Pith. sign in

REVIEW 7 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.02158 v2 pith:4KMDQKB4 submitted 2024-07-02 cs.CV

classification cs.CV
keywords high-resolutionimagestrainingultrapixelcomplexityefficiencygenerationimage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

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 (\textit{e.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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    ElasticDiT introduces an elastic DiT architecture with adjustable spatial compression and block depth plus Shift Sparse Block Attention and a distilled VAE to enable a single model to cover multiple fidelity-latency p...

  2. LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts

    cs.CV 2026-02 conditional novelty 6.0 of 10

    A latent-cascaded video generation framework with dual frequency-split experts reports state-of-the-art 2K/4K video generation on VBench, FIDpatch, and human preference.

  3. SURF: Signature-Retained Fast Video Generation

    cs.GR 2025-11 unverdicted novelty 6.0 of 10

    SURF accelerates high-resolution video generation up to 12.5x by using noise reshifting for low-res previews from pretrained models and a shifting-window Refiner for efficient upscaling that retains original signatures.

  4. CineScale: Free Lunch in High-Resolution Cinematic Visual Generation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    CineScale extends pre-trained diffusion models to 8k image and 4k video generation with mostly tuning-free inference plus a small LoRA adaptation for video.

  5. SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers

    cs.CV 2024-10 unverdicted novelty 6.0 of 10

    Sana-0.6B produces high-resolution images with strong text alignment at 20x smaller size and 100x higher throughput than Flux-12B by combining 32x image compression, linear DiT blocks, and a decoder-only LLM text encoder.

  6. Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions

    cs.CV 2026-06 unverdicted novelty 5.0 of 10

    Ultra Flash introduces a cascaded streaming super-resolution framework with specialized training, upsampling, and optimization to enable real-time high-resolution video generation from low-res diffusion models.

  7. RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification

    cs.CV 2025-03 unverdicted novelty 5.0 of 10

    RectifiedHR is a training-free method that uses noise refresh and latent energy analysis to enable efficient high-resolution synthesis in diffusion models.

Pith tools