REVIEW 4 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
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.
Forward citations
Cited by 4 Pith papers
-
LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts
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.
-
CineScale: Free Lunch in High-Resolution Cinematic Visual Generation
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.
-
Progressive Growing of Video Tokenizers for Temporally Compact Latent Spaces
Progressive growing of a video tokenizer from 4x to 8x and 16x temporal compression yields higher reconstruction quality and efficient diffusion training than direct training.
-
FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion
A tuning-free scale-fusion method that lets frozen diffusion models generate 8k images and high-res videos by combining global and local attention through frequency filtering.
Discussion (0). Continue with ORCID to comment.