Instructions to use Wan-AI/Wan2.1-T2V-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Wan-AI/Wan2.1-T2V-14B 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/Wan2.1-T2V-14B", 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
Something I'd love - a cinemagraph model.
#33
by BlueNipples - opened
Just personally, is a video to AI for creating cinemagraph effects. Seamlessly looping elements like rain on/outside windows, candles flickering, fireplaces burning, snowfall, water rippling or bubbling, neon lights flickering, mist or fog rolling, sunlight beaming etc, that gives life to otherwise still images.
I know the silly tavern community would dig this. Photographers might love it too (many love cinemagraph. Seems like it would be considerably easier to get looking good with AI compared to full video too, given that most of the elements remain static (which would also mean that the resolution is preserved largely).