Gpt-image-1.5 Prompting Guide

1. Introduction

gpt-image-1.5 is our latest image generation model, designed for production-quality visuals and highly controllable creative workflows. It delivers major improvements in realism, accuracy, and editability, making it well-suited for both professional design tasks and iterative content creation. It delivers major improvements in realism, accuracy, and editability compared to the previous generation, and supports both high-quality rendering and low-latency use cases.

Key Capabilities include:

• High-fidelity photorealism with natural lighting, accurate materials, and rich color rendering
• Flexible quality–latency tradeoffs, allowing faster generation at lower settings while still exceeding the visual quality of prior-generation image models
• Robust facial and identity preservation for edits, character consistency, and multi-step workflows
• Reliable text rendering with crisp lettering, consistent layout, and strong contrast inside images
• Complex structured visuals, including infographics, diagrams, and multi-panel compositions
• Precise style control and style transfer with minimal prompting, supporting everything from branded design systems to fine-art styles
• Strong real-world knowledge and reasoning, enabling accurate depictions of objects, environments, and scenarios

This guide highlights prompting patterns, best practices, and example prompts drawn from real production use cases.

2. Prompting Fundamentals

• Structure + goal: Write prompts in a consistent order (background/scene → subject → key details → constraints) and include the intended use (ad, UI mock, infographic) to set the “mode” and level of polish. For complex requests, use short labeled segments or line breaks instead of one long paragraph.

• Specificity + quality cues: Be concrete about materials, shapes, textures, and the visual medium (photo, watercolor, 3D render), and add targeted “quality levers” only when needed (e.g., film grain, textured brushstrokes, macro detail). For photorealism, camera/composition terms (lens, aperture feel, lighting) often steer realism more reliably than generic “8K/ultra-detailed.”

• Latency vs fidelity: For latency-sensitive or high-volume use cases, start with setting quality="low" and evaluate whether it meets your visual requirements. In many cases, it provides sufficient fidelity with significantly faster generation.

• Composition: Specify framing and viewpoint (close-up, wide, top-down), perspective/angle (eye-level, low-angle), and lighting/mood (soft diffuse, golden hour, high-contrast) to control the shot. If layout matters, call out placement (e.g., “logo top-right,” “subject centered with negative space on left”).

• Constraints (what to change vs preserve): State exclusions and invariants explicitly (e.g., “no watermark,” “no extra text,” “no logos/trademarks,” “preserve identity/geometry/layout/brand elements”). For edits, use “change only X” + “keep everything else the same,” and repeat the preserve list on each iteration to reduce drift.

• Text in images: Put literal text in quotes or ALL CAPS and specify typography details (font style, size, color, placement) as constraints. For tricky words (brand names, uncommon spellings), spell them out letter-by-letter to improve character accuracy.

• Multi-image inputs: Reference each input by index and description (“Image 1: product photo… Image 2: style reference…”) and describe how they interact (“apply Image 2’s style to Image 1”). When compositing, be explicit about which elements move where (“put the bird from Image 1 on the elephant in Image 2”).

• Iterate instead of overloading: Start with a clean base prompt, then refine with small, single-change follow-ups (“make lighting warmer,” “remove the extra tree,” “restore the original background”). Use references like “same style as before” or “the subject” to leverage context, but re-specify critical details if they start to drift.

3. Setup

Run this once. It:

• creates the API client
• creates output_images/ in the images folder.
• adds a small helper to save base64 images

Put any reference images used for edits into input_images/ (or update the paths in the examples).

4. Use Cases — Generate (text → image)

4.1 Infographics

Use infographics to explain structured information for a specific audience: students, executives, customers, or the general public. Examples include explainers, posters, labeled diagrams, timelines, and “visual wiki” assets. For dense layouts or heavy in-image text, it's recommedned to set output generation quality to "high".

4.2 Translation in Images

Used for localizing existing designs (ads, UI screenshots, packaging, infographics) into another language without rebuilding the layout from scratch. The key is to preserve everything except the text—keep typography style, placement, spacing, and hierarchy consistent—while translating verbatim and accurately, with no extra words, no reflow unless necessary, and no unintended edits to logos, icons, or imagery.

Output Image:

4.3 Photorealistic Images that Feel “natural”

To get believable photorealism, prompt the model as if a real photo is being captured in the moment. Use photography language (lens, lighting, framing) and explicitly ask for real texture (pores, wrinkles, fabric wear, imperfections). Avoid words that imply studio polish or staging. When detail matters, set quality="high".

Output Image:

4.4 World knowledge

GPT-image-1.5 has built-in reasoning and strong world knowledge. For example, when asked to generate a scene set in Bethel, New York in August 1969, it can infer Woodstock and produce an accurate, context-appropriate image without being explicitly told about the event.

Output Image:

4.5 Logo Generation

Strong logo generation comes from clear brand constraints and simplicity. Describe the brand’s personality and use case, then ask for a clean, original mark with strong shape, balanced negative space, and scalability across sizes.

You can specify parameter "n" to denote the number of variations you would like to generate.

Output Images:

Option 1	Option 2	Option 3	Option 4

4.6 Story-to-Comic Strip

For story-to-comic generation, define the narrative as a sequence of clear visual beats, one per panel. Keep descriptions concrete and action-focused so the model can translate the story into readable, well-paced panels.

Output Image:

4.7 UI Mockups

UI mockups work best when you describe the product as if it already exists. Focus on layout, hierarchy, spacing, and real interface elements, and avoid concept art language so the result looks like a usable, shipped interface rather than a design sketch.

Output Image:

5. Use cases — Edit (text + image → image)

5.1 Style Transfer

Style transfer is useful when you want to keep the visual language of a reference image (palette, texture, brushwork, film grain, etc.) while changing the subject or scene. For best results, describe what must stay consistent (style cues) and what must change (new content), and add hard constraints like background, framing, and “no extra elements” to prevent drift.

Input Image:

Output Image:

5.2 Virtual Clothing Try-On

Virtual try-on is ideal for ecommerce previews where identity preservation is critical. The key is to explicitly lock the person (face, body shape, pose, hair, expression) and allow changes only to garments, then require realistic fit (draping, folds, occlusion) plus consistent lighting/shadows so the outfit looks naturally worn—not pasted on.

Input Images:

Full Body	Item 1
Item 2	Item 3

Output Image:

5.3 Drawing → Image (Rendering)

Sketch-to-render workflows are great for turning rough drawings into photorealistic concepts while keeping the original intent. Treat the prompt like a spec: preserve layout and perspective, then add realism by specifying plausible materials, lighting, and environment. Include “do not add new elements/text” to avoid creative reinterpretations.

Input Image:

Output Image:

5.4 Product Mockups (transparent background + label integrity)

Product extraction and mockup prep is commonly used for catalogs, marketplaces, and design systems. Success depends on edge quality (clean silhouette, no fringing/halos) and label integrity (text stays sharp and unchanged). If you want realism without re-styling, ask for only light polishing and optionally a subtle contact shadow that respects the alpha.

Input Image:

Output Image:

5.5 Marketing Creatives with Real Text In-Image

Marketing creatives with real in-image text are great for rapid ad concepting, but typography needs explicit constraints. Put the exact copy in quotes, demand verbatim rendering (no extra characters), and describe placement and font style. If text fidelity is imperfect, keep the prompt strict and iterate—small wording/layout tweaks usually improve legibility.

Input Image:

Output Image:

5.6 Lighting and Weather Transformation

Used to re-stage a photo for different moods, seasons, or time-of-day variants (e.g., sunny → overcast, daytime → dusk, clear → snowy) while keeping the scene composition intact. The key is to change only environmental conditions—lighting direction/quality, shadows, atmosphere, precipitation, and ground wetness—while preserving identity, geometry, camera angle, and object placement so it still reads as the same original photo.

Output Image:

5.7 Object Removal

Person-in-scene compositing is useful for storyboards, campaigns, and “what if” scenarios where facial/identity preservation matters. Anchor realism by specifying a grounded photographic look (natural lighting, believable detail, no cinematic grading), and lock what must not change about the subject. When available, higher input fidelity helps maintain likeness during larger scene edits.

5.8 Insert the Person Into a Scene

Person-in-scene compositing is useful for storyboards, campaigns, and “what if” scenarios where facial/identity preservation matters. Anchor realism by specifying a grounded photographic look (natural lighting, believable detail, no cinematic grading), and lock what must not change about the subject. When available, higher input fidelity helps maintain likeness during larger scene edits.

Output Image:

5.9 Multi-Image Referencing and Compositing

Used to combine elements from multiple inputs into a single, believable image—great for “insert this object/person into that scene” workflows without re-generating everything. The key is to clearly specify what to transplant (the dog from image 2), where it should go (right next to the woman in image 1), and what must remain unchanged (scene, background, framing), while matching lighting, perspective, scale, and shadows so the composite looks naturally captured in the original photo.

6. Additional High-Value Use Cases

6.1 Interior design “swap” (precision edits)

Used for visualizing furniture or decor changes in real spaces without re-rendering the entire scene. The goal is surgical realism: swap a single object while preserving camera angle, lighting, shadows, and surrounding context so the edit looks like a real photograph, not a redesign.

6.2 3D pop-up holiday card (product-style mock)

Ideal for seasonal marketing concepts and print previews. Emphasizes tactile realism—paper layers, fibers, folds, and soft studio lighting—so the result reads as a photographed physical product rather than a flat illustration.

Output Image:

6.3 Collectible Action Figure / Plush Keychain (merch concept)

Used for early merch ideation and pitch visuals. Focuses on premium product photography cues (materials, packaging, print clarity) while keeping designs original and non-infringing. Works well for testing multiple character or packaging variants quickly.

Output Image:

6.4 Children’s Book Art with Character Consistency (multi-image workflow)

Designed for multi-page illustration pipelines where character drift is unacceptable. A reusable “character anchor” ensures visual continuity across scenes, poses, and pages while allowing environmental and narrative variation.

1️⃣ Character Anchor — establish the reusable main character

Goal: Lock the character’s appearance, proportions, outfit, and tone.

Output Image:

2️⃣ Story continuation — reuse character, advance the narrative

Goal: Same character, new scene + action. Character appearance must remain unchanged.

Output Image:

Conclusion

In this notebook, we demonstrate how to use gpt-image-1.5 to build high-quality, controllable image generation and editing workflows that hold up in real production settings. The cookbook emphasizes prompt structure, explicit constraints, and small iterative changes as the primary tools for controlling realism, layout, text accuracy, and identity preservation. We cover both generation and editing patterns—ranging from infographics, photorealism, UI mockups, and logos to translation, style transfer, virtual try-on, compositing, and lighting changes. Throughout the examples, the cookbook reinforces the importance of clearly separating what should change from what must remain invariant, and of restating those invariants on every iteration to prevent drift. We also highlight how quality and input-fidelity settings enable deliberate tradeoffs between latency and visual precision depending on the use case. Together, these examples form a practical, repeatable playbook for deploying gpt-image-1.5 in production image workflows.