Instructions to use ostris/Flex.1-alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ostris/Flex.1-alpha 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/Flex.1-alpha", 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
Turbo Mode?
#7
by radames - opened
Flux LoRAs need to merge or drop 4-15. Blocks 16, 17, 18 become 5, 6, 7
I plan to do a turbo mode eventually. I may wait for the final version. It just depends on time and compute.
Can try this workflow, LORA do appear to be working.
https://openart.ai/workflows/sleepyguy/flex-1-alpha/GtbYAX8cmtujFejhJLTH
KJ custom nodes has a LORA loader that allows for not loading blocks.
