Injecting Image Guidance into Text-Conditioned Diffusion Models at Inference

• URL: http://arxiv.org/abs/2605.25191v1
• Date: Sun, 24 May 2026 17:47:21 GMT
• Title: Injecting Image Guidance into Text-Conditioned Diffusion Models at Inference
• Abstract summary: Text-to-image diffusion models generate high-quality images from text, but lack a way to inject visual guidance at inference without retraining.<n>We introduce Visual Concept Fusion (VCF), the first method offering dual conditioning on both an image and text prompt at inference time without any concept-specific training.<n>VCF successfully transfers visual attributes including style, composition, and color palette from reference images while maintaining prompt adherence.
• Score: 1.7394635819080972
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Text-to-image diffusion models like Stable Diffusion generate high-quality images from text, but lack a way to inject visual guidance (e.g. sketches, styles) at inference without retraining. Existing methods either require computationally expensive fine-tuning or rely on style transfer techniques that risk semantic misalignment with textual prompts. We introduce Visual Concept Fusion (VCF), the first method offering dual conditioning on both an image and text prompt at inference time without any concept-specific training. VCF enables visual concept injection into Stable Diffusion by aligning CLIP image features with the text embedding space. VCF consists of three components: (1) a lightweight aligner that maps image tokens to the text embedding manifold using InfoNCE and cross-attention reconstruction losses, (2) a fusion strategy that preserves both textual and visual semantics, and (3) an optional Prompt-Noise Optimization (PNO) module for test-time refinement. Our experiments demonstrate that VCF successfully transfers visual attributes including style, composition, and color palette from reference images while maintaining prompt adherence. Quantitative results show a trade-off between text alignment (CLIP score) and visual correspondence (LPIPS), with VCF outperforming baselines in reference fidelity.

Related papers

• Prompt Reinjection: Alleviating Prompt Forgetting in Multimodal Diffusion Transformers [64.4017917917109]
  Multimodal Diffusion Transformers (MMDiTs) for text-to-image generation maintain separate text and image branches.<n>We observe a prompt forgetting phenomenon: the semantics of the prompt representation in the text branch is progressively forgotten as depth increases.<n>Motivated by these findings, we introduce a training-free approach, prompt reinjection, which reinjects prompt representations from early layers into later layers to alleviate this forgetting.
  arXiv  Detail & Related papers  (2026-02-06T17:19:53Z)
• TextGuider: Training-Free Guidance for Text Rendering via Attention Alignment [68.91073792449201]
  We propose TextGuider, a training-free method that encourages accurate and complete text appearance.<n>Specifically, we analyze attention patterns in Multi-Modal Diffusion Transformer(MM-DiT) models, particularly for text-related tokens intended to be rendered in the image.<n>Our method achieves state-of-the-art performance in test-time text rendering, with significant gains in recall and strong results in OCR accuracy and CLIP score.
  arXiv  Detail & Related papers  (2025-12-10T06:18:30Z)
• Leveraging Textual Compositional Reasoning for Robust Change Captioning [28.774190149120134]
  We present CORTEX, a novel framework that integrates complementary textual cues to enhance change understanding.<n> CORTEX consists of three key modules: (i) an Image-level Change Detector that identifies low-level visual differences between paired images, (ii) a Reasoning-aware Text Extraction (RTE) module that use VLMs to generate compositional reasoning descriptions implicit in visual features, and (iii) an Image-Text Dual Alignment (ITDA) module that aligns visual and textual features for fine-grained relational reasoning.
  arXiv  Detail & Related papers  (2025-11-28T06:11:23Z)
• Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learning [69.33115351856785]
  We present a novel method, called T2I-PAL, to tackle the modality gap issue when using only text captions for PEFT.<n>The core design of T2I-PAL is to leverage pre-trained text-to-image generation models to generate photo-realistic and diverse images from text captions.<n>Extensive experiments on multiple benchmarks, including MS-COCO, VOC2007, and NUS-WIDE, show that our T2I-PAL can boost recognition performance by 3.47% in average.
  arXiv  Detail & Related papers  (2025-06-12T11:09:49Z)
• VSC: Visual Search Compositional Text-to-Image Diffusion Model [15.682990658945682]
  We introduce a novel compositional generation method that leverages pairwise image embeddings to improve attribute-object binding.<n>Our approach decomposes complex prompts into sub-prompts, generates corresponding images, and computes visual prototypes that fuse with text embeddings to enhance representation.<n>Our approaches outperform existing compositional text-to-image diffusion models on the benchmark T2I CompBench, achieving better image quality, evaluated by humans, and emerging robustness under scaling number of binding pairs in the prompt.
  arXiv  Detail & Related papers  (2025-05-02T08:31:43Z)
• PTDiffusion: Free Lunch for Generating Optical Illusion Hidden Pictures with Phase-Transferred Diffusion Model [23.479182559911813]
  Optical illusion hidden picture is an interesting visual phenomenon where an image is cleverly integrated into another picture in a way that is not immediately obvious to the viewer.<n>We propose a novel training-free text-guided image-to-image (I2I) translation framework dubbed as textbfPhase-textbfTransferred textbfDiffusion Model (PTDiffusion) for hidden art syntheses.
  arXiv  Detail & Related papers  (2025-03-08T12:06:21Z)
• Contrastive Prompts Improve Disentanglement in Text-to-Image Diffusion Models [68.47333676663312]
  We show a simple modification of classifier-free guidance can help disentangle image factors in text-to-image models. The key idea of our method, Contrastive Guidance, is to characterize an intended factor with two prompts that differ in minimal tokens. We illustrate whose benefits in three scenarios: (1) to guide domain-specific diffusion models trained on an object class, (2) to gain continuous, rig-like controls for text-to-image generation, and (3) to improve the performance of zero-shot image editors.
  arXiv  Detail & Related papers  (2024-02-21T03:01:17Z)
• RealignDiff: Boosting Text-to-Image Diffusion Model with Coarse-to-fine Semantic Re-alignment [112.45442468794658]
  We propose a two-stage coarse-to-fine semantic re-alignment method, named RealignDiff. In the coarse semantic re-alignment phase, a novel caption reward is proposed to evaluate the semantic discrepancy between the generated image caption and the given text prompt. The fine semantic re-alignment stage employs a local dense caption generation module and a re-weighting attention modulation module to refine the previously generated images from a local semantic view.
  arXiv  Detail & Related papers  (2023-05-31T06:59:21Z)
• Unleashing Text-to-Image Diffusion Models for Visual Perception [84.41514649568094]
  VPD (Visual Perception with a pre-trained diffusion model) is a new framework that exploits the semantic information of a pre-trained text-to-image diffusion model in visual perception tasks. We show that VPD can be faster adapted to downstream visual perception tasks using the proposed VPD.
  arXiv  Detail & Related papers  (2023-03-03T18:59:47Z)
• Text to Image Generation with Semantic-Spatial Aware GAN [41.73685713621705]
  A text to image generation (T2I) model aims to generate photo-realistic images which are semantically consistent with the text descriptions. We propose a novel framework Semantic-Spatial Aware GAN, which is trained in an end-to-end fashion so that the text encoder can exploit better text information.
  arXiv  Detail & Related papers  (2021-04-01T15:48:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.