Instructions to use xiaozaa/flux1-fill-dev-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use xiaozaa/flux1-fill-dev-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("xiaozaa/flux1-fill-dev-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
Differences Between This Flux-Fill Version and the Original?
#1
by davayton - opened
Hi there,
Thank you for your contributions to the open-source community.
I was wondering what the difference is between this version of Flux-Fill and the one released by the authors. I noticed that the input dimension is different, but what other changes have been made? Was this model trained on any specific data?
Thank you for your help.