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
Can you upload FP16 unet only version please so we can train with Kohya
#23
by MonsterMMORPG - opened
Can you upload FP16 unet only version please so we can train with Kohya
I think this might be able to convert it https://github.com/kohya-ss/sd-scripts/blob/sd3/tools/convert_diffusers_to_flux.py.
You might have to edit the file to:
# make reverse map from diffusers map
NUM_DOUBLE_BLOCKS = 19
NUM_SINGLE_BLOCKS = 38
diffusers_to_bfl_map = flux_utils.make_diffusers_to_bfl_map(NUM_DOUBLE_BLOCKS,NUM_SINGLE_BLOCKS)