Instructions to use ostris/OpenFLUX.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ostris/OpenFLUX.1 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/OpenFLUX.1", 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
suggested diffusers inference example
#10
by linoyts - opened
Awesome work thanks for sharing it!
we added a community pipeline to diffusers that supports CFG to easily inference flux with CFG like this:
- download pipeline script (or alternatively change to your pipeline implementation :))
!wget https://raw.githubusercontent.com/huggingface/diffusers/main/examples/community/pipeline_flux_with_cfg.py
- load & prompt
import torch
import diffusers
from pipeline_flux_with_cfg import FluxCFGPipeline
pipe = FluxCFGPipeline.from_pretrained("ostris/OpenFLUX.1", torch_dtype=torch.bfloat16)
pipe(prompt="a tiny astronaut hatching from an egg").images[0]