Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding Paper • 2405.08748 • Published May 14 • 17 • 2
Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling Paper • 2401.15977 • Published Jan 29 • 35 • 8
PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models Paper • 2401.05252 • Published Jan 10 • 43 • 4