You can deploy this model and start earning money today!

Huage001/
URAE

Name: URAE
Availability: InStock

Views

No views yet

URAE: Your Free FLUX Pro Ultra

arXiv

HuggingFace

Ultra-Resolution Adaptation with Ease
Ruonan Yu*, Songhua Liu*, Zhenxiong Tan, and Xinchao Wang
xML Lab, National University of Singapore

🪶Features

Easy-to-Use High-Quality and High-Resolution Generation😊: Ultra-Resolution Adaptation with Ease, or URAE in short, generates high-resolution images with FLUX, with minimal code modifications.
Easy Training🚀: URAE tames light-weight adapters with a handful of synthetic data from FLUX1.1 Pro Ultra.

🔥News

[2025/03/20] We release models and codes for both training and inference of URAE.

Introduction

Text-to-image diffusion models have achieved remarkable progress in recent years. However, training models for high-resolution image generation remains challenging, particularly when training data and computational resources are limited. In this paper, we explore this practical problem from two key perspectives: data and parameter efficiency, and propose a set of key guidelines for ultra-resolution adaptation termed URAE. For data efficiency, we theoretically and empirically demonstrate that synthetic data generated by some teacher models can significantly promote training convergence. For parameter efficiency, we find that tuning minor components of the weight matrices outperforms widely-used low-rank adapters when synthetic data are unavailable, offering substantial performance gains while maintaining efficiency. Additionally, for models leveraging guidance distillation, such as FLUX, we show that disabling classifier-free guidance, i.e., setting the guidance scale to 1 during adaptation, is crucial for satisfactory performance. Extensive experiments validate that URAE achieves comparable 2K-generation performance to state-of-the-art closed-source models like FLUX1.1 [Pro] Ultra with only 3K samples and 2K iterations, while setting new benchmarks for 4K-resolution generation.

Quick Start

If you have not, install PyTorch, diffusers, transformers, and peft.
Clone this repo to your project directory:

bash
1git clone https://github.com/Huage001/URAE.git 2cd URAE
You only need minimal modifications!

diff
1import torch 2- from diffusers import FluxPipeline 3+ from pipeline_flux import FluxPipeline 4+ from transformer_flux import FluxTransformer2DModel 5 6bfl_repo = "black-forest-labs/FLUX.1-dev" 7+ transformer = FluxTransformer2DModel.from_pretrained(bfl_repo, subfolder="transformer", torch_dtype=torch.bfloat16) 8- pipe = FluxPipeline.from_pretrained(bfl_repo, torch_dtype=torch.bfloat16) 9+ pipe = FluxPipeline.from_pretrained(bfl_repo, transformer=transformer, torch_dtype=torch.bfloat16) 10+ pipe.scheduler.config.use dynamic_shifting = False 11+ pipe.scheduler.config.time shift = 10 12pipe.enable_model_cpu_offload() #save some VRAM by offloading the model to CPU. Remove this if you have enough GPU power 13 14+ pipe.load_lora_weights("Huage001/URAE", weight_name="urae_2k_adapter.safetensors") 15 16prompt = "An astronaut riding a green horse" 17image = pipe( 18 prompt, 19- height=1024, 20- width=1024, 21+ height=2048, 22+ width=2048, 23 guidance_scale=3.5, 24 num_inference_steps=50, 25 max_sequence_length=512, 26 generator=torch.Generator("cpu").manual_seed(0) 27).images[0] 28image.save("flux-urae.png")

⚠️ FLUX requires at least 28GB of GPU memory to operate at a 2K resolution. A 48GB GPU is recommended for the full functionalities of URAE, including both 2K and 4K. We are actively integrating model lightweighting strategies into URAE! If you have a good idea, feel free to submit a PR!
Do not want to run the codes? No worry! Try the model on Huggingface Space!
- URAE w. FLUX1.schnell (Faster)
- URAE w. FLUX1.dev (Higher Quality)

Installation

Clone this repo to your project directory:

Huage001/URAE