|
MGVQ (16x16x8)
|
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Toke…
|
0.49
|
2025-07-14
|
|
|
MGVQ (16x16x4)
|
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Toke…
|
0.64
|
2025-07-14
|
|
|
GigaTok-XL-XXL
|
GigaTok: Scaling Visual Tokenizers to 3 Billion P…
|
0.79
|
2025-04-11
|
|
|
OptVQ (16x16x8)
|
Preventing Local Pitfalls in Vector Quantization …
|
0.91
|
2024-12-19
|
|
|
OptVQ (16x16x4)
|
Preventing Local Pitfalls in Vector Quantization …
|
1.00
|
2024-12-19
|
|
|
IBQ (16x16)
|
Taming Scalable Visual Tokenizer for Autoregressi…
|
1.00
|
2024-12-03
|
|
|
Mo-VQGAN (16x16x4)
|
MoVQ: Modulating Quantized Vectors for High-Fidel…
|
1.12
|
2022-09-19
|
|
|
Open-Magvit2 (16x16)
|
Open-MAGVIT2: An Open-Source Project Toward Democ…
|
1.17
|
2024-09-06
|
|
|
ViT-VQGAN (16x16)
|
Vector-quantized Image Modeling with Improved VQG…
|
1.28
|
2021-10-09
|
|
|
MaskBit (16x16)
|
MaskBit: Embedding-free Image Generation via Bit …
|
1.66
|
2024-09-24
|
|
|
TiTok-S-128
|
An Image is Worth 32 Tokens for Reconstruction an…
|
1.71
|
2024-06-11
|
|
|
RQ-VAE (8x8x16)
|
Autoregressive Image Generation using Residual Qu…
|
1.83
|
2022-03-03
|
|
|
MaskGIT-VQGAN (16x16)
|
MaskGIT: Masked Generative Image Transformer
|
2.28
|
2022-02-08
|
|
|
VQGAN-LC (16x16)
|
Scaling the Codebook Size of VQGAN to 100,000 wit…
|
2.62
|
2024-06-17
|
|
|
Taming-VQGAN (16x16)
|
Taming Transformers for High-Resolution Image Syn…
|
3.64
|
2020-12-17
|
|