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
diffusers how to use Negative Prompt
diffusers how to use Negative Prompt?
I went past your question a few times, wasn't going to say anything, cuz I've always heard that flux does what you tell it to, so it doesn't need a negative prompt. Until I ran a few generations, now I get why you're asking. I only wanted to make the default image of the girl holding a cake into a boy instead, but you cannot generate an image of a boy that isn't wearing a dress with positive prompts alone. Damn female biased shit.. Yea, women need more representation like I need a hole in the head..
Anyways, You may not be able to literally enter negative prompts, but just use the positive prompts with negative adverbs like 'he is not wearing a dress'. That seems to work. Just wish these models weren't so sexist to begin with.