AuraFlow v0.2

This is a copy of fal/AuraFlow-v0.2 but with the transformer converted to float16 in order to save disk space, allow faster loading, and download if using something without static storage, like Colab.

You may get black images, if so use madebyollin's fp16 fixed SDXL VAE, I don't seem to need it when using MPS but I did have some issues on Colab.

AuraFlow v0.2 is the fully open-sourced largest flow-based text-to-image generation model. The model was trained with more compute compared to the previous version, AuraFlow-v0.1

This model achieves state-of-the-art results on GenEval. Read our blog post for more technical details. 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 important. Join fal's Discord to give us feedback and stay in touch with the model development.

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

Usage

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

from diffusers import AuraFlowPipeline
import torch

pipeline = AuraFlowPipeline.from_pretrained(
    "Vargol/auraflow0.2-fp16-diffusers", 
    torch_dtype=torch.float16,
    variant="fp16",
).to("cuda")

image = pipeline(
    prompt="close-up portrait of a majestic iguana with vibrant blue-green scales, piercing amber eyes, and orange spiky crest. Intricate textures and details visible on scaly skin. Wrapped in dark hood, giving regal appearance. Dramatic lighting against black background. Hyper-realistic, high-resolution image showcasing the reptile's expressive features and coloration.",
    height=1024,
    width=1024,
    num_inference_steps=50, 
    generator=torch.Generator().manual_seed(666),
    guidance_scale=3.5,
).images[0]

image.save("output.png")