Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# WAN 2.2 Image-to-Video Models
|
| 2 |
+
|
| 3 |
+
High-performance Image-to-Video generation models for ComfyUI.
|
| 4 |
+
|
| 5 |
+
## Models Included
|
| 6 |
+
|
| 7 |
+
| File | Description | Size |
|
| 8 |
+
|------|-------------|------|
|
| 9 |
+
| `Wan2_2-I2V-A14B-HIGH_fp8_e4m3fn_scaled_KJ.safetensors` | HIGH noise I2V model | ~14GB |
|
| 10 |
+
| `Wan2_2-I2V-A14B-LOW_fp8_e4m3fn_scaled_KJ.safetensors` | LOW noise I2V model | ~1.3GB |
|
| 11 |
+
| `umt5_xxl_fp8_e4m3fn_scaled.safetensors` | Text encoder (UMT5-XXL) | ~6GB |
|
| 12 |
+
| `wan_2.1_vae.safetensors` | VAE decoder | ~243MB |
|
| 13 |
+
|
| 14 |
+
## Usage with RunPod
|
| 15 |
+
|
| 16 |
+
Set in RunPod endpoint settings:
|
| 17 |
+
- **Model**: `Aloukik21/wan22-i2v`
|
| 18 |
+
- **HF Token**: Your HuggingFace token
|
| 19 |
+
|
| 20 |
+
## Features
|
| 21 |
+
- I2V Original (20 steps)
|
| 22 |
+
- I2V Lightning (4-8 steps with LoRAs)
|
| 23 |
+
- First-Last Frame interpolation
|
| 24 |
+
- RIFE frame interpolation support
|