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
thank you! no need to reply just happy for folks like you!
#14
by RickyPossum - opened
Training the distillation out of Flux. I wonder if you'd understand that phrase if you went back in time 4 years and told yourself that's what 2024 was about. lol. This is really cool and I'm always curious why they didnt explore this option? Is it just for financial concerns later down the line or is there an article I can read on distillation?