Qrange-group/SUR-adapter
ACM MM'23 (oral), SUR-adapter for pre-trained diffusion models can acquire the powerful semantic understanding and reasoning capabilities from large language models to build a high-quality textual semantic representation for text-to-image generation.
PythonMIT
Stargazers
- amadeuzou
- atfortesTsinghua University @thu-ml
- BoyuanJiang
- brynne8
- carvychen
- chaoso
- dedekindsTsinghua University
- Donghao-LiXidian University
- fly51flyPRIS
- forrestbingAlibaba Inc
- gaomingqiUniversity of Warwick | SUSTech
- houxuedong
- hujunchao
- HUuxiaobinTechnische Universität München (TUM)
- JeffCarpenterCanada
- ju-chen
- KevinYc5UESTC
- KyleYueyeUniversity of Chinese Academy of Science
- lleuad-Codi
- marcussacanaVNX+
- marson666Beijing
- metaclue
- ninjasaid2k
- QinJinghui
- Question406UCSB
- RazoRTR
- SandalotsVolcanak
- TonyLianLongUC Berkeley
- ultranity
- windlu-1
- winterfell00Peking University
- WujieByte
- xuanhan863Los Angeles, USA
- YunzhongTianjingALIBABA
- zhongshsh
- zyhrainbowSHANGHAI