EMNLP Findings2025
EditID: Training-Free Editable ID Customization for Text-to-Image Generation
Abstract
We propose EditID, a training-free approach based on the DiT architecture, which achieves highly editable customized IDs for text to image generation. Existing text-to-image models for customized IDs typically focus more on ID consistency while neglecting editability. It is challenging to alter facial orientation, character attributes, and other features through prompts. EditID addresses this by deconstructing the text-to-image model for customized IDs into an image generation branch and a character feature branch. The character feature branch is further decoupled into three modules: feature extraction, feature fusion, and feature integration. By introducing a combination of mapping features and shift features, along with controlling the intensity of ID feature integration, EditID achieves semantic compression of local features across network depths, forming an editable feature space. This enables the successful generation of high-quality images with editable IDs while maintaining ID consistency, achieving excellent results in the IBench evaluation, which is an editability evaluation framework for the field of customized ID text-to-image generation that quantitatively demonstrates the superior performance of EditID. EditID is the first text-to-image solution to propose customizable ID editability on the DiT architecture, meeting the demands of long prompts and high-quality image generation.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis cites High-Resolution Image Synthesis with Latent Diffusion Models
- SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis cites Scalable Diffusion Models with Transformers
- Scalable Diffusion Models with Transformers cites High-Resolution Image Synthesis with Latent Diffusion Models
Builds on16
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Flamingo: a Visual Language Model for Few-Shot LearningJean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech et al.NeurIPS 2022 · 6,707 citations
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 5,568 citations
- SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisDustin Podell, Zion English, Kyle Lacey, Andreas Blattmann et al.ICLR 2024 · 4,569 citations
- MUSIQ: Multi-scale Image Quality TransformerJunjie Ke, Qifei Wang, Yilin Wang, Peyman Milanfar et al.ICCV 2021 · 1,325 citations
Related papers
- PuLID: Pure and Lightning ID Customization via Contrastive AlignmentZinan Guo, Yanze Wu, Zhuowei Chen, Lang Chen et al.NeurIPS 2024 · 184 citations
- TF-TI2I: Training-Free Text-And-Image-To-Image Generation via Multi-Modal Implicit-Context Learning in Text-To-Image ModelsTeng-Fang Hsiao, Bo-Kai Ruan, Yi-Lun Wu, Tzu-Ling Lin et al.ICCV 2025 · 3 citations
- DynamicID: Zero-Shot Multi-ID Image Personalization With Flexible Facial EditabilityXirui Hu, Jiahao Wang, Hao Chen, Weizhan Zhang et al.ICCV 2025 · 3 citations
- Personalize Anything for Free with Diffusion TransformerHaoran Feng, Zehuan Huang, Lin Li, Lu ShengAAAI 2026 · 1 citation
- UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image PersonalizationJunjie He, Yifeng Geng, Liefeng BoICCV 2025 · 2 citations
