Instructions to use lightx2v/Autoencoders with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lightx2v/Autoencoders 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/Autoencoders", 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/Autoencoders 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
Is a decoder coming to WAN 2.2 14B?
#10
by deleted - opened
I tried it on my workflow, using the lightvae2.1 and lighttae2.1 on my workflow instead of the regular decoder, it works, but output video is ugly. It decoded a 480x848 81frames in just 0.72s seconds compared to regular decoder 3.8s.
I know you only done 2.1 and 2.2 TI2V 5B.
Just wondering if this is coming to WAN 2.2 14B version?