Instructions to use fal/AuraFlow-v0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use fal/AuraFlow-v0.3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fal/AuraFlow-v0.3", 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
FP8, NF4 ?
#2
by froilo - opened
how to convert?
i did a couple of them lol https://huggingface.co/marduk191/Auraflow0.3_collection/tree/main
thank u , ser!
Question: can this use the same T5XXL encoder flux and SD3 use and thus a unet model without the text encoder be downloaded, in order to save disk space?