Downloads · 30 days
6.7K
3% of all-time downloads
DiT-XL-2-256
facebook/DiT-XL-2-256
DiT-XL-2-256 is a machine learning model from facebook. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as cc-by-nc-4.0.
We train latent diffusion models, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the scalability of our Diffusion Transformers (DiTs) through the lens of forw…
All-time downloads
263K
Public
Repo size
6.7 GB
Likes
36
Trending 2
Repo makeup
Click a slice to open those files.
.bin3.3 GB · 100%
At a glance
- Library
- diffusers
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Jan 17, 2023
- Updated
- Jan 17, 2023
- SHA
- eab87f77
Model card
From the Hugging Face model README
Scalable Diffusion Models with Transformers (DiT)
Abstract
We train latent diffusion models, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the scalability of our Diffusion Transformers (DiTs) through the lens of forward pass complexity as measured by Gflops. We find that DiTs with higher Gflops---through increased transformer depth/width or increased number of input tokens---consistently have lower FID. In addition to good scalability properties, our DiT-XL/2 models outperform all prior diffusion models on the class-conditional ImageNet 512×512 and 256×256 benchmarks, achieving a state-of-the-art FID of 2.27 on the latter.
- Library
- diffusers
- License
- cc-by-nc-4.0
- Created
- Jan 17, 2023
- Updated
- Jan 17, 2023