Maskbit
Collection
11 items
•
Updated
This model is the MaskBit generator with a vocabulary size of 16 bits. It is trained on ImageNet for images of resolution 256 and evaluated with 64 sampling steps.
You can find more details on the project page and in the paper.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Dataset used to train markweber/maskbit_generator_16bit
Collection including markweber/maskbit_generator_16bit
Evaluation results
- FID on ILSVRC/imagenet-1kself-reported1.620
- InceptionScore on ILSVRC/imagenet-1kself-reported330.700