---
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)

---

## 📊 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.

---

## 🧪 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

---

## 📈 Key Findings

### 🎨 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

### 🧱 Structure
- Slight reduction in SSIM and PSNR indicates mild structural deviation from GT
- Increased sharpness suggests enhanced edge emphasis and micro-detail amplification

### 👁️ Perceptual behavior
- Outputs appear more vivid and detailed than GT
- Trade-off between realism fidelity and perceptual enhancement

---

## 📊 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%**

---

## 🧮 Reconstruction Quality

### Wan 2.2 Base HDR VAE vs GT

- SSIM: **-1.42%**
- PSNR: **-2.31%**
- MSE: **+13.09%**

➡️ Slight reduction in structural fidelity with moderate increase in reconstruction error

---

## 🧠 Interpretation

**Color axis → Strong winner: Wan 2.2 Base HDR VAE**  
- Large gains in LAB volume, saturation, and color diversity

**Structure axis → Slight trade-off**  
- Small degradation in SSIM/PSNR balanced by increased sharpness

**Perceptual axis → Winner: Wan 2.2 Base HDR VAE**  
- More visually rich and detailed outputs compared to GT

---

## 🏁 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.