How to use arlaz/modular-flux123-multidiffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("arlaz/modular-flux123-multidiffusion", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
https://huggingface.co/arlaz/modular-flux123-multidiffusion/resolve/main/examples/__init__.py
hf download hf://arlaz/modular-flux123-multidiffusion/examples/__init__.py
curl -L -o __init__.py https://huggingface.co/arlaz/modular-flux123-multidiffusion/resolve/main/examples/__init__.py
