Instructions to use Wan-AI/Wan2.2-T2V-A14B-Diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Wan-AI/Wan2.2-T2V-A14B-Diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.2-T2V-A14B-Diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
T2V diffusers version does not work
#11
by felfri - opened
I am using the T2V diffusers implementation of WAN22 14B and I am always generating videos in industrial settings. It seems there is a problem with the text conditioning:
"encoder.embed_tokens.weight | MISSING"
When using the non-diffusers implementation, everything works just fine. Also the I2V diffusers implementation works fine.
did you find a fix for this?
ended up using the non-diffusers version with the help of claude code