Create README.md

README.md

@@ -0,0 +1,26 @@
+# diff_lora-r8_anisora_wan2.1_i2v_480p14B_fp8e4m3fn
+
+This is a **LoRA (Low-Rank Adaptation) model** representing the *raw parameter difference* between the following two video generation models:
+
+- **Finetuned model (Anisora):**  
+  [`Wan2_1-Anisora-I2V-480P-14B_fp8_e4m3fn.safetensors`](https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1-Anisora-I2V-480P-14B_fp8_e4m3fn.safetensors)
+
+- **Base pretrained model:**  
+  [`wan2.1_i2v_480p_14B_fp8_e4m3fn.safetensors`](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/diffusion_models/wan2.1_i2v_480p_14B_fp8_e4m3fn.safetensors)
+
+## ❗ Disclaimer
+
+- This LoRA was generated by taking the direct parameter **difference** between the two `.safetensors` files.
+- No additional training, fine-tuning, or quality filtering has been applied.
+- While it **can** be used for `text2video` and related pipelines (e.g. with ComfyUI), its behavior and correctness are **not guaranteed**.
+- Treat this as a **technical test** or experimental reference only.
+
+## 📦 Details
+
+| Field             | Value                                      |
+|------------------|--------------------------------------------|
+| LoRA Rank         | 8                                          |
+| Base Model        | Wan2.1 I2V 480p 14B fp8 e4m3fn             |
+| Finetuned Target  | Wan2.1-Anisora-I2V                         |
+| Precision         | fp8 (e4m3fn)                               |
+| Format            | `.safetensors`                             |