Cover Image

Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scaling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Chao, Wei, Tianyi, Yu, Nenghai
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation
by: Zhang, Yabo, et al.
Published: (2026)

TIIF-Bench: How Does Your T2I Model Follow Your Instructions?
by: Wei, Xinyu, et al.
Published: (2025)

Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping
by: Zhou, Chao, et al.
Published: (2026)

Show Me: Unifying Instructional Image and Video Generation with Diffusion Models
by: Pu, Yujiang, et al.
Published: (2025)

Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following
by: Feng, Yutong, et al.
Published: (2023)

In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer
by: Zhang, Zechuan, et al.
Published: (2025)

Forge-and-Quench: Enhancing Image Generation for Higher Fidelity in Unified Multimodal Models
by: Zeng, Yanbing, et al.
Published: (2026)

UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
by: Zhao, Haozhe, et al.
Published: (2024)

Follow-Your-Instruction: A Comprehensive MLLM Agent for World Data Synthesis
by: Feng, Kunyu, et al.
Published: (2025)

Enhanced Multi-Scale Cross-Attention for Person Image Generation
by: Tang, Hao, et al.
Published: (2025)

Instruction-Free Tuning of Large Vision Language Models for Medical Instruction Following
by: Kang, Myeongkyun, et al.
Published: (2026)

Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs
by: Chen, Zhi-Kai, et al.
Published: (2026)

AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation
by: Liu, Yexin, et al.
Published: (2025)

Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
by: Yang, Te, et al.
Published: (2024)

MIGE: Mutually Enhanced Multimodal Instruction-Based Image Generation and Editing
by: Tian, Xueyun, et al.
Published: (2025)

Why Not Use Your Textbook? Knowledge-Enhanced Procedure Planning of Instructional Videos
by: Nagasinghe, Kumaranage Ravindu Yasas, et al.
Published: (2024)

Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning
by: Xu, Zhiyang, et al.
Published: (2024)

DreamVE: Unified Instruction-based Image and Video Editing
by: Xia, Bin, et al.
Published: (2025)

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation
by: Wang, Ao, et al.
Published: (2024)

Keypoint-Integrated Instruction-Following Data Generation for Enhanced Human Pose and Action Understanding in Multimodal Models
by: Zhang, Dewen, et al.
Published: (2024)

Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models
by: Zhang, Yang, et al.
Published: (2024)

How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing
by: Zhang, Huanyu, et al.
Published: (2026)

Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generation
by: Wei, Tianyi, et al.
Published: (2024)

InsightEdit: Towards Better Instruction Following for Image Editing
by: Xu, Yingjing, et al.
Published: (2024)

IF-VidCap: Can Video Caption Models Follow Instructions?
by: Li, Shihao, et al.
Published: (2025)

Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation
by: Zhou, Yucheng, et al.
Published: (2025)

Watch Your Steps: Local Image and Scene Editing by Text Instructions
by: Mirzaei, Ashkan, et al.
Published: (2023)

Investigating the Scaling Effect of Instruction Templates for Training Multimodal Language Model
by: Wang, Shijian, et al.
Published: (2024)

Go with Your Gut: Scaling Confidence for Autoregressive Image Generation
by: Chen, Harold Haodong, et al.
Published: (2025)

Score2Instruct: Scaling Up Video Quality-Centric Instructions via Automated Dimension Scoring
by: Xie, Qizhi, et al.
Published: (2025)

A High-Quality Text-Rich Image Instruction Tuning Dataset via Hybrid Instruction Generation
by: Zhou, Shijie, et al.
Published: (2024)

Learn Your Scales: Towards Scale-Consistent Generative Novel View Synthesis
by: Forghani, Fereshteh, et al.
Published: (2025)

UniBlendNet: Unified Global, Multi-Scale, and Region-Adaptive Modeling for Ambient Lighting Normalization
by: Dai, Jiatao, et al.
Published: (2026)

Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models
by: Huang, Yupan, et al.
Published: (2023)

VII: Visual Instruction Injection for Jailbreaking Image-to-Video Generation Models
by: Zheng, Bowen, et al.
Published: (2026)

OphIn-500K: Curating Web-Scale Visual Instructions for Scaling Ophthalmic Multimodal Large Language Models
by: Dong, Xuanzhao, et al.
Published: (2026)

Efficient Inference of Vision Instruction-Following Models with Elastic Cache
by: Liu, Zuyan, et al.
Published: (2024)

DeCoT: Decomposing Complex Instructions for Enhanced Text-to-Image Generation with Large Language Models
by: Lin, Xiaochuan, et al.
Published: (2025)

CREval: An Automated Interpretable Evaluation for Creative Image Manipulation under Complex Instructions
by: Wang, Chonghuinan, et al.
Published: (2026)

Advancing Aesthetic Image Generation via Composition Transfer
by: Zou, Kai, et al.
Published: (2026)