Article

An Efficient and Training-Free Approach for Subject-Driven Text-to-Image Generation

2026-01-09

Abstract excerpt

Subject-driven text-to-image generation presents a significant challenge: faithfully reproducing a specific subject's identity within novel, text-described scenes. Existing solutions typically involve computationally expensive model fine-tuning or less performant training-free methods. This paper introduces Content-Adaptive Grafting (CAG), a novel, efficient, and entirely training-free framework designed to achiev...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 884f9f46-21b3-5a8d-9743-899961ea7474
DOI: 10.20944/preprints202601.0734.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

An Efficient and Training-Free Approach for Subject-Driven Text-to-Image GenerationDOI 10.20944/preprints202601.0734.v1Read

Generative AI for Text-to-Video Generation: Recent Advances and Future DirectionsSemantic proximity Read

Identity-Preserving Text-to-Video Generation by Frequency DecompositionSemantic proximity Read

HEADHUNTER: Training-Free Annotated Dataset Synthesis via Self-Guided Diffusion Transformer Attention Head SelectionSemantic proximity Read

HEADHUNTER: Training-Free Annotated Dataset Synthesis via Self-Guided Diffusion Transformer Attention Head SelectionSemantic proximity Read

A Survey on Video Generation Technologies, Applications, and Ethical ConsiderationsSemantic proximity Read

Introduction to Diffusion Models, Autoencoders and Transformers: Review of Current AdvancementsSemantic proximity Read

Adaptive Semantic Fusion for Contextual Image CaptioningSemantic proximity Read

MotionCharacter: Identity-Preserving and Motion Controllable Human Video GenerationSemantic proximity Read

CalliFormer: A Structure-Aware Transformer for Chinese Calligraphy GenerationSemantic proximity Read

LinGen-Uni: A Universal Linear-Complexity Framework for High-Resolution Minute-Length Text-to-Video GenerationSemantic proximity Read

Evaluating Text-to-Image Generated Photorealistic Images of Human AnatomySemantic proximity Read

Benchmark Collapse in Text CAPTCHAs: Generator Heterogeneity, Cross-Generator Transfer, and Reliability-Aware Synthetic EvaluationSemantic proximity Read