Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering
Hanshen Zhu PRO
CIawevy
·
AI & ML interests
Controllable Generation, Text Rendering, Large Language Model, Agent Modeling
Recent Activity
upvoted a paper 30 days ago
SeFi-Image: A Text-to-Image Foundation Model with Semantic-First Diffusion liked a dataset 4 months ago
cyberagent/crelloOrganizations
models 5
CIawevy/Flux.1-dev-TextPecker-SQPA
Text-to-Image • Updated •
CIawevy/SD3.5M-TextPecker-SQPA
Text-to-Image • Updated
CIawevy/TextPecker-8B-Qwen3VL
Image-Text-to-Text • 9B • Updated • 26 • 1
CIawevy/TextPecker-8B-InternVL3
Image-Text-to-Text • 8B • Updated • 23 • 1
CIawevy/QwenImage-TextPecker-SQPA
Text-to-Image • 21B • Updated • • 1