Instructions to use lightx2v/Wan2.2-NVFP4-Sparse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lightx2v/Wan2.2-NVFP4-Sparse with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("lightx2v/Wan2.2-NVFP4-Sparse", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -41,7 +41,7 @@ We strongly recommend using the official LightX2V Docker image for the cleanest
|
|
| 41 |
|
| 42 |
```bash
|
| 43 |
# 1. Pull LightX2V Docker image
|
| 44 |
-
docker pull lightx2v/lightx2v:
|
| 45 |
|
| 46 |
# 2. Run inference
|
| 47 |
bash scripts/wan22/distill/run_wan22_moe_t2v_extreme.sh
|
|
@@ -105,7 +105,7 @@ Script: [run_wan22_moe_t2v_extreme.sh](https://github.com/ModelTC/LightX2V/blob/
|
|
| 105 |
### System Requirements
|
| 106 |
|
| 107 |
- **Required Hardware**: NVIDIA RTX 50-series GPUs or other Blackwell architecture GPUs.
|
| 108 |
-
- **Recommended Runtime**: `lightx2v/lightx2v:
|
| 109 |
|
| 110 |
### Dependencies
|
| 111 |
|
|
|
|
| 41 |
|
| 42 |
```bash
|
| 43 |
# 1. Pull LightX2V Docker image
|
| 44 |
+
docker pull lightx2v/lightx2v:26052801-cu130-5090
|
| 45 |
|
| 46 |
# 2. Run inference
|
| 47 |
bash scripts/wan22/distill/run_wan22_moe_t2v_extreme.sh
|
|
|
|
| 105 |
### System Requirements
|
| 106 |
|
| 107 |
- **Required Hardware**: NVIDIA RTX 50-series GPUs or other Blackwell architecture GPUs.
|
| 108 |
+
- **Recommended Runtime**: `lightx2v/lightx2v:26052801-cu130-5090`.
|
| 109 |
|
| 110 |
### Dependencies
|
| 111 |
|