Auraflow V0.3

🚀 AuraFlow v0.3

AuraFlow v0.3 is a fully open - sourced flow - based text - to - image generation model. It offers enhanced performance compared to its predecessor, trained with more compute and fine - tuned on aesthetic datasets, supporting various aspect ratios.

🚀 Quick Start

AuraFlow v0.3 is a powerful text - to - image generation model. It has been trained with more computational resources than its previous version, [AuraFlow - v0.2](https://huggingface.co/fal/AuraFlow - v0.2), and fine - tuned on more aesthetic datasets. It now supports various aspect ratios, with width and height up to 1536 pixels.


📦 Installation

Before using AuraFlow v0.3, you need to install the necessary dependencies. Run the following commands in your terminal:

$ 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(
    "terminusresearch/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.