# Customized Generation Reimagined: Fidelity and Editability Harmonized

arXiv: https://arxiv.org/abs/2412.04831 · HTML: https://mlsanity.com/paper/2412.04831/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 62 references that are in the map.
- First posted on arXiv 6 Dec 2024.

## Builds on (most cited first, 6 of 6)

- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Prompt-aligned Gradient for Prompt Tuning](https://mlsanity.com/paper/2205.14865/) (2022)
- [FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention](https://mlsanity.com/paper/2305.10431/) (2023)
- [Cones: Concept Neurons in Diffusion Models for Customized Generation](https://mlsanity.com/paper/2303.05125/) (2023)
- [Enhancing Detail Preservation for Customized Text-to-Image Generation: A Regularization-Free Approach](https://mlsanity.com/paper/2305.13579/) (2023)
- [ViCo: Plug-and-play Visual Condition for Personalized Text-to-image Generation](https://mlsanity.com/paper/2306.00971/) (2023)

## Built on by (most cited first, 3 of 3)

- [Personalized Image Generation with Deep Generative Models: A Decade Survey](https://mlsanity.com/paper/2502.13081/) (2025)
- [OrthoTryOn: Geometric Orthogonalization for Conflict-Free Unified Fashion Generation](https://mlsanity.com/paper/2606.27880/) (2026)
- [Training for Identity, Inference for Controllability: A Unified Approach to Tuning-Free Face Personalization](https://mlsanity.com/paper/2512.03964/) (2025)

## Abstract (arXiv)

Customized generation aims to incorporate a novel concept into a pre-trained text-to-image model, enabling new generations of the concept in novel contexts guided by textual prompts. However, customized generation suffers from an inherent trade-off between concept fidelity and editability, i.e., between precisely modeling the concept and faithfully adhering to the prompts. Previous methods reluctantly seek a compromise and struggle to achieve both high concept fidelity and ideal prompt alignment simultaneously. In this paper, we propose a Divide, Conquer, then Integrate (DCI) framework, which performs a surgical adjustment in the early stage of denoising to liberate the fine-tuned model from the fidelity-editability trade-off at inference. The two conflicting components in the trade-off are decoupled and individually conquered by two collaborative branches, which are then selectively integrated to preserve high concept fidelity while achieving faithful prompt adherence. To obtain a better fine-tuned model, we introduce an Image-specific Context Optimization} (ICO) strategy for model customization. ICO replaces manual prompt templates with learnable image-specific contexts, providing an adaptive and precise fine-tuning direction to promote the overall performance. Extensive experiments demonstrate the effectiveness of our method in reconciling the fidelity-editability trade-off.