cs.CVMar 10, 2026

CogBlender: Towards Continuous Cognitive Intervention in Text-to-Image Generation

Authors: Shengqi Dang, Yi He, Jiaying Lei, Ziqing Qian, Nan Cao

Organizations: Tongji University · Shanghai Innovation Institute

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Beyond conveying semantic information, images also possess cognitive properties that elicit specific psychological responses from viewers, such as memory encoding or emotional reactions. Although modern text-to-image (T2I) models generate semantically coherent content effectively, they struggle to control cognitive properties (e.g., valence, memorability) and often fail to align with the user's psychological intent. To bridge the gap, we introduce CogBlender, an algorithm that enables continuous and multi-dimensional intervention on cognitive properties through a novel two-stage approach. First, we construct discrete cognition-aware rewritten prompts-variants of the input prompt that represent distinct extreme cognitive states. Second, we translate these discrete prompts into continuous control signals by interpolating within the velocity-field domain of flow-matching models. By dynamically blending the velocity fields predicted from these prompts according to the target cognitive scores, CogBlender smoothly steers the generative trajectory to realize the desired cognitive properties in the final image. Extensive experiments across four cognitive properties (i.e., valence, arousal, dominance, and memorability) demonstrate that CogBlender achieves effective cognitive intervention.

Figures & tables

Figure 1: Algorithm Overview. To illustrate key notations, a two-dimensional Valence-Arousal (V-A) space is depicted as a visual example.
CapabilityNano Banana 2FLUX.2EmotiCrafter ∗GANalyze †CogBlender (Ours)
Text input✔✔✔✗✔
Flexible dimensional control✔✔✗✗✔
Continuous control✗✗✔✔✔
✔ supported, ✗ not supported.
∗ Supports only two fixed dimensions (Valence and Arousal).
† Supports only Valence and Memorability, and only a single dimension can be manipulated during generation.
Table 1: Comparison of baselines and our method across key control capabilities.
Figure 2: Qualitative comparison on the C-EICG task.
 MethodCLIPScore ↑\uparrowCLIPIQA ↑\uparrowV-Err ↓\downarrowA-Err ↓\downarrowD-Err ↓\downarrow
V-ANano Banana 225.6450.9370.2770.319–
FLUX.226.3550.8850.2850.323–
EmotiCrafter17.5440.8610.2210.304–
CogBlender (Ours)25.7510.9170.2570.299–
V-A-DNano Banana 225.7740.9320.3120.3700.357
FLUX.226.3500.8860.3230.3720.362
Table 2: Quantitative comparison on C-EICG. The best and second best results are highlighted with dark blue and light blue backgrounds, respectively.
DimensionMAE ↓\downarrowPearson’s rr ↑\uparrow
 CogBlender (Ours)Nano Banana 2 (Baseline)CogBlender (Ours)Nano Banana 2 (Baseline)
Dominance0.2030.2770.5940.147
Valence0.1140.1230.8900.884
Arousal0.1900.2370.8050.549
Table 3: User study results.
Figure 3: Comparison results on the Memorability-Aware Image Content Generation (MICG) task.
Figure 7
Figure 5: Interpolation results along the trajectory from (V, A) = (0.3, 0.3) to (V, A) = (0.6, 0.6) for the prompt “A teddy bear is walking in the park.”
More in this topic

T2I Generation

Text-to-image generation creates images from natural-language prompts using generative models, with research focused on fidelity, control, efficiency, and safety.

See all 299 papers

Explore similar work

CardsList
Jun 7, 2026

Seeing is Believing: Aligning Prompt Rewriting with Visual Anchors for Text-to-Image Generation

Despite the impressive capabilities of text-to-image (T2I) models, an intent-generation gap often persists due to the brevity and ambiguity of user prompts. Existing approaches primarily polish the prompt for fluency and readability. However, the enhancement process still lacks visual grounding. As a result, the rewriter may over-infer missing details, causing an intent-generation gap. To address this limitation, we propose FaithRewriter, a novel prompt-enhancement framework for T2I generation. Specifically, FaithRewriter first leverages a multimodal MLLM to generate an image from the original prompt as an intermediate visual cue. This cue is then combined with the prompt and fed into a large-scale LLM to produce visually grounded augmentations that better reflect how the intended content should appear in images. Finally, these augmentations are distilled into a small-scale LLM for efficient deployment, enhancing its ability to generate effective T2I prompts. Experiments show that FaithRewriter yields prompts that are more faithful to the user intent and more visually plausible than strong baselines, helping narrow the intent-generation gap.

Xuanyi Liu, Deyi Ji, Junyu Lu +6

Peking University · Tencent · Dalian University of Technology +4

T2I GenerationPrompt Optimization for T2I GenerationVisual GroundingPrompt Engineering
AskPDF
Jul 8, 2026

Tree-of-Thoughts Reasoning for Text-to-Image In-Context Learning

In text-to-image in-context learning (T2I-ICL), a model has to infer a latent compositional pattern from fewshot demonstrations for generating a query image. Recent studies show that state-of-the-art multimodal large language models struggle with this setting, particularly due to limited compositional reasoning and sensitivity to prompt construction. In this work, we propose a Tree-of-Thoughts (ToT) reasoning framework for T2I-ICL that introduces a multi-stage reasoning and selection layer that generates, evaluates, and selects among multiple candidate hypotheses before constructing the final prompt for image synthesis. By exploring alternative reasoning branches and selecting a coherent interpretation, the proposed approach mitigates prompt ambiguity and compositional errors. We implement the proposed approach in a complete ToT-T2IICL inference pipeline and evaluate it on the CoBSAT benchmark. Both qualitative and quantitative results show that structured multi-branch reasoning leads to more consistent and semantically aligned image generation compared to baseline and Chain-of-Thought prompting strategies, without any additional training or fine-tuning.

Stepanida Alekseeva, Jenifer Kalafatovich, Seong-Whan Lee

Department of Artificial Intelligence, Korea University, Seoul, Korea.

Tree of ThoughtsMultimodal ICLCompositional T2I GenerationIn-Context Learning
AskPDF
Aug 14, 2026

Concept Guidance: Precise, Training-Free Latent Control for Text-to-Image Generation

Text-to-image diffusion models have two major drawbacks that severely limit their practical utility: (1) standard models lack an intrinsic mechanism for continuous, concept-specific guidance (e.g., for precisely controlling how aesthetically pleasing an image looks), and (2) they lack reliability for tasks requiring high local coherence (e.g., generating text or human hands). To tackle these issues, we introduce a novel notion of concept-wise mutual information and find large, concept-dependent differences between individual layers, demonstrating that the generation of specific structures is localized in distinct parts of the network. We exploit this insight by reinforcing the impact of concept-relevant layers in Concept Guidance (CoG), a precise, target-specific guidance method that works for models out-of-the-box without additional training, external models, gradients, or prompt engineering. CoG first quantifies each layer's concept-specific impact and then guides denoising using a weighted combination of predictions generated with concept-relevant layers skipped. We demonstrate performance increases across various targets and popular models like PixArt-alpha, SD3, SD3.5, and FLUX.1-dev. Code is available at https://github.com/CompVis/concept_guidance

Nikolai Röhrich, Isabell Hans, Felix Krause +1

LMU Munich, Germany · Konrad Zuse School of Excellence in Reliable AI (relAI), Germany · Munich Center for Machine Learning (MCML), Germany

Diffusion Model GuidanceT2I GenerationControllable Image GenerationDiffusion GuidanceDiffusion Models
AskPDF