AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios

Tian Ye, Song Fei, Lei Zhu

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SNR-Aware Huber Wavelet loss (ablation)Flux + F16 VAE · 4K ablationHPSv3: 9.22 -> 9.70Improved
add SNR-Aware Huber Wavelet loss (ablation)Flux + F16 VAE · 4K ablationFID: 151.40 -> 148.81Improved
add SACL on top of SNR-HW (ablation)UltraFlux · 4K ablationHPSv3: 9.70 -> 10.30Improved
add SACL on top of SNR-HW (ablation)UltraFlux · 4K ablationArtiMuse: 67.23 -> 67.31No clear effect
add Resonance 2D RoPE with YaRN (ablation)UltraFlux · 4K ablationHPSv3: 10.30 -> 10.91Improved
add Resonance 2D RoPE with YaRN (ablation)UltraFlux · 4K ablationFID: 147.32 -> 146.93Improved
swap Diffusion-4K-v2 data for MultiAspect-4K-1M with plain Flux (ablation)Flux, latent L2 · 4K data-model ablationHPSv3: 8.57 -> 9.17Improved
swap Diffusion-4K-v2 data for MultiAspect-4K-1M with UltraFlux (ablation)UltraFlux · 4K data-model ablationHPSv3: 10.03 -> 10.78Improved
use UltraFlux model instead of Flux latent L2 on MultiAspect-4K-1M (ablation)MultiAspect-4K-1M · 4K data-model ablationFID: 151.41 -> 145.81Improved
post-train VAE (UltraFlux-F16-VAE) vs Flux-VAE-F16Flux F16 VAE · Aesthetic-4K@4096rFID: 2.201 -> 0.547Improved
add VAE post-training vs Flux-VAE-F16-SCFlux-VAE-F16-SC · Aesthetic-4K@4096LPIPS: 0.097 -> 0.102Hurt
add prompt refiner to UltraFlux vs Seedream 4.0UltraFlux · 4K vs Seedream 4.0HPSv3: 12.03 vs 11.98Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy