metadata
license: apache-2.0
datasets:
- ILSVRC/imagenet-1k
model-index:
- name: MaskGIT-Tokenizer-10bits
results:
- task:
type: image-generation
dataset:
name: ILSVRC/imagenet-1k
type: ILSVRC/imagenet-1k
metrics:
- name: rFID
type: rFID
value: 1.96
- name: InceptionScore
type: InceptionScore
value: 178.3
- name: LPIPS
type: LPIPS
value: 0.331
- name: PSNR
type: PSNR
value: 18.6
- name: SSIM
type: SSIM
value: 0.47
- name: CodebookUsage
type: CodebookUsage
value: 1
This model is the MaskGIT tokenizer with a vocabulary size of 10bits adopted for the usage in the MaskBit codebase. It uses a downsampling factor of 16 and is trained on ImageNet for images of resolution 256.
You can find more details in the original repository and in the paper. All credits for this model belong to Huiwen Chang, Han Zhang, Lu Jiang, Ce Liu, and William T. Freeman.