FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion Paper • 2412.09626 • Published 4 days ago • 12
NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Training Paper • 2412.02030 • Published 14 days ago • 17
Tulu 3 Datasets Collection All datasets released with Tulu 3 -- state of the art open post-training recipes. • 32 items • Updated 19 days ago • 60
PUMA: Empowering Unified MLLM with Multi-granular Visual Generation Paper • 2410.13861 • Published Oct 17 • 52
Improving Long-Text Alignment for Text-to-Image Diffusion Models Paper • 2410.11817 • Published Oct 15 • 14
ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification and KV Cache Compression Paper • 2410.08584 • Published Oct 11 • 12
Semantic Score Distillation Sampling for Compositional Text-to-3D Generation Paper • 2410.09009 • Published Oct 11 • 13