test
| Model | SD_1.5_vae | SDXL_0.9_vae | Flux.1_vae | Wan2.1_vae | Qwen-Image_vae | Wan2.2_vae | Flux.2_vae | Qwen-Image-VAE-2.0 (f16c64) |
|---|---|---|---|---|---|---|---|---|
| Original Resolution | 512 x 512 x 3 | 1024 x 1024 x 3 | 1024 x 1024 x 3 | 1024 x 1024 x 3 | 1024 x 1024 x 3 | 1024 x 1024 x 3 | 1024 x 1024 x 3 | 1024 x 1024 x 3 |
| Latent Resolution | 64 x 64 x 4 | 128 x 128 x 4 | 128 x 128 x 16 | 128 x 128 x 16 | 128 x 128 x 16 | 64 x 64 x 48 | 128 x 128 x 32 | 64 x 64 x 64 |
| Spatial Compression Ratio | 1/48 | 1/48 | 1/12 | 1/12 | 1/12 | 1/16 | 1/6 | 1/16 |
| Temporal Compression Ratio | - | - | - | 1/4 | - | 1/4 | - | - |
| Representative Models | SD1.5 | SDXL | Flux.1 HiDream-I1 Z-Image |
Wan2.1 Wan2.2 (14B) Cosmos-Predict-2 |
Qwen-Image Anima Krea-2 |
Wan2.2 (5B) | Flux.2 ERNIE-Image |
Qwen-Image-2.0 |
| Image1 | SD1.5_vae | SDXL_0.9_vae | Flux.1_vae | wan_2.1_vae | qwen_image_vae | wan_2.2_vae | Flux.2_vae |
|---|---|---|---|---|---|---|---|
| MAE_Similarity | 98.8 % | 99.0 % | 99.4 % | 99.5 % | 99.6 % | 99.7 % | 99.2 % |
| SSIM_similarity | 99.5 % | 99.6 % | 99.9 % | 100.0 % | 100.0 % | 100.0 % | 99.9 % |
| Red | 0.0 % | 0.3 % | 0.0 % | 0.3 % | 0.2 % | 0.1 % | 0.5 % |
| Green | -0.7 % | 0.5 % | 0.1 % | 0.2 % | 0.2 % | 0.1 % | -0.4 % |
| Blue | -0.2 % | 0.0 % | -0.2 % | 0.2 % | 0.2 % | 0.1 % | 0.3 % |
| Image2 | SD1.5_vae | SDXL_0.9_vae | Flux.1_vae | wan_2.1_vae | qwen_image_vae | wan_2.2_vae | Flux.2_vae |
|---|---|---|---|---|---|---|---|
| MAE_Similarity | 97.8 % | 98.3 % | 99.0 % | 99.2 % | 99.4 % | 99.5 % | 98.8 % |
| SSIM_similarity | 98.8 % | 99.1 % | 99.8 % | 99.9 % | 99.9 % | 100.0 % | 99.8 % |
| Red | -0.5 % | 0.2 % | 0.0 % | 0.2 % | 0.3 % | 0.1 % | 0.4 % |
| Green | -0.9 % | 0.2 % | 0.1 % | 0.1 % | 0.2 % | 0.1 % | -0.3 % |
| Blue | 0.0 % | 0.0 % | 0.0 % | 0.2 % | 0.3 % | 0.2 % | 0.7 % |
| Image3 | SD1.5_vae | SDXL_0.9_vae | Flux.1_vae | wan_2.1_vae | qwen_image_vae | wan_2.2_vae | Flux.2_vae |
|---|---|---|---|---|---|---|---|
| MAE_Similarity | 97.1 % | 97.8 % | 98.8 % | 98.9 % | 99.2 % | 99.1 % | 98.9 % |
| SSIM_similarity | 98.0 % | 98.6 % | 99.7 % | 99.8 % | 99.9 % | 99.8 % | 99.8 % |
| Red | -0.4 % | 0.0 % | -0.2 % | 0.2 % | 0.4 % | 0.3 % | 0.4 % |
| Green | -0.8 % | 0.1 % | 0.0 % | 0.1 % | 0.3 % | 0.2 % | -0.1 % |
| Blue | -0.4 % | 0.1 % | 0.0 % | 0.3 % | 0.4 % | 0.2 % | 0.1 % |
| Image4 | SD1.5_vae | SDXL_0.9_vae | Flux.1_vae | wan_2.1_vae | qwen_image_vae | wan_2.2_vae | Flux.2_vae |
|---|---|---|---|---|---|---|---|
| MAE_Similarity | 98.0 % | 98.3 % | 99.0 % | 99.2 % | 99.3 % | 99.0 % | 99.0 % |
| SSIM_similarity | 98.3 % | 98.8 % | 99.8 % | 99.8 % | 99.8 % | 99.8 % | 99.8 % |
| Red | 0.0 % | 0.2 % | 0.1 % | 0.1 % | 0.3 % | 0.1 % | 0.3 % |
| Green | -0.8 % | 0.3 % | 0.2 % | 0.0 % | 0.2 % | 0.0 % | 0.0 % |
| Blue | -0.3 % | 0.3 % | 0.2 % | 0.2 % | 0.3 % | 0.1 % | 0.2 % |
| Image5 | SD1.5_vae | SDXL_0.9_vae | Flux.1_vae | wan_2.1_vae | qwen_image_vae | wan_2.2_vae | Flux.2_vae |
|---|---|---|---|---|---|---|---|
| MAE_Similarity | 97.9 % | 98.3 % | 98.7 % | 99.0 % | 99.2 % | 99.2 % | 98.8 % |
| SSIM_similarity | 99.1 % | 99.3 % | 99.7 % | 99.8 % | 99.8 % | 99.8 % | 99.8 % |
| Red | 0.1 % | -0.1 % | 0.0 % | 0.2 % | 0.4 % | 0.2 % | 0.6 % |
| Green | -1.1 % | 0.4 % | 0.3 % | 0.1 % | 0.3 % | 0.1 % | -0.3 % |
| Blue | -0.2 % | -0.1 % | -0.1 % | 0.2 % | 0.3 % | 0.2 % | 0.4 % |
| Average | SD1.5_vae | SDXL_0.9_vae | Flux.1_vae | wan_2.1_vae | qwen_image_vae | wan_2.2_vae | Flux.2_vae |
|---|---|---|---|---|---|---|---|
| MAE_Similarity | 97.9 % | 98.3 % | 99.0 % | 99.2 % | 99.3 % | 99.3 % | 98.9 % |
| SSIM_similarity | 98.7 % | 99.1 % | 99.8 % | 99.9 % | 99.9 % | 99.9 % | 99.8 % |
| Red | -0.2 % | 0.1 % | 0.0 % | 0.2 % | 0.3 % | 0.2 % | 0.4 % |
| Green | -0.9 % | 0.3 % | 0.1 % | 0.1 % | 0.3 % | 0.1 % | -0.2 % |
| Blue | -0.2 % | 0.1 % | 0.0 % | 0.2 % | 0.3 % | 0.1 % | 0.3 % |