# UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks

arXiv: https://arxiv.org/abs/2407.02158 · HTML: https://mlsanity.com/paper/2407.02158/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 53 references that are in the map.
- First posted on arXiv 2 Jul 2024.

## Builds on (most cited first, 30 of 43)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [LION: Latent Point Diffusion Models for 3D Shape Generation](https://mlsanity.com/paper/2210.06978/) (2022)
- [MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation](https://mlsanity.com/paper/2302.08113/) (2023)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)
- [Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild](https://mlsanity.com/paper/2401.13627/) (2024)

## Built on by (most cited first, 30 of 65)

- [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://mlsanity.com/paper/2410.10629/) (2024)
- [SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration](https://mlsanity.com/paper/2410.02367/) (2024)
- [Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining](https://mlsanity.com/paper/2408.02657/) (2024)
- [SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation](https://mlsanity.com/paper/2503.09641/) (2025)
- [Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation](https://mlsanity.com/paper/2502.20388/) (2025)
- [POSTA: A Go-to Framework for Customized Artistic Poster Generation](https://mlsanity.com/paper/2503.14908/) (2025)
- [FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation](https://mlsanity.com/paper/2502.05179/) (2025)
- [FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion](https://mlsanity.com/paper/2412.09626/) (2024)
- [Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models](https://mlsanity.com/paper/2503.18446/) (2025)
- [I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flow](https://mlsanity.com/paper/2410.07536/) (2024)
- [HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance](https://mlsanity.com/paper/2504.06232/) (2025)
- [Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models](https://mlsanity.com/paper/2504.17789/) (2025)
- [UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset](https://mlsanity.com/paper/2510.20661/) (2025)
- [FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling](https://mlsanity.com/paper/2410.18410/) (2024)
- [LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts](https://mlsanity.com/paper/2602.11564/) (2026)
- [DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion](https://mlsanity.com/paper/2510.20766/) (2025)
- [Diffusion Models Need Visual Priors for Image Generation](https://mlsanity.com/paper/2410.08531/) (2024)
- [Ultra-Resolution Adaptation with Ease](https://mlsanity.com/paper/2503.16322/) (2025)
- [Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis](https://mlsanity.com/paper/2504.14470/) (2025)
- [RobustGS: Unified Boosting of Feedforward 3D Gaussian Splatting under Low-Quality Conditions](https://mlsanity.com/paper/2508.03077/) (2025)
- [UltraImage: Rethinking Resolution Extrapolation in Image Diffusion Transformers](https://mlsanity.com/paper/2512.04504/) (2025)
- [JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation](https://mlsanity.com/paper/2605.04128/) (2026)
- [DreamRelation: Bridging Customization and Relation Generation](https://mlsanity.com/paper/2410.23280/) (2024)
- [PocketSR: The Super-Resolution Expert in Your Pocket Mobiles](https://mlsanity.com/paper/2510.03012/) (2025)
- [HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming](https://mlsanity.com/paper/2512.21338/) (2025)
- [Latent Wavelet Diffusion For Ultra-High-Resolution Image Synthesis](https://mlsanity.com/paper/2506.00433/) (2025)
- [Semantic Context Matters: Improving Conditioning for Autoregressive Models](https://mlsanity.com/paper/2511.14063/) (2025)
- [Fast Image Super-Resolution via Consistency Rectified Flow](https://mlsanity.com/paper/2605.12377/) (2026)
- [Timeline and Boundary Guided Diffusion Network for Video Shadow Detection](https://mlsanity.com/paper/2408.11785/) (2024)
- [ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion](https://mlsanity.com/paper/2510.25818/) (2025)

## Abstract (arXiv)

Ultra-high-resolution image generation poses great challenges, such as increased semantic planning complexity and detail synthesis difficulties, alongside substantial training resource demands. We present UltraPixel, a novel architecture utilizing cascade diffusion models to generate high-quality images at multiple resolutions (textite.g., 1K to 6K) within a single model, while maintaining computational efficiency. UltraPixel leverages semantics-rich representations of lower-resolution images in the later denoising stage to guide the whole generation of highly detailed high-resolution images, significantly reducing complexity. Furthermore, we introduce implicit neural representations for continuous upsampling and scale-aware normalization layers adaptable to various resolutions. Notably, both low- and high-resolution processes are performed in the most compact space, sharing the majority of parameters with less than 3% additional parameters for high-resolution outputs, largely enhancing training and inference efficiency. Our model achieves fast training with reduced data requirements, producing photo-realistic high-resolution images and demonstrating state-of-the-art performance in extensive experiments.