Sep 2026
DuoDiT: a parameter-efficient dual-stream architecture for image generation in diffusion transformers
DuoDiT is introduced, a parameter-efficient dual-stream architecture that keeps a pre-trained DiT-XL/2 backbone frozen and adds a trainable fine-grained Second Stream, which obtains the lowest KID and LPIPS-Mean while maintaining competitive FID.
Mostafa Shahbazi Dil, M. Mahmoudabadi, M. Rezghi
· Multimedia tools and applica... · 0 citations