Auraflow V0.3

🚀 AuraFlow v0.3

A fully open-sourced flow-based text-to-image generation model that achieves state-of-the-art results on GenEval.

AuraFlow v0.3 is the fully open-sourced flow-based text-to-image generation model. Compared to its previous version, AuraFlow-v0.2, this model was trained with more computational resources.

It has been fine-tuned on more aesthetic datasets and now supports various aspect ratios, with the width and height up to 1536 pixels.

This model achieves state-of-the-art results on GenEval. For more technical details, read our blog post. You can also check out the comparison with other models on this gallery page.

The model is currently in beta. We are working on improving it, and the community's feedback is crucial. Join fal's Discord to give us feedback and stay updated on the model development.

Credits: A huge thank you to @cloneofsimo and @isidentical for bringing this project to life. It's amazing what two talented engineers can achieve in such a short time. We also thank the incredible researchers whose prior work laid the foundation for our efforts.

🚀 Quick Start

📦 Installation

$ pip install transformers accelerate protobuf sentencepiece
$ pip install git+https://github.com/huggingface/diffusers.git

💻 Usage Examples

Basic Usage

from diffusers import AuraFlowPipeline
import torch

pipeline = AuraFlowPipeline.from_pretrained(
    "fal/AuraFlow-v0.3",
    torch_dtype=torch.float16,
    variant="fp16",
).to("cuda")

image = pipeline(
    prompt="rempage of the iguana character riding F1, fast and furious, cinematic movie poster",
    width=1536,
    height=768,
    num_inference_steps=50, 
    generator=torch.Generator().manual_seed(1),
    guidance_scale=3.5,
).images[0]

image.save("output.png")

📄 License

This project is licensed under the Apache-2.0 license.