Instructions to use shihaozhao/LaVi-Bridge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use shihaozhao/LaVi-Bridge with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("shihaozhao/LaVi-Bridge", 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
- Local Apps
- Draw Things
- DiffusionBee
Linking paper page & feedback
#2
by merve HF Staff - opened
Hello @shihaozhao congratulations on release!
I am Merve and I work at HF on computer vision. We are indexing papers and linking them to their repositories, so people can discuss about your paper in paper page (which is here https://huggingface.co/papers/2403.07860) and easily find associated model/dataset.
Moreover, it's a HF best practice to host each model checkpoint in different repositories, e.g. shihaozhao/LaVi-Bridge-small, shihaozhao/LaVi-Bridge-large etc. So people don't have to download all the weights when they want to try your model.
Lastly, if you want to build a demo and host on HF Spaces, we'll provide you an A100 grant.
In the meantime, merging this PR is appreciated!