SCHEMA for Gemini 3 Pro Image: A Structured Methodology for Controlled AI Image Generation on Google's Native Multimodal Model

• URL: http://arxiv.org/abs/2602.18903v1
• Date: Sat, 21 Feb 2026 16:51:40 GMT
• Title: SCHEMA for Gemini 3 Pro Image: A Structured Methodology for Controlled AI Image Generation on Google's Native Multimodal Model
• Abstract summary: SCHEMA is an engineered framework built on systematic professional practice encompassing 850 verified API predictions.<n>SchEMA scales practitioner control from exploratory (approximately 5%) to directive (approximately 95%)<n>Key findings include an observed 91% Mandatory compliance rate and 94% Prohibitions compliance rate across 621 structured prompts.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents SCHEMA (Structured Components for Harmonized Engineered Modular Architecture), a structured prompt engineering methodology specifically developed for Google Gemini 3 Pro Image. Unlike generic prompt guidelines or model-agnostic tips, SCHEMA is an engineered framework built on systematic professional practice encompassing 850 verified API predictions within an estimated corpus of approximately 4,800 generated images, spanning six professional domains: real estate photography, commercial product photography, editorial content, storyboards, commercial campaigns, and information design. The methodology introduces a three-tier progressive system (BASE, MEDIO, AVANZATO) that scales practitioner control from exploratory (approximately 5%) to directive (approximately 95%), a modular label architecture with 7 core and 5 optional structured components, a decision tree with explicit routing rules to alternative tools, and systematically documented model limitations with corresponding workarounds. Key findings include an observed 91% Mandatory compliance rate and 94% Prohibitions compliance rate across 621 structured prompts, a comparative batch consistency test demonstrating substantially higher inter-generation coherence for structured prompts, independent practitioner validation (n=40), and a dedicated Information Design validation demonstrating >95% first-generation compliance for spatial and typographical control across approximately 300 publicly verifiable infographics. Previously published on Zenodo (doi:10.5281/zenodo.18721380).

Related papers

• TRACE-Bench: Decomposing and Diagnosing Multi-Reference Image Generation [74.69068352546073]
  TRACE-Bench is an evaluation tool for multi-reference images spanning diverse artistic styles and real-world subjects.<n>It is built from 631 formula templates and around 4,000 reference images spanning diverse artistic styles and real-world subjects.<n>Its formula structure drives an operator-aligned evaluation protocol for per-capability scoring and a diagnostic tree analysis.
  arXiv  Detail & Related papers  (2026-08-17T16:15:50Z)
• Page image classifier fine-tuned on century-spanning archives of scanned documents for further content-specific processing [0.0]
  Digitization projects in the humanities produce vast, heterogeneous archives of historical documents.<n>This work addresses the need for an automated system to classify scanned page images based on visual content type.<n>An image classification system was developed and evaluated on a dataset of over 48,000 annotated historical page images.
  arXiv  Detail & Related papers  (2026-05-25T08:36:36Z)
• MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale [92.09717763663873]
  We present MinerU2.5-Pro, which advances the state of the art purely through data engineering and training strategy design.<n>At its core is a Data Engine co-designed around coverage, informativeness, and annotation accuracy.<n>We show that MinerU2.5-Pro achieves 95.69 on OmniDocBench v1.6, improving over the same-architecture baseline by 2.71 points and surpassing all existing methods.
  arXiv  Detail & Related papers  (2026-04-06T15:44:18Z)
• Designing Any Imaging System from Natural Language: Agent-Constrained Composition over a Finite Primitive Basis [1.7259824817932294]
  spec.md is a structured specification format that translates a one-sentence natural-language description into a validated forward model with bounded reconstruction error.<n>A design-to-real error theorem decomposes total reconstruction error into five independently bounded terms, each linked to a corrective action.<n>Ten novel designs -- composing primitives into chains from 3D to 5D -- demonstrate compositional reach beyond any single-modality tool.
  arXiv  Detail & Related papers  (2026-03-26T16:47:27Z)
• VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents [1.06378109904813]
  VAREX is a benchmark for evaluating structured data extraction from government forms.<n>The benchmark comprises 1,777 documents with 1,771 unique documents with validated ground truth through three-phase quality assurance.<n>Results reveal that below 4B parameters, compliance output -- not extraction capability -- is a dominant bottleneck.
  arXiv  Detail & Related papers  (2026-03-16T11:15:56Z)
• Structured Context Engineering for File-Native Agentic Systems: Evaluating Schema Accuracy, Format Effectiveness, and Multi-File Navigation at Scale [0.0]
  Large Language Model agents increasingly operate systems through programmatic interfaces.<n>Yet practitioners lack empirical guidance on how to structure the context these agents consume.<n>We study 9,649 experiments across 11 models, 4 formats, and schemas ranging from 10 to 10,000 tables.
  arXiv  Detail & Related papers  (2026-02-05T08:39:05Z)
• How Well Do Models Follow Visual Instructions? VIBE: A Systematic Benchmark for Visual Instruction-Driven Image Editing [56.60465182650588]
  We introduce three-level interaction hierarchy that captures deictic grounding, morphological manipulation, and causal reasoning.<n>We propose a robust LMM-as-a-judge evaluation framework with task-specific metrics to enable scalable and fine-grained assessment.<n>We find that proprietary models exhibit early-stage visual instruction-following capabilities and consistently outperform open-source models.
  arXiv  Detail & Related papers  (2026-02-02T09:24:45Z)
• ProImage-Bench: Rubric-Based Evaluation for Professional Image Generation [151.75112778479468]
  We study professional image generation, where a model must synthesize scientifically precise illustrations from technical descriptions.<n>For 654 figures collected from real textbooks and technical reports, we construct detailed image instructions and a hierarchy of rubrics that decompose correctness into 6,076 criteria and 44,131 binary checks.<n>We benchmark several representative text-to-image models on ProImage-Bench and find that, despite strong open-domain performance, the best base model reaches only 0.791 accuracy and 0.553 criterion score overall.
  arXiv  Detail & Related papers  (2025-12-13T07:13:43Z)
• Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing [40.13961086100904]
  Pico-Banana-400K is a comprehensive 400K-image dataset for instruction-based image editing.<n>Our dataset is constructed by leveraging Nano-Banana to generate diverse edit pairs from real photographs.<n>By providing this large-scale, high-quality, and task-rich resource, Pico-Banana-400K establishes a robust foundation for training and benchmarking the next generation of text-guided image editing models.
  arXiv  Detail & Related papers  (2025-10-22T17:43:15Z)
• Factuality Matters: When Image Generation and Editing Meet Structured Visuals [46.627460447235855]
  We construct a large-scale dataset of 1.3 million high-quality structured image pairs.<n>We train a unified model that integrates a VLM with FLUX.1 Kontext.<n>A three-stage training curriculum enables progressive feature alignment, knowledge infusion, and reasoning-augmented generation.
  arXiv  Detail & Related papers  (2025-10-06T17:56:55Z)
• PRISM: Phase-enhanced Radial-based Image Signature Mapping framework for fingerprinting AI-generated images [2.119461028150219]
  We introduce PRISM, a scalable framework for fingerprinting AI-generated images.<n>We construct PRISM-36K, a novel dataset of 36,000 images generated by six text-to-image GAN- and diffusion-based models.<n> PRISM achieves an attribution accuracy of 92.04% on this dataset.
  arXiv  Detail & Related papers  (2025-09-18T10:57:26Z)
• OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks [52.87238755666243]
  We present OmniEAR, a framework for evaluating how language models reason about physical interactions, tool usage, and multi-agent coordination in embodied tasks.<n>We model continuous physical properties and complex spatial relationships across 1,500 scenarios spanning household and industrial domains.<n>Our systematic evaluation reveals severe performance degradation when models must reason from constraints.
  arXiv  Detail & Related papers  (2025-08-07T17:54:15Z)
• IC-Custom: Diverse Image Customization via In-Context Learning [93.65917928168558]
  IC-Custom is a unified framework that seamlessly integrates position-aware and position-free image customization.<n>We propose the In-context Multi-Modal Attention (ICMA) mechanism, which employs learnable task-oriented register tokens and boundary-aware positional embeddings.<n> IC-Custom supports various industrial applications, including try-on, image insertion, and creative IP customization.
  arXiv  Detail & Related papers  (2025-07-02T17:36:38Z)
• Elucidating the Design Space of Multimodal Protein Language Models [69.3650883370033]
  Multimodal protein language models (PLMs) integrate sequence and token-based structural information.<n>This paper systematically elucidates the design space of multimodal PLMs to overcome their limitations.<n>Our advancements approach finer-grained supervision, demonstrating that token-based multimodal PLMs can achieve robust structural modeling.
  arXiv  Detail & Related papers  (2025-04-15T17:59:43Z)
• SAGI: Semantically Aligned and Uncertainty Guided AI Image Inpainting [11.216906046169683]
  SAGI-D is the largest and most diverse dataset of AI-generated inpaintings.<n>Our experiments show that semantic alignment significantly improves image quality and aesthetics.<n>Using SAGI-D for training several image forensic approaches increases in-domain detection performance on average by 37.4%.
  arXiv  Detail & Related papers  (2025-02-10T15:56:28Z)
• ProVision: Programmatically Scaling Vision-centric Instruction Data for Multimodal Language Models [103.25208095165486]
  Existing practices rely on powerful but costly large language models (LLMs) or multimodal language models (MLMs) to produce instruction data.<n>We present a programmatic approach that employs scene graphs as symbolic representations of images and human-written programs to systematically synthesize vision-centric instruction data.<n>Our approach ensures the interpretability and controllability of the data generation process and scales efficiently while maintaining factual accuracy.
  arXiv  Detail & Related papers  (2024-12-09T21:44:02Z)
• Multi-method Integration with Confidence-based Weighting for Zero-shot Image Classification [1.7265013728931]
  This paper introduces a novel framework for zero-shot learning (ZSL) to recognize new categories that are unseen during training. We propose three strategies to enhance the model's performance to handle ZSL.
  arXiv  Detail & Related papers  (2024-05-03T15:02:41Z)
• Learning Customized Visual Models with Retrieval-Augmented Knowledge [104.05456849611895]
  We propose REACT, a framework to acquire the relevant web knowledge to build customized visual models for target domains. We retrieve the most relevant image-text pairs from the web-scale database as external knowledge, and propose to customize the model by only training new modualized blocks while freezing all the original weights. The effectiveness of REACT is demonstrated via extensive experiments on classification, retrieval, detection and segmentation tasks, including zero, few, and full-shot settings.
  arXiv  Detail & Related papers  (2023-01-17T18:59:06Z)

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.