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

Shengqi Dang; Yi He; Jiaying Lei; Ziqing Qian; Nan Cao

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

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.

✔ supported, ✗ not supported.
Capability	Nano Banana 2	FLUX.2	EmotiCrafter ∗	GANalyze †	CogBlender (Ours)
Text input	✔	✔	✔	✗	✔
Flexible dimensional control	✔	✔	✗	✗	✔
Continuous control	✗	✗	✔	✔	✔
∗ 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.

	Method	CLIPScore $\uparrow$	CLIPIQA $\uparrow$	V-Err $\downarrow$	A-Err $\downarrow$	D-Err $\downarrow$
V-A	Nano Banana 2	25.645	0.937	0.277	0.319	–
	FLUX.2	26.355	0.885	0.285	0.323	–
	EmotiCrafter	17.544	0.861	0.221	0.304	–
	CogBlender (Ours)	25.751	0.917	0.257	0.299	–
V-A-D	Nano Banana 2	25.774	0.932	0.312	0.370	0.357
	FLUX.2	26.350	0.886	0.323	0.372	0.362

Table 2: Quantitative comparison on C-EICG. The best and second best results are highlighted with dark blue and light blue backgrounds, respectively.

Dimension	MAE $\downarrow$		Pearson’s $r$ $\uparrow$
	CogBlender (Ours)	Nano Banana 2 (Baseline)	CogBlender (Ours)	Nano Banana 2 (Baseline)
Dominance	0.203	0.277	0.594	0.147
Valence	0.114	0.123	0.890	0.884
Arousal	0.190	0.237	0.805	0.549

Table 3: User study results.

Figure 3: Comparison results on the Memorability-Aware Image Content Generation (MICG) task.

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.”

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

Seeing is Believing: Aligning Prompt Rewriting with Visual Anchors for Text-to-Image Generation
Jun 7, 2026Xuanyi Liu, Deyi Ji, Junyu Lu +6T2I Generation Prompt Optimization for T2I Generation
Peking University · Tencent · Dalian University of Technology +4
Tree-of-Thoughts Reasoning for Text-to-Image In-Context Learning
Jul 8, 2026Stepanida Alekseeva, Jenifer Kalafatovich, Seong-Whan LeeTree of Thoughts Multimodal ICL
Department of Artificial Intelligence, Korea University, Seoul, Korea.
Concept Guidance: Precise, Training-Free Latent Control for Text-to-Image Generation
Aug 14, 2026Nikolai Röhrich, Isabell Hans, Felix Krause +1Diffusion Model Guidance T2I Generation
LMU Munich, Germany · Konrad Zuse School of Excellence in Reliable AI (relAI), Germany · Munich Center for Machine Learning (MCML), Germany

Jun 7, 2026J/K move · Enter open · S save

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

Xuanyi Liu, Deyi Ji, Junyu Lu, Jing Wang+5

Peking University · Tencent · Dalian University of Technology+4

T2I Generation Prompt Optimization for T2I Generation Visual Grounding Prompt Engineering

Open paper AskPDF arXiv

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.

Abstract

T2I Generation

Explore similar work

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

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

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