Instructions to use Anzhc/Z-Image_Anime_VAE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Anzhc/Z-Image_Anime_VAE with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Anzhc/Z-Image_Anime_VAE", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Thanks! Used your VAE as a base for my release
#1
by easygoing0114 - opened
I have released a color-adjusted VAE model based on the FLUX Anime VAE B2.safetensors. Thank you for releasing such a wonderful model!
Anzhc changed discussion status to closed
It seems Anzhc has disapproved it, lol