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
Model training
#25
by Crized - opened
Hello! Thank you for your work.
I was wandering, what number of "num_train_timesteps" did you actially do while training your model? 1000, as specified in the scheduler (scheduler/scheduler_config.json), or not?
Also, did you use lognorm(0, 1) or uniform distribution of timesteps?
Crized changed discussion title from Sampling question to Model training