---
license: apache-2.0
base_model:
  - Wan-AI/Wan2.1-T2V-14B
---

# VAE Reconstruction & Color Expansion Evaluation  
### Wan2.1 Base VAE vs HDR VAE

---

## 📊 At-a-Glance Summary

**Color expansion (HDR VAE vs GT):**
- LAB volume: **~+50%**
- Saturation: **~+27%**
- Unique colors: **~+30%**
- Gradient strength: **~+7%**

**Structural cost:**
- SSIM: **~-2%**
- MSE: **~+50%**

### Key takeaway
HDR VAE significantly increases chromatic richness and color diversity,  
but reduces structural fidelity and increases reconstruction error relative to Wan2.1 Base VAE.

---

## 🧪 Evaluation Setup

- Task: Image reconstruction (VAE decoding comparison)
- Models:
  - Wan2.1 Base VAE
  - HDR VAE
  - Ground Truth (GT)
- Mode: Deterministic image-to-image reconstruction
- Metrics:
  - Color statistics (HSV / LAB / RGB)
  - Structural metrics (SSIM, MSE, PSNR)
  - Frequency features (edges, gradients)
  - Entropy + color diversity

---

## 📈 Key Findings

### 🎨 Color behavior
- **Wan2.1 Base VAE:** slight compression of GT color space
- **HDR VAE:** strong expansion of color space (+30% to +50%)

### 🧱 Structure
- **Wan2.1 Base VAE:** closer to GT, smoother output
- **HDR VAE:** sharper, more high-frequency artifacts

### 👁️ Perceptual behavior
- **Wan2.1 Base VAE:** higher fidelity, lower distortion
- **HDR VAE:** more vivid but less faithful reconstruction

---

## 📊 Quantitative Results vs GT

### Wan2.1 Base VAE
- Brightness: -0.71%
- Contrast: -0.23%
- Saturation: -0.11%
- Entropy: -0.08%
- Dynamic range: -0.46%
- Edge density: -15.35%
- Gradient strength: -5.90%
- LAB color volume: -5.00%
- Quantized colors: -6.60%
- Unique colors: +7.90%
- Sharpness: -45.65%

---

### HDR VAE
- Brightness: +0.90%
- Contrast: +0.93%
- Saturation: +26.90%
- Entropy: +0.17%
- Dynamic range: -0.07%
- Edge density: +14.98%
- Gradient strength: +7.10%
- LAB color volume: +48.60%
- Quantized colors: +45.60%
- Unique colors: +29.50%
- Sharpness: +32.15%

---

## 🧮 Reconstruction Quality

### Wan2.1 Base VAE
- SSIM: **0.822**
- PSNR: **25.86**
- MSE: **180.88**

➡️ Best structural fidelity and lowest reconstruction error

---

### HDR VAE
- SSIM: **0.806**
- PSNR: **24.06**
- MSE: **278.08**

➡️ Higher distortion but stronger chromatic expansion

---

## 🧠 Interpretation

**Color axis → Winner: HDR VAE**  
- Largest increase in LAB volume, saturation, and color diversity

**Structure axis → Winner: Wan2.1 Base VAE**  
- Closer SSIM and lower MSE

**Fidelity axis → Winner: Wan2.1 Base VAE**  
- More faithful reconstruction of GT distribution

---

## 🏁 Final Conclusion

HDR VAE acts as a **chromatic expansion decoder**, increasing color space occupancy and high-frequency detail.

Wan2.1 Base VAE remains closer to the **ground-truth manifold**, prioritizing structural and perceptual fidelity over color amplification.