Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ye, Tian, Fei, Song, Zhu, Lei
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LucidFlux: Caption-Free Photo-Realistic Image Restoration via a Large-Scale Diffusion Transformer
par: Fei, Song, et autres
Publié: (2025)

NARAIM: Native Aspect Ratio Autoregressive Image Models
par: Fernández, Daniel Gallo, et autres
Publié: (2024)

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
par: Bai, Jinbin, et autres
Publié: (2024)

CoDi: Subject-Consistent and Pose-Diverse Text-to-Image Generation
par: Gao, Zhanxin, et autres
Publié: (2025)

Data Extrapolation for Text-to-image Generation on Small Datasets
par: Ye, Senmao, et autres
Publié: (2024)

PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolution
par: Li, Wenxue, et autres
Publié: (2026)

LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images
par: Xu, Ruyi, et autres
Publié: (2024)

Diverse Text-to-Image Generation via Contrastive Noise Optimization
par: Kim, Byungjun, et autres
Publié: (2025)

UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks
par: Ren, Jingjing, et autres
Publié: (2024)

CTA-Flux: Integrating Chinese Cultural Semantics into High-Quality English Text-to-Image Communities
par: Gong, Yue, et autres
Publié: (2025)

DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models
par: Wang, Zhendong, et autres
Publié: (2025)

Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models
par: Zhang, Jinjin, et autres
Publié: (2025)

DescriptorMedSAM: Language-Image Fusion with Multi-Aspect Text Guidance for Medical Image Segmentation
par: Zhang, Wenjie, et autres
Publié: (2025)

Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment
par: Ba, Ying, et autres
Publié: (2025)

Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image
par: Zhao, Yu, et autres
Publié: (2024)

NativeTok: Native Visual Tokenization for Improved Image Generation
par: Wu, Bin, et autres
Publié: (2026)

On the Fairness, Diversity and Reliability of Text-to-Image Generative Models
par: Vice, Jordan, et autres
Publié: (2024)

Learning to Sample Effective and Diverse Prompts for Text-to-Image Generation
par: Yun, Taeyoung, et autres
Publié: (2025)

D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation
par: Yoo, Nobline, et autres
Publié: (2025)

Preliminary Explorations with GPT-4o(mni) Native Image Generation
par: Cao, Pu, et autres
Publié: (2025)

Generating Multi-Image Synthetic Data for Text-to-Image Customization
par: Kumari, Nupur, et autres
Publié: (2025)

LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Flow-Based Real-World Super-Resolution
par: Fei, Song, et autres
Publié: (2026)

Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis
par: Ren, Jingjing, et autres
Publié: (2025)

Navigating Text-to-Image Generative Bias across Indic Languages
par: Mittal, Surbhi, et autres
Publié: (2024)

Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction Generation
par: Wu, Qingxuan, et autres
Publié: (2025)

Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model
par: Gong, Lixue, et autres
Publié: (2025)

Native-Resolution Image Synthesis
par: Wang, Zidong, et autres
Publié: (2025)

DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation
par: Jiang, Dongzhi, et autres
Publié: (2025)

DynamiCtrl: Rethinking the Basic Structure and the Role of Text for High-quality Human Image Animation
par: Zhao, Haoyu, et autres
Publié: (2025)

MotionFlux: Efficient Text-Guided Motion Generation through Rectified Flow Matching and Preference Alignment
par: Gao, Zhiting, et autres
Publié: (2025)

PKU-AIGIQA-4K: A Perceptual Quality Assessment Database for Both Text-to-Image and Image-to-Image AI-Generated Images
par: Yuan, Jiquan, et autres
Publié: (2024)

ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation
par: Chern, Ethan, et autres
Publié: (2024)

Measuring Diversity in Co-creative Image Generation
par: Ibarrola, Francisco, et autres
Publié: (2024)

TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis
par: Xie, Yu, et autres
Publié: (2025)

QuadGPT: Native Quadrilateral Mesh Generation with Autoregressive Models
par: Liu, Jian, et autres
Publié: (2025)

Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
par: Zhao, Chenxi, et autres
Publié: (2026)

Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters
par: Wang, Weizhi, et autres
Publié: (2024)

PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
par: Chen, Junsong, et autres
Publié: (2024)

Text4Seg: Reimagining Image Segmentation as Text Generation
par: Lan, Mengcheng, et autres
Publié: (2024)

Generalize Polyp Segmentation via Inpainting across Diverse Backgrounds and Pseudo-Mask Refinement
par: Ma, Jiajian, et autres
Publié: (2024)