Instructions to use ostris/primal_vae with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ostris/primal_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("ostris/primal_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
Commit History
Yesterday
-
Add gradient checkpointing to the vae
Verified signature5dcf26e -
Apache 2.0 license
Verified signature1f441a8
2 days ago
-
Update weights for 2x1 to latest step
Verified signaturef425156 -
patchify takes total compression, unpatchify infers it
Verified signature8a432f7 -
Primal VAE 2x1 and 2x2
Verified signaturebee1996 -
initial commit
Verified signatureb269527