Instructions to use wangkanai/wan22-fp8-t2v-loras with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use wangkanai/wan22-fp8-t2v-loras with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("wangkanai/wan22-fp8-t2v-loras", 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
Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,22 +1,14 @@
|
|
| 1 |
---
|
| 2 |
license: other
|
| 3 |
-
license_name: wan-license
|
| 4 |
-
license_link: https://huggingface.co/wangfuyun/AnimateLCM-SVD-xt
|
| 5 |
library_name: diffusers
|
| 6 |
pipeline_tag: text-to-video
|
| 7 |
tags:
|
| 8 |
-
- video-generation
|
| 9 |
-
- lora
|
| 10 |
-
- camera-control
|
| 11 |
-
- lighting
|
| 12 |
-
- quality-enhancement
|
| 13 |
- wan
|
| 14 |
-
- image-to-video
|
| 15 |
- text-to-video
|
| 16 |
-
-
|
| 17 |
---
|
| 18 |
|
| 19 |
-
<!-- README Version: v1.
|
| 20 |
|
| 21 |
# WAN LoRA Collection v2.2 - Text-to-Video Edition (FP8)
|
| 22 |
|
|
@@ -290,9 +282,15 @@ If you use these LoRAs in your research or projects, please cite:
|
|
| 290 |
- Enhanced T2V-specific usage guidance and optimization tips
|
| 291 |
- Clarified 14B model compatibility throughout documentation
|
| 292 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 293 |
---
|
| 294 |
|
| 295 |
**Model Version**: v2.2
|
| 296 |
-
**README Version**: v1.
|
| 297 |
-
**Last Updated**: 2025-10-
|
| 298 |
**Repository Size**: 2.6 GB
|
|
|
|
| 1 |
---
|
| 2 |
license: other
|
|
|
|
|
|
|
| 3 |
library_name: diffusers
|
| 4 |
pipeline_tag: text-to-video
|
| 5 |
tags:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
- wan
|
|
|
|
| 7 |
- text-to-video
|
| 8 |
+
- image-generation
|
| 9 |
---
|
| 10 |
|
| 11 |
+
<!-- README Version: v1.4 -->
|
| 12 |
|
| 13 |
# WAN LoRA Collection v2.2 - Text-to-Video Edition (FP8)
|
| 14 |
|
|
|
|
| 282 |
- Enhanced T2V-specific usage guidance and optimization tips
|
| 283 |
- Clarified 14B model compatibility throughout documentation
|
| 284 |
|
| 285 |
+
### Version 1.4 (2025-10-28)
|
| 286 |
+
- Simplified YAML frontmatter to meet HuggingFace requirements
|
| 287 |
+
- Removed non-standard metadata fields (license_name, license_link)
|
| 288 |
+
- Streamlined tags to core identifiers (wan, text-to-video, image-generation)
|
| 289 |
+
- Validated YAML structure for proper HuggingFace compatibility
|
| 290 |
+
|
| 291 |
---
|
| 292 |
|
| 293 |
**Model Version**: v2.2
|
| 294 |
+
**README Version**: v1.4
|
| 295 |
+
**Last Updated**: 2025-10-28
|
| 296 |
**Repository Size**: 2.6 GB
|