Instructions to use lilquail/Qwanima-vae with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lilquail/Qwanima-vae with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("lilquail/Qwanima-vae", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Please provide additional comparisons
#1
by Shanesan - opened
I came to view this VAE because it sounded interesting.
The one comparison image of what appears to be a koala holding a birdcage appears to be the same picture.
You may have put a lot of work into this VAE, and this example does not do your work justice.
yeah let me create a few more comparisons
lilquail changed discussion status to closed
lilquail changed discussion status to open
oops! there should now be an improved comparison mosaic and full res comparison images