Instructions to use Phr00t/WAN2.2-14B-Rapid-AllInOne with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Wan2.2
How to use Phr00t/WAN2.2-14B-Rapid-AllInOne 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
base_model:
- Wan-AI/Wan2.2-I2V-A14B
- Wan-AI/Wan2.2-T2V-A14B
tags:
- wan
- wan2.2
- accelerator
This is an "all in one" merge of the WAN 2.2 models into 1. Models also include umt5xxl CLIP and WAN 2.1 VAE. FP8 precision.
Basically, I mixed in "high" + "low" WAN 2.2, WAN 2.1 models, and finally added Lightx2v and PUSA loras for speed.
I'm going for a "jack of all trades" solution here: speed, WAN 2.2 features, WAN 2.1 lora compatibility and simplicity.
You only need to use the "Load Checkpoint" ComfyUI node and can pull the CLIP and VAE alongside the Model.
4 steps, 1 cfg, sa_solver sampler and beta scheduler highly recommended. If you don't like the higher contrast look, you can try euler_a or other samplers. YMMV.
Initial testing shows this is pretty neat and is compatible with WAN 2.1 loras. Give it a try!



