Instructions to use lightx2v/Wan2.2-Distill-Models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lightx2v/Wan2.2-Distill-Models 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-Distill-Models", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Diffusion Single File
How to use lightx2v/Wan2.2-Distill-Models with Diffusion Single File:
# 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
|
@@ -26,8 +26,13 @@ library_name: diffusers
|
|
| 26 |
|
| 27 |
[](https://huggingface.co/lightx2v/Wan2.2-Distill-Models)
|
| 28 |
[](https://github.com/ModelTC/LightX2V)
|
|
|
|
| 29 |
[](LICENSE)
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
---
|
| 32 |
|
| 33 |
## π₯ News
|
|
@@ -69,6 +74,7 @@ library_name: diffusers
|
|
| 69 |
|
| 70 |
### π§ Easy Integration
|
| 71 |
- Compatible with LightX2V framework
|
|
|
|
| 72 |
- ComfyUI support
|
| 73 |
- Simple configuration files
|
| 74 |
|
|
@@ -199,8 +205,25 @@ bash scripts/wan22/inference/distill/run_wan22_moe_i2v_distill.sh
|
|
| 199 |
- **Parameter Offloading**: [Offload Documentation](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/method_tutorials/offload.html)
|
| 200 |
|
| 201 |
---
|
|
|
|
| 202 |
|
| 203 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 204 |
|
| 205 |
Please refer to [workflow](https://huggingface.co/lightx2v/Wan2.2-Distill-Models/blob/main/wan2.2_moe_i2v_scale_fp8_comfyui.json)
|
| 206 |
|
|
@@ -224,4 +247,4 @@ Please refer to [workflow](https://huggingface.co/lightx2v/Wan2.2-Distill-Models
|
|
| 224 |
|
| 225 |
If you find this project helpful, please give us a β on [GitHub](https://github.com/ModelTC/LightX2V)
|
| 226 |
|
| 227 |
-
</div>
|
|
|
|
| 26 |
|
| 27 |
[](https://huggingface.co/lightx2v/Wan2.2-Distill-Models)
|
| 28 |
[](https://github.com/ModelTC/LightX2V)
|
| 29 |
+
[](https://x2v.light-ai.top/)
|
| 30 |
[](LICENSE)
|
| 31 |
|
| 32 |
+
> π **Create online with [LightX2V Studio](https://x2v.light-ai.top/)** β
|
| 33 |
+
> an AI avatar and multimodal content production platform built on LightX2V.
|
| 34 |
+
> Use Wan2.2 video generation in your browser, with no local setup required.
|
| 35 |
+
> [See the online usage guide below](#method-2-lightx2v-studio--online-creation).
|
| 36 |
---
|
| 37 |
|
| 38 |
## π₯ News
|
|
|
|
| 74 |
|
| 75 |
### π§ Easy Integration
|
| 76 |
- Compatible with LightX2V framework
|
| 77 |
+
- Online creation with [LightX2V Studio](https://x2v.light-ai.top/)
|
| 78 |
- ComfyUI support
|
| 79 |
- Simple configuration files
|
| 80 |
|
|
|
|
| 205 |
- **Parameter Offloading**: [Offload Documentation](https://lightx2v-zhcn.readthedocs.io/zh-cn/latest/method_tutorials/offload.html)
|
| 206 |
|
| 207 |
---
|
| 208 |
+
### Method 2: LightX2V Studio β Online Video Creation
|
| 209 |
|
| 210 |
+
[**LightX2V Studio**](https://x2v.light-ai.top/) is an online AI avatar
|
| 211 |
+
and multimodal content production platform built on the LightX2V video
|
| 212 |
+
generation inference framework. It focuses on AI avatar video creation
|
| 213 |
+
and also offers text-to-video and image-to-video generation.
|
| 214 |
+
|
| 215 |
+
Create a **silent video** in your browser: sign in, choose **Text-to-Video**
|
| 216 |
+
or **Image-to-Video**, enter a prompt or upload an image, review the
|
| 217 |
+
settings and credit cost, then generate and download the result.
|
| 218 |
+
No local installation or GPU setup is required.
|
| 219 |
+
|
| 220 |
+
**Current Wan2.2 deployment:** 4-step Rank64 LoRAs from
|
| 221 |
+
[Wan2.2 Distill LoRAs](https://huggingface.co/lightx2v/Wan2.2-Distill-Loras):
|
| 222 |
+
`_1217` high/low-noise LoRAs for T2V and `_1022` high/low-noise LoRAs
|
| 223 |
+
for I2V. Both online workflows generate video **without audio**.
|
| 224 |
+
|
| 225 |
+
---
|
| 226 |
+
### Method 3: ComfyUI
|
| 227 |
|
| 228 |
Please refer to [workflow](https://huggingface.co/lightx2v/Wan2.2-Distill-Models/blob/main/wan2.2_moe_i2v_scale_fp8_comfyui.json)
|
| 229 |
|
|
|
|
| 247 |
|
| 248 |
If you find this project helpful, please give us a β on [GitHub](https://github.com/ModelTC/LightX2V)
|
| 249 |
|
| 250 |
+
</div>
|