Ovis-Image Collection Ovis-Image is a 7B text-to-image model specifically optimized for high-quality text rendering under stringent computational constraints. • 7 items • Updated 2 days ago • 5
Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models Paper • 2511.03317 • Published Nov 5 • 6
Ovis2.5 Collection Our next-generation MLLMs for native-resolution vision and advanced reasoning • 5 items • Updated Aug 19 • 56
TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance Paper • 2507.18192 • Published Jul 24 • 7
Ovis-U1 Collection An unified model for multimodal understanding, text-to-image generation, and image editing. • 3 items • Updated Jul 2 • 6
CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation Paper • 2502.12579 • Published Feb 18 • 1
Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities Paper • 2505.02567 • Published May 5 • 80
Ovis2 Collection Our latest advancement in multi-modal large language models (MLLMs) • 15 items • Updated Mar 25 • 65