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
Wan2.1_VAE.safetensors is it not 2-3 times faster than the native vae and kijai
#9
by hydraofm0 - opened
Basically, every image I generate with T2i - WAN 2.2, using the VAE I had, compared to the one in your repo, isn't any faster.
I also tried LightVAE, and the quality worsens significantly, despite having the same speed.
Or perhaps your focus isn't on T2i, but rather on T2V and I2V.