Pinned Loading

1. microsoft/LLM2CLIP microsoft/LLM2CLIP Public

   LLM2CLIP significantly improves already state-of-the-art CLIP models.

   Python 646 29

2. microsoft/A-CLIP microsoft/A-CLIP Public

   Official Implementation of Attentive Mask CLIP (ICCV2023, https://arxiv.org/abs/2212.08653)

   Python 36 5

3. microsoft/RAS microsoft/RAS Public

   An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional variability in sampling steps

   Python 152 8

4. microsoft/BizGenEval microsoft/BizGenEval Public

   Bridging the gap between image generation and real-world design: a benchmark for structured, multi-constraint commercial visual content generation.

   Python 14 2

5. microsoft/AVGen-Bench microsoft/AVGen-Bench Public

   AVGen-Bench is a task-driven benchmark for multi-granular evaluation of Text-to-Audio-Video (T2AV) generation.

   Python 3

6. microsoft/MM-WebAgent microsoft/MM-WebAgent Public

   Build coherent and visually polished multimodal webpages with hierarchical planning, AIGC tools, and iterative reflection.

   Python 5