Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models

2025-03-24

AI Summary

Current text-to-image diffusion models struggle to directly generate high-quality 4K images due to the absence of publicly available 4K synthetic datasets and standardized evaluation protocols. To address this, we propose an end-to-end 4K image generation framework. Our key contributions are: (1) the first open-source 4K aesthetic benchmark, Aesthetic-4K; (2) a wavelet-domain fine-tuning method enabling efficient latent-space optimization for high-fidelity 4K detail preservation; and (3) a fine-grained evaluation metric—GLCM Score—integrated with FID, CLIPScore, and compression ratio for comprehensive multidimensional assessment. Leveraging SD3-2B and Flux-12B backbones with GPT-4o–assisted automatic annotation, our approach achieves significant improvements in perceptual detail fidelity and text–image alignment on Aesthetic-4K, outperforming all existing state-of-the-art methods across quantitative and qualitative metrics.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In this paper, we present Diffusion-4K, a novel framework for direct ultra-high-resolution image synthesis using text-to-image diffusion models. The core advancements include: (1) Aesthetic-4K Benchmark: addressing the absence of a publicly available 4K image synthesis dataset, we construct Aesthetic-4K, a comprehensive benchmark for ultra-high-resolution image generation. We curated a high-quality 4K dataset with carefully selected images and captions generated by GPT-4o. Additionally, we introduce GLCM Score and Compression Ratio metrics to evaluate fine details, combined with holistic measures such as FID, Aesthetics and CLIPScore for a comprehensive assessment of ultra-high-resolution images. (2) Wavelet-based Fine-tuning: we propose a wavelet-based fine-tuning approach for direct training with photorealistic 4K images, applicable to various latent diffusion models, demonstrating its effectiveness in synthesizing highly detailed 4K images. Consequently, Diffusion-4K achieves impressive performance in high-quality image synthesis and text prompt adherence, especially when powered by modern large-scale diffusion models (e.g., SD3-2B and Flux-12B). Extensive experimental results from our benchmark demonstrate the superiority of Diffusion-4K in ultra-high-resolution image synthesis.

Problem

• Lack of public 4K image synthesis dataset
• Need for evaluating ultra-high-resolution image details
• Direct training method for 4K image synthesis

Innovation

• Constructed Aesthetic-4K benchmark for 4K synthesis
• Proposed wavelet-based fine-tuning for 4K images
• Achieved high-quality ultra-high-resolution image synthesis