published Oct 13 • 8
DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing Paper • 2510.02253 • Published Oct 2 • 14
Dynamic Experts Search: Enhancing Reasoning in Mixture-of-Experts LLMs at Test Time Paper • 2509.22572 • Published Sep 26 • 12
Dynamic Experts Search: Enhancing Reasoning in Mixture-of-Experts LLMs at Test Time Paper • 2509.22572 • Published Sep 26 • 12 • 1
Does FLUX Already Know How to Perform Physically Plausible Image Composition? Paper • 2509.21278 • Published Sep 25 • 16
Reconstruction Alignment Improves Unified Multimodal Models Paper • 2509.07295 • Published Sep 8 • 40
RecA Collection Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning! • 8 items • Updated Sep 22 • 13
CreatiPoster: Towards Editable and Controllable Multi-Layer Graphic Design Generation Paper • 2506.10890 • Published Jun 12 • 9
Running on Zero Featured 94 FLUX.1 Dev ControlNet Union Pro 2.0 🔥 94 Generate images using prompts and control images