DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation
Paper
•
2503.10618
•
Published
•
17
wenze
wenzehu
AI & ML interests
None yet
Recent Activity
authored
a paper
20 days ago
DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture
Design in Text to Image Generation
upvoted
a
paper
4 months ago
STIV: Scalable Text and Image Conditioned Video Generation
Organizations
None yet