DanceGRPO: Unleashing GRPO on Visual Generation
Paper
• 2505.07818 • Published
• 32
CHINA
-
-
Wan-AI/Wan2.1-VACE-14B
Image-to-Video • Updated • 4.9k • 490 -
Qwen/Qwen2.5-Omni-7B-GPTQ-Int4
Any-to-Any • 11B • Updated • 23.8k • 13 -
hustvl/PixelHacker
Updated • 8 -
ByteDance-Seed/BAGEL-7B-MoT
Any-to-Any • 15B • Updated • 3.48k • 1.18k -
deepseek-ai/DeepSeek-R1-0528
Text Generation • 685B • Updated • 1.11M • • 2.41k -
ByteDance-Seed/BM-Model
Image-to-Image • Updated • 3 -
selftok-team/SelftokTokenizer
Updated • 2 -
ByteDance/XVerse
Text-to-Image • Updated • 73 • 89 -
AIDC-AI/Ovis-U1-3B
Any-to-Any • Updated • 1.23k • 215 -
X-Omni/X-Omni-Zh
Updated • 47 • 7 -
Qwen/Qwen-Image
Text-to-Image • Updated • 202k • • 2.42k -
Skywork/Skywork-UniPic-1.5B
Any-to-Any • Updated • 57 • 114 -
nunchaku-ai/nunchaku-qwen-image
Text-to-Image • Updated • 11.9k • 256 -
meituan-longcat/LongCat-Image
Text-to-Image • Updated • 39.8k • • 235
