DiT-XL/2 + CADS
ETH ZurichDisney ResearchImage generation
Developed by ETH Zurich,Disney Research in 2023, DiT-XL/2 + CADS is a image generation model with 675000000.0 parameters.
About DiT-XL/2 + CADS
While conditional diffusion models are known to have good coverage of the data distribution, they still face limitations in output diversity, particularly when sampled with a high classifier-free guidance scale for optimal image quality or when train
Details
- Provider
- ETH Zurich,Disney Research
- Task
- Image generation
- Parameters
- 675000000.0
- Released
- 2023-10-26
- Open weights
- No