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]
Is there a way to use this vae on ComfyUI?
Not currently. Though, until something it trained with it, it doesn't really do much on its own currently.
· Sign up or log in to comment
