Downloads · 30 days
279
0% of all-time downloads
vqgan_imagenet_f16_16384
dalle-mini/vqgan_imagenet_f16_16384
vqgan_imagenet_f16_16384 is a machine learning model from dalle-mini. 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 transformers.
This is a Flax/JAX implementation of VQGAN, which learns a codebook of context-rich visual parts by leveraging both the use of convolutional methods and transformers. It was introduced in Taming Transformers for High-…
All-time downloads
860K
Public
Repo size
795 MB
Likes
43
Public
Repo makeup
Click a slice to open those files.
.msgpack304 MB · 100%
At a glance
- Library
- transformers
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Mar 1, 2022
- SHA
- 9f990ec0
Model card
From the Hugging Face model README
VQGAN-f16-16384
Model Description
This is a Flax/JAX implementation of VQGAN, which learns a codebook of context-rich visual parts by leveraging both the use of convolutional methods and transformers. It was introduced in Taming Transformers for High-Resolution Image Synthesis (CVPR paper).
The model allows the encoding of images as a fixed-length sequence of tokens taken from the codebook.
This version of the model uses a reduction factor f=16 and a vocabulary of 16,384 tokens.
As an example of how the reduction factor works, images of size 256x256 are encoded to sequences of 256 tokens: 256/16 * 256/16. Images of 512x512 would result in sequences of 1024 tokens.
This model was ported to JAX using a checkpoint trained on ImageNet.
How to Use
The checkpoint can be loaded using Suraj Patil's implementation of VQModel.
Other
This model can be used as part of the implementation of DALL·E mini. Our report contains more details on how to leverage it in an image encoding / generation pipeline.
- Library
- transformers
- Created
- Mar 2, 2022
- Updated
- Mar 1, 2022