Instructions to use Felldude/Wan2.2-Diffusers-HDR-VAE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Felldude/Wan2.2-Diffusers-HDR-VAE with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Felldude/Wan2.2-Diffusers-HDR-VAE", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
| license: apache-2.0 | |
| base_model: | |
| - Wan-AI/Wan2.2-Animate-14B | |
| - nvidia/Cosmos3-Super | |
| - nvidia/Cosmos3-Nano | |
| # VAE Reconstruction & Color Expansion Evaluation | |
| ### Wan 2.2 Base HDR VAE vs Ground Truth (GT) | |
| --- | |
| ## ๐ At-a-Glance Summary | |
| **Color expansion (Wan 2.2 Base HDR VAE vs GT):** | |
| - LAB volume: **~+34.09%** | |
| - Saturation: **~+22.27%** | |
| - Unique colors: **~+23.68%** | |
| - Quantized colors: **~+30.32%** | |
| - Sharpness: **~+4.25%** | |
| **Structural cost:** | |
| - SSIM: **~-1.42%** | |
| - PSNR: **~-2.31%** | |
| - MSE: **~+13.09%** | |
| ### Key takeaway | |
| Wan 2.2 Base HDR VAE significantly increases perceptual color richness and detail density, | |
| while introducing a mild reduction in structural fidelity and a moderate increase in reconstruction error relative to ground truth. | |
| --- | |
| ## ๐งช Evaluation Setup | |
| - Task: Image reconstruction (VAE decode comparison) | |
| - Model: | |
| - Wan 2.2 Base HDR VAE | |
| - Reference: | |
| - Ground Truth (GT) | |
| - Mode: Deterministic image reconstruction evaluation | |
| - Metrics: | |
| - Color statistics (HSV / LAB / RGB) | |
| - Structural similarity (SSIM) | |
| - Pixel fidelity (PSNR, MSE) | |
| - Texture features (edges, gradients, sharpness) | |
| - Entropy and color diversity measures | |
| --- | |
| ## ๐ Key Findings | |
| ### ๐จ Color behavior | |
| - Wan 2.2 Base HDR VAE significantly expands GT color space | |
| - Strong increases in saturation and LAB distribution volume | |
| - Noticeably richer and more expressive chromatic output | |
| ### ๐งฑ Structure | |
| - Slight reduction in SSIM and PSNR indicates mild structural deviation from GT | |
| - Increased sharpness suggests enhanced edge emphasis and micro-detail amplification | |
| ### ๐๏ธ Perceptual behavior | |
| - Outputs appear more vivid and detailed than GT | |
| - Trade-off between realism fidelity and perceptual enhancement | |
| --- | |
| ## ๐ Quantitative Results vs GT | |
| ### Wan 2.2 Base HDR VAE | |
| - Brightness: **+0.79%** | |
| - Contrast: **+0.73%** | |
| - Saturation: **+22.27%** | |
| - Entropy: **+0.13%** | |
| - Dynamic range: **-0.13%** | |
| - Edge density: **-1.41%** | |
| - Gradient strength: **-0.68%** | |
| - LAB color volume: **+34.09%** | |
| - Quantized colors: **+30.32%** | |
| - Unique colors: **+23.68%** | |
| - Sharpness: **+4.25%** | |
| --- | |
| ## ๐งฎ Reconstruction Quality | |
| ### Wan 2.2 Base HDR VAE vs GT | |
| - SSIM: **-1.42%** | |
| - PSNR: **-2.31%** | |
| - MSE: **+13.09%** | |
| โก๏ธ Slight reduction in structural fidelity with moderate increase in reconstruction error | |
| --- | |
| ## ๐ง Interpretation | |
| **Color axis โ Strong winner: Wan 2.2 Base HDR VAE** | |
| - Large gains in LAB volume, saturation, and color diversity | |
| **Structure axis โ Slight trade-off** | |
| - Small degradation in SSIM/PSNR balanced by increased sharpness | |
| **Perceptual axis โ Winner: Wan 2.2 Base HDR VAE** | |
| - More visually rich and detailed outputs compared to GT | |
| --- | |
| ## ๐ Final Conclusion | |
| Wan 2.2 Base HDR VAE acts as a **perceptual and chromatic enhancement VAE**, expanding color richness and visible detail density beyond ground truth. | |
| It trades a small amount of structural fidelity for significantly improved perceptual richness, making it more suitable for downstream generative pipelines where visual expressiveness is prioritized over strict reconstruction accuracy. |