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 Settings
- Draw Things
- DiffusionBee
Loading components for the flux1-dev checkpoint
#158
by VTaPo - opened
I cannot loading components for the flux1-dev checkpoint.
Here is my code:
pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
# pipe.enable_model_cpu_offload()
pipe.to(torch.float16)
prompt = "Create a commercial poster for restaurant"
out = pipe(
prompt=prompt,
guidance_scale=3.5,
height=768,
width=768,
num_inference_steps=1,
).images[0]
out.save("image.png")
The process always stops when 20% loading.
I have 40GB CPU RAM and 24GB VRAM on RTX3090
You need more RAM. Try with 64GB.