DanceGRPO: Unleashing GRPO on Visual Generation
Paper
•
2505.07818
•
Published
•
32
CHINA
-
-
Wan-AI/Wan2.1-VACE-14B
Image-to-Video • Updated • 9.6k • 472 -
Qwen/Qwen2.5-Omni-7B-GPTQ-Int4
Any-to-Any • 5B • Updated • 399 • 10 -
hustvl/PixelHacker
Updated • 7 -
ByteDance-Seed/BAGEL-7B-MoT
Any-to-Any • 15B • Updated • 705 • 1.14k -
deepseek-ai/DeepSeek-R1-0528
Text Generation • 685B • Updated • 700k • • 2.37k -
ByteDance-Seed/BM-Model
Image-to-Image • Updated • 3 -
selftok-team/SelftokTokenizer
Updated • 2 -
ByteDance/XVerse
Text-to-Image • Updated • 121 • 90 -
AIDC-AI/Ovis-U1-3B
Any-to-Any • 4B • Updated • 778 • 199 -
X-Omni/X-Omni-Zh
10B • Updated • 225 • 7 -
Qwen/Qwen-Image
Text-to-Image • Updated • 114k • • 2.08k -
Skywork/Skywork-UniPic-1.5B
Any-to-Any • Updated • 63 • 112 -
nunchaku-tech/nunchaku-qwen-image
Text-to-Image • Updated • 69.2k • 197
