LlamaGen (16x16)

Reported on 4 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical4 results

Image ReconstructiononUltra-High Resolution Image Reconstruction Benchmark
LPIPS· 2024-06-10
0.177
best: 0.092 (MGVQ (16x16x4))
SOTA
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation arXiv:2406.06525
Image ReconstructiononUltra-High Resolution Image Reconstruction Benchmark
SSIM· 2024-06-10
0.72
best: 0.844 (MGVQ (16x16x4))
SOTA
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation arXiv:2406.06525
Image ReconstructiononUltra-High Resolution Image Reconstruction Benchmark
PSNR· 2024-06-10
23.9
best: 28.27 (MGVQ (16x16x4))
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation arXiv:2406.06525
Image ReconstructiononUltra-High Resolution Image Reconstruction Benchmark
rFID· 2024-06-10
5.59
best: 1.07 (SD-VAE (16x16))
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation arXiv:2406.06525