Instructions to use geceff/Wan2.2-Custom-Models-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Wan2.2
How to use geceff/Wan2.2-Custom-Models-GGUF with Wan2.2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -28,9 +28,10 @@ To achieve perfect video motion without artifacts or image degradation (preventi
|
|
| 28 |
| **Sampling Steps** | `4` | When using Wan2.2 Lightning / Distilled V2 |
|
| 29 |
| **CFG Scale** | `1.0` | Crucial for preventing burnt images |
|
| 30 |
| **High Noise Steps** | `2` or `3` | To lock in strong motion and structure before the Lightning layer clears noise |
|
|
|
|
| 31 |
| **Sampler / Scheduler** | `euler` + `simple` | Standard diffusion setup |
|
| 32 |
|
| 33 |
-
*(Note for Higher Quality: If you want to achieve higher visual fidelity and enhance micro-details, it is highly recommended to use `wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors` as your final step. This hybrid approach significantly sharpens fine details and effectively eliminates motion blur during camera movements. This multi-step workflow is recommended for NVIDIA Tesla T4 GPUs or higher, and it can be seamlessly combined with any other GGUF High Noise models available in this repository.)
|
| 34 |
|
| 35 |
## 💾 Available Model Variants
|
| 36 |
|
|
|
|
| 28 |
| **Sampling Steps** | `4` | When using Wan2.2 Lightning / Distilled V2 |
|
| 29 |
| **CFG Scale** | `1.0` | Crucial for preventing burnt images |
|
| 30 |
| **High Noise Steps** | `2` or `3` | To lock in strong motion and structure before the Lightning layer clears noise |
|
| 31 |
+
| **low Noise Steps** | `3` or `4 |
|
| 32 |
| **Sampler / Scheduler** | `euler` + `simple` | Standard diffusion setup |
|
| 33 |
|
| 34 |
+
*(Note for Higher Quality: If you want to achieve higher visual fidelity and enhance micro-details, it is highly recommended to use `wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors` as your final step. This hybrid approach significantly sharpens fine details and effectively eliminates motion blur during camera movements. This multi-step workflow is recommended for NVIDIA Tesla T4 GPUs or higher, and it can be seamlessly combined with any other GGUF High Noise models available in this repository.)
|
| 35 |
|
| 36 |
## 💾 Available Model Variants
|
| 37 |
|