Instructions to use arlaz/modular-flux2-multidiffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use arlaz/modular-flux2-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-flux2-multidiffusion", 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
Download examples/prompt.csv from arlaz/modular-flux2-multidiffusion: direct link, hf CLI and curl.
- Browser
- Download file 543 Bytes
-
https://huggingface.co/arlaz/modular-flux2-multidiffusion/resolve/main/examples/prompt.csv
- Command line
-
hf download hf://arlaz/modular-flux2-multidiffusion/examples/prompt.csv
-
curl -L -o prompt.csv https://huggingface.co/arlaz/modular-flux2-multidiffusion/resolve/main/examples/prompt.csv
543 Bytes
| mask,prompt | |
| 00.png,"a luminous renaissance fresco sky with iridescent clouds" | |
| 01.png,"a marble palace facade with caustic golden light" | |
| 02.png,"a lush garden filled with bright wildflowers" | |
| 03.png,"a reflective canal with ornate bridges" | |
| 04.png,"a distant mountain village at sunrise" | |
| 05.png,"a detailed foreground of carved stone figures" | |
| 06.png,"a market square with flowing silk banners" | |
| 07.png,"a forest edge glowing with emerald light" | |
| 08.png,"a quiet chapel interior with stained glass" | |
| 09.png,"a dramatic horizon with warm sunset haze" | |