Injecting Image Guidance into Text-Conditioned Diffusion Models at Inference

Hugging Face Daily Papers Papers

Summary

Visual Concept Fusion (VCF) enables dual conditioning on both an image and text prompt in diffusion models at inference time without retraining, using a lightweight aligner and fusion strategy.

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.
Original Article
View Cached Full Text

Cached at: 05/26/26, 02:44 PM

Paper page - Injecting Image Guidance into Text-Conditioned Diffusion Models at Inference

Source: https://huggingface.co/papers/2605.25191

Abstract

Visual Concept Fusion enables dual text and image conditioning in diffusion models through feature alignment and fusion strategies without requiring retraining.

Text-to-image diffusion modelslikeStable Diffusiongenerate high-quality images from text, but lack a way to injectvisual 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 intoStable Diffusionby aligningCLIP image featureswith thetext embedding space. VCF consists of three components: (1) a lightweight aligner that maps image tokens to the text embedding manifold usingInfoNCEandcross-attention reconstructionlosses, (2) afusion strategythat preserves both textual and visual semantics, and (3) an optionalPrompt-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.

View arXiv pageView PDFGitHub0Add to collection

Get this paper in your agent:

hf papers read 2605\.25191

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.25191 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.25191 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.25191 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Scaling Properties of Text Conditioning in Visual Generation

Hugging Face Daily Papers

This paper studies empirical scaling properties for text conditioning in visual generation, showing that converged diffusion loss scales with structured language in prompts, and introduces methods to improve diffusability and promptability.

Hierarchical text-conditional image generation with CLIP latents

OpenAI Blog

OpenAI proposes a hierarchical two-stage model for text-conditional image generation using CLIP latents: a prior that generates CLIP image embeddings from text captions, and a diffusion-based decoder that generates images from embeddings. The approach improves image diversity and enables zero-shot language-guided image manipulations.