DiT-XL/2
New York University (NYU)University of California (UC) BerkeleyImage generationOpen weights
Developed by New York University (NYU),University of California (UC) Berkeley in 2023, DiT-XL/2 is a image generation model with 675000000.0 parameters with openly available weights.
About DiT-XL/2
We explore a new class of diffusion models based on the transformer architecture. We train latent diffusion models of images, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the scalability of
Details
- Provider
- New York University (NYU),University of California (UC) Berkeley
- Task
- Image generation
- Parameters
- 675000000.0
- Released
- 2023-03-02
- Open weights
- Yes