TALE: Training-free Cross-domain Image Composition via Adaptive Latent Manipulation and Energy-guided Optimization
Kien T. Pham, Jingye Chen, Qifeng Chen
2024Year
2Citations
5Top-tier citations
Abstract
We present TALE, a novel training-free framework harnessing the generative capabilities of text-to-image diffusion models to address the cross-domain image composition task that focuses on flawlessly incorporating user-specified objects into a designated visual
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 589f1449-5b1a-4735-a33d-402d680d7b7cCited by top-tier papers5
- Does FLUX Already Know How to Perform Physically Plausible Image Composition?Shilin Lu, Zhuming Lian, Zihan Zhou, Shaocong Zhang et al.ICLR 2026 · 34 citations
- SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video GenerationKien T. Pham, Yingqing He, Yazhou Xing, Qifeng Chen et al.ACM MM 2025 · 1 citation
- HOComp: Interaction-Aware Human-Object CompositionDong Liang, Jinyuan Jia, Yuhao Liu, Rynson W. H. LauNeurIPS 2025 · 1 citation
- AIcomposer: Any Style and Content Image Composition via Feature IntegrationHaowen Li, Zhenfeng Fan, Zhang Wen, Zhengzhou Zhu et al.ICCV 2025 · 1 citation
- CareCom: Generative Image Composition with Calibrated Reference FeaturesJiaxuan Chen, Bo Zhang, Qingdong He, Jinlong Peng et al.AAAI 2026
Builds on37
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao et al.ICCV 2023 · 13,211 citations
- Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 13,211 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
Related papers
- TF-ICON: Diffusion-Based Training-Free Cross-Domain Image CompositionShilin Lu, Yanzhu Liu, Adams Wai-Kin KongICCV 2023 · 214 citations
- Energy-Guided Optimization for Personalized Image Editing with Pretrained Text-to-Image Diffusion ModelsRui Jiang, Xinghe Fu, Guangcong Zheng, Teng Li et al.AAAI 2025 · 2 citations
- RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion ModelsXinchen Zhang, Ling Yang, Yaqi Cai, Zhaochen Yu et al.NeurIPS 2024 · 22 citations
- FreeInsert: Personalized Object Insertion with Geometric and Style ControlYuhong Zhang, Han Wang, Yiwen Wang, Rong Xie et al.ACM MM 2025 · 1 citation
- Teleportraits: Training-Free People Insertion Into Any SceneJialu Gao, K. J. Joseph, Fernando De la TorreICCV 2025
