Instructions to use spacepxl/sd-vae-REPA-E-e2e-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use spacepxl/sd-vae-REPA-E-e2e-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("spacepxl/sd-vae-REPA-E-e2e-diffusers", 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
what model works with this one?
#1
by ryg81 - opened
what model works with this one?
SD1.5, SDXL, Flux?
If you look at where this comes from, you will see that it's based on the VAE used with SD1.5, but it has been finetuned significantly by the REPA-E authors, so it will not work as a drop in replacement for diffusion models that were not trained for it.