Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training Paper • 2510.12586 • Published Oct 14, 2025 • 113
In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer Paper • 2504.20690 • Published Apr 29, 2025 • 19
3DIS-FLUX: simple and efficient multi-instance generation with DiT rendering Paper • 2501.05131 • Published Jan 9, 2025 • 37
