Upload README.md with huggingface_hub

README.md

@@ -3,18 +3,17 @@ library_name: diffusers
 tags:
 - fp8
 - safetensors
-- lora
-- low-rank
+- precision-recovery
 - diffusion
 - converted-by-gradio
 ---
-# FP8 Model with Low-Rank LoRA
+# FP8 Model with Precision Recovery
 - **Source**: `https://huggingface.co/spacepxl/Wan2.1-VAE-upscale2x`
 - **File**: `Wan2.1_VAE_upscale2x_imageonly_real_v1.safetensors`
 - **FP8 Format**: `E5M2`
-- **LoRA Rank**: 128
-- **Architecture**: all
-- **LoRA File**: `Wan2.1_VAE_upscale2x_imageonly_real_v1-lora-r128.safetensors`
+- **Architecture**: vae
+- **Precision Recovery Type**: Correction Factors
+- **Precision Recovery File**: `Wan2.1_VAE_upscale2x_imageonly_real_v1-correction-vae.safetensors`
 - **FP8 File**: `Wan2.1_VAE_upscale2x_imageonly_real_v1-fp8-e5m2.safetensors`
 ## Usage (Inference)
 ```python
@@ -22,17 +21,29 @@ from safetensors.torch import load_file
 import torch
 # Load FP8 model
 fp8_state = load_file("Wan2.1_VAE_upscale2x_imageonly_real_v1-fp8-e5m2.safetensors")
-lora_state = load_file("Wan2.1_VAE_upscale2x_imageonly_real_v1-lora-r128.safetensors")
-# Reconstruct approximate original weights
+# Load precision recovery file
+recovery_state = load_file("Wan2.1_VAE_upscale2x_imageonly_real_v1-correction-vae.safetensors") if "Wan2.1_VAE_upscale2x_imageonly_real_v1-correction-vae.safetensors" else {}
+# Reconstruct high-precision weights
 reconstructed = {}
 for key in fp8_state:
-    if f"lora_A.{key}" in lora_state and f"lora_B.{key}" in lora_state:
-        A = lora_state[f"lora_A.{key}"].to(torch.float32)
-        B = lora_state[f"lora_B.{key}"].to(torch.float32)
-        lora_weight = B @ A  # (out_features, rank) @ (rank, in_features) -> (out_features, in_features)
-        fp8_weight = fp8_state[key].to(torch.float32)
-        reconstructed[key] = fp8_weight + lora_weight
+    fp8_weight = fp8_state[key].to(torch.float32)
+    if recovery_state:
+        # For LoRA approach
+        if "lora_A" in recovery_state:
+            if f"lora_A.{key}" in recovery_state and f"lora_B.{key}" in recovery_state:
+                A = recovery_state[f"lora_A.{key}"].to(torch.float32)
+                B = recovery_state[f"lora_B.{key}"].to(torch.float32)
+                lora_weight = B @ A
+                reconstructed[key] = fp8_weight + lora_weight
+            else:
+                reconstructed[key] = fp8_weight
+        # For correction factor approach
+        elif f"correction.{key}" in recovery_state:
+            correction = recovery_state[f"correction.{key}"].to(torch.float32)
+            reconstructed[key] = fp8_weight + correction
+        else:
+            reconstructed[key] = fp8_weight
     else:
-        reconstructed[key] = fp8_state[key].to(torch.float32)
+        reconstructed[key] = fp8_weight
 ```
 > Requires PyTorch ≥ 2.1 for FP8 support.