All undergraduates! He Kaiming's new work: Text-to-image, 258M parameters are enough
Researchers, including a team led by Kaiming He and composed primarily of undergraduate students, have introduced MiniT2I, a novel text-to-image generation model. This model achieves competitive results with significantly fewer parameters (258M) and lower training costs, comparable to standard ImageNet experiments. MiniT2I utilizes a new MM-JiT architecture that operates directly in pixel space, eliminating the need for VAEs and simplifying the diffusion process by removing mechanisms like AdaLN, which are common in other large-scale text-to-image models. AI
IMPACT Demonstrates a path to more efficient text-to-image generation, potentially lowering barriers for research and development.