Cover Image

CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Guo, Xiefan, Ma, Xinzhu, Zhang, Haiyu, Huang, Di
Format:	Preprint
Published:	2026
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

EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesis
by: Guo, Xiefan, et al.
Published: (2026)

InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization
by: Guo, Xiefan, et al.
Published: (2024)

Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models
by: Zhang, Jinjin, et al.
Published: (2025)

Image Inpainting via Conditional Texture and Structure Dual Generation
by: Guo, Xiefan, et al.
Published: (2021)

ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning
by: Guo, Xiefan, et al.
Published: (2025)

Spatial Gram Alignment for Ultra-High-Resolution Image Synthesis
by: Zhang, Jinjin, et al.
Published: (2026)

I4VGen: Image as Free Stepping Stone for Text-to-Video Generation
by: Guo, Xiefan, et al.
Published: (2024)

Ultra-High-Resolution Image Synthesis: Data, Method and Evaluation
by: Zhang, Jinjin, et al.
Published: (2025)

What Makes Synthetic Data Effective in Image Segmentation
by: Zhang, Jinjin, et al.
Published: (2026)

TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
by: Sun, Haojun, et al.
Published: (2024)

TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models
by: Huang, Haocheng, et al.
Published: (2024)

AsyncDiff: Asynchronous Timestep Conditioning for Enhanced Text-to-Image Diffusion Inference
by: Xu, Longhuan, et al.
Published: (2025)

GraspLDP: Towards Generalizable Grasping Policy via Latent Diffusion
by: Xiang, Enda, et al.
Published: (2026)

TASR: Timestep-Aware Diffusion Model for Image Super-Resolution
by: Lin, Qinwei, et al.
Published: (2024)

Towards Unbiased Source-Free Object Detection via Vision Foundation Models
by: Cai, Zhi, et al.
Published: (2026)

Timestep-Aware Correction for Quantized Diffusion Models
by: Yao, Yuzhe, et al.
Published: (2024)

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
by: Liu, Feng, et al.
Published: (2024)

Rethinking Timesteps Samplers and Prediction Types
by: Xie, Bin, et al.
Published: (2025)

QArtSR: Quantization via Reverse-Module and Timestep-Retraining in One-Step Diffusion based Image Super-Resolution
by: Zhu, Libo, et al.
Published: (2025)

Timestep-Aware Block Masking for Efficient Diffusion Model Inference
by: He, Haodong, et al.
Published: (2026)

Timestep-Aware Diffusion Model for Extreme Image Rescaling
by: Wang, Ce, et al.
Published: (2024)

ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion
by: Peng, Xurui, et al.
Published: (2025)

Explainable Synthetic Image Detection through Diffusion Timestep Ensembling
by: Wu, Yixin, et al.
Published: (2025)

Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing
by: Liu, Bingyan, et al.
Published: (2024)

Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning
by: Lin, Wang, et al.
Published: (2025)

Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping
by: Ding, Ning, et al.
Published: (2025)

Exploring Multi-Timestep Multi-Stage Diffusion Features for Hyperspectral Image Classification
by: Zhou, Jingyi, et al.
Published: (2023)

TiNO-Edit: Timestep and Noise Optimization for Robust Diffusion-Based Image Editing
by: Chen, Sherry X., et al.
Published: (2024)

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens
by: Pan, Kaihang, et al.
Published: (2025)

Self-Cross Diffusion Guidance for Text-to-Image Synthesis of Similar Subjects
by: Qiu, Weimin, et al.
Published: (2024)

Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner
by: Xia, Mengfei, et al.
Published: (2023)

Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
by: Miao, Zichen, et al.
Published: (2024)

VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control
by: Wu, Shaojin, et al.
Published: (2024)

ITA-MDT: Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-On
by: Hong, Ji Woo, et al.
Published: (2025)

IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance
by: Guo, Jiayi, et al.
Published: (2025)

Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs
by: Tang, Bao, et al.
Published: (2025)

TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision
by: Zhuang, Shaobin, et al.
Published: (2025)

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
by: Chen, Dong, et al.
Published: (2026)

UniTransfer: Video Concept Transfer via Progressive Spatial and Timestep Decomposition
by: Lei, Guojun, et al.
Published: (2025)

HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration
by: Sun, Desen, et al.
Published: (2026)