Instructions to use black-forest-labs/FLUX.1-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use black-forest-labs/FLUX.1-dev with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Prompting tips?
#38
by the-french-artist - opened
I find it harder to specify a painting style, either by naming the style, or the artist.
What am I doing wrong?
Eg. pointillist oil on canvas of a flower field landscape with a small river by Claude Monet.
This will return good results on Stable Diffusion and mediocre ones in FLUX.
I don't think they incorporated artists yet. Just like you will have a hard time finding recognizable celebrities. EU law is not to joke with.
I understand the artist issue. But the style, or genre, is still very lightly followed, even at high guidance.
If I remember correctly the model understands caps, so maybe CLAUDE MONET? Worth a shot, nothing to lose.