Instructions to use Freepik/flux.1-lite-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Freepik/flux.1-lite-8B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Freepik/flux.1-lite-8B", 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 Settings
- Draw Things
- DiffusionBee
Any plans on doing a "Fill" version of it?
#1
by stduhpf - opened
I believe (but don't take my word for it) that it could be fairly easy to turn it into an inpaint model by just swapping the img_in block with the one from Flux-Fill-Dev. Have you already experimented with that?
Ok I tried on my end it's not that simple. I guess some transformer layers might need some adjustments too.