{"id":2321,"date":"2026-05-30T09:00:00","date_gmt":"2026-05-30T09:00:00","guid":{"rendered":"https:\/\/wiro.ai\/blog\/?p=2321"},"modified":"2026-09-27T22:23:01","modified_gmt":"2026-09-27T22:23:01","slug":"gpt-image-1-5-6-prompt-tests-for-text-and-edits","status":"publish","type":"post","link":"https:\/\/wiro.ai\/blog\/gpt-image-1-5-6-prompt-tests-for-text-and-edits\/","title":{"rendered":"GPT Image 1.5: 6 Prompt Tests for Text and Edits"},"content":{"rendered":"<p>GPT Image 1.5 was tested here for the jobs that make image generation useful in production: product photography, short readable text, packaging layouts, reflective materials, illustration style, and a constrained image edit. Each GPT Image 1.5 test used one output at 3:2, high quality, JPEG with compression 90, low moderation, and one sample. The edit used a supplied watch image and a direct instruction to preserve the product. The model accepts text prompts, optional source images and masks, 1:1, 3:2, or 2:3 output sizes, three quality settings, PNG\/JPEG\/WEBP output, up to 10 samples, and high or low input fidelity for edits.<\/p>\n<h2>Contents<\/h2>\n<ul>\n<li><a href=\"#setup\">Test setup and recorded timings<\/a><\/li>\n<li><a href=\"#results\">What the six outputs show<\/a><\/li>\n<li><a href=\"#choose\">When to choose GPT Image 1.5<\/a><\/li>\n<\/ul>\n<h2>Model and setup<\/h2>\n<p><a href=\"https:\/\/wiro.ai\/models\/openai\/gpt-image-1-5\">GPT Image 1.5 on Wiro<\/a> covers both text-to-image generation and image editing. The six prompts were deliberately specific. That makes the results more useful than a broad request for a pretty image: each one asks the model to bind materials, light, text, placement, or preservation rules to a visible outcome.<\/p>\n<table id=\"setup\">\n<thead>\n<tr>\n<th>Setting<\/th>\n<th>Value used<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Canvas<\/td>\n<td>3:2 (1536 x 1024)<\/td>\n<\/tr>\n<tr>\n<td>Quality<\/td>\n<td>High<\/td>\n<\/tr>\n<tr>\n<td>Format<\/td>\n<td>JPEG, compression 90<\/td>\n<\/tr>\n<tr>\n<td>Outputs per prompt<\/td>\n<td>1<\/td>\n<\/tr>\n<tr>\n<td>Moderation<\/td>\n<td>Low<\/td>\n<\/tr>\n<tr>\n<td>Edit fidelity<\/td>\n<td>High for the watch edit<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>The recorded completion times range from 42 to 55 seconds. These are observations from these six Wiro runs, not a service guarantee. No per-output price was recorded with the original runs, and the model documentation reviewed for this update does not state a Wiro per-image price. Rather than infer a cost from another provider or a different setting, the table marks it as unavailable.<\/p>\n<h2 id=\"results\">What the six GPT Image 1.5 tests show<\/h2>\n<h3>1. Macro product shot: materials and lighting<\/h3>\n<p>The coffee-mug prompt asks for wet slate, an espresso drip, small ripples, a left softbox, a right rim light, sharp specular highlights, and an 85mm look. The output completed in 51 seconds. It holds the studio-light direction together: the mug remains matte while the puddle and wet slate carry the strongest highlights. The useful result is not just a dramatic coffee photo. It shows that GPT Image 1.5 can separate materials when the prompt names the lighting role and surface behavior.<\/p>\n<figure><img loading=\"lazy\" decoding=\"async\" width=\"1536\" height=\"1024\" class=\"wp-image-2314\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-1.jpg\" alt=\"GPT Image 1.5 macro product photo of a matte black coffee mug on wet slate\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-1.jpg 1536w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-1-510x340.jpg 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-1-900x600.jpg 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-1-768x512.jpg 768w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-1-1200x800.jpg 1200w\" sizes=\"auto, (max-width: 1536px) 100vw, 1536px\" \/><figcaption>Prompt: Macro product photo of a matte black ceramic coffee mug on wet black slate. One espresso drip falls into a shallow puddle and makes small ripples. Softbox key light from the left, rim light from the right, sharp specular highlights, realistic reflections, shallow depth of field, 85mm lens look, high detail.<\/figcaption><\/figure>\n<h3>2. Chalkboard menu: short text under texture<\/h3>\n<p>The menu test asks for four exact short strings: DRIP COFFEE 3, OAT LATTE 5, CROISSANT 4, and OPEN 7AM. It returned in 45 seconds. The lettering is readable at article size and sits convincingly on a chalkboard in a real-looking cafe scene. That is the right scope for the result: short lines, strong contrast, and a loose handwritten style. It should not be treated as final artwork for a dense menu, legal copy, or a price list that cannot tolerate a single character error. Check every character before shipping.<\/p>\n<figure><img loading=\"lazy\" decoding=\"async\" width=\"1536\" height=\"1024\" class=\"wp-image-2315\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-2.jpg\" alt=\"GPT Image 1.5 coffee shop chalkboard menu text rendering test\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-2.jpg 1536w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-2-510x340.jpg 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-2-900x600.jpg 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-2-768x512.jpg 768w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-2-1200x800.jpg 1200w\" sizes=\"auto, (max-width: 1536px) 100vw, 1536px\" \/><figcaption>Prompt: Photo of a small coffee shop chalkboard menu on a brick wall. The chalk text must be clear and spelled exactly as written. Text lines: DRIP COFFEE 3 ; OAT LATTE 5 ; CROISSANT 4. Add a small line at the bottom that says OPEN 7AM. Handwritten chalk style, warm indoor lighting, shallow depth of field.<\/figcaption><\/figure>\n<h3>3. Packaging mockup: text and straight edges<\/h3>\n<p>The protein-bar wrapper puts three pieces of copy on a small surface: MOUNTAIN FUEL, Cocoa + Sea Salt, and 12g protein. It completed in 45 seconds. The output reads as a plausible studio mockup and keeps the wrapper edges straighter than a busy collage prompt usually would. The lesson is practical. Ask for a limited hierarchy, give the exact strings, and leave generous empty space. For regulated packaging or final brand files, use this as a concept image and rebuild approved copy in a design tool.<\/p>\n<figure><img loading=\"lazy\" decoding=\"async\" width=\"1536\" height=\"1024\" class=\"wp-image-2316\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-3.jpg\" alt=\"GPT Image 1.5 protein bar packaging mockup with text layout\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-3.jpg 1536w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-3-510x340.jpg 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-3-900x600.jpg 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-3-768x512.jpg 768w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-3-1200x800.jpg 1200w\" sizes=\"auto, (max-width: 1536px) 100vw, 1536px\" \/><figcaption>Prompt: Studio mockup of a wrapped protein bar on a light gray surface. Minimal shadows. The wrapper design must have clear text. Large brand text: MOUNTAIN FUEL. Subtitle text: Cocoa + Sea Salt. Small line: 12g protein. Modern sans serif typography, clean layout, premium look, high detail.<\/figcaption><\/figure>\n<h3>4. Glass and mirror: reflection consistency<\/h3>\n<p>The iced-tea scene combines a transparent glass, condensation, lemon, a round mirror, afternoon sunlight, table reflections, and a blurred street. It was the slowest generation at 55 seconds. The output keeps a coherent light direction and gives the glass, mirror, and wood distinct highlight behavior. It is a good prompt pattern for lifestyle product concepts. It is less suitable when a campaign needs exact product geometry, a specific label, or physically measured reflections.<\/p>\n<figure><img loading=\"lazy\" decoding=\"async\" width=\"1536\" height=\"1024\" class=\"wp-image-2317\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-4.jpg\" alt=\"GPT Image 1.5 iced tea glass and mirror reflection test\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-4.jpg 1536w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-4-510x340.jpg 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-4-900x600.jpg 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-4-768x512.jpg 768w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-4-1200x800.jpg 1200w\" sizes=\"auto, (max-width: 1536px) 100vw, 1536px\" \/><figcaption>Prompt: Photorealistic scene: a tall glass of iced tea with lemon on a wooden table next to a small round mirror. Afternoon sun comes through a window and creates strong reflections on the glass, table, and mirror. Condensation droplets on the glass, sharp highlights, soft background bokeh with a city street outside the window, realistic depth of field, high detail.<\/figcaption><\/figure>\n<h3>5. Children&#8217;s illustration: style control<\/h3>\n<p>The raccoon astronaut test asks for clean ink lines, watercolor fills, warm light, readable shapes, and a simple background. It completed in 54 seconds. The output shows why style instructions work best when they describe both the mark-making and the scene complexity. The restrained background gives the character and pancakes room to read. This is a solid choice for a first visual direction, story pitch, or social graphic. It still needs a human art pass if a series must maintain exact characters across many images.<\/p>\n<figure><img loading=\"lazy\" decoding=\"async\" width=\"1536\" height=\"1024\" class=\"wp-image-2318\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-5.jpg\" alt=\"GPT Image 1.5 watercolor children's book raccoon astronaut illustration\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-5.jpg 1536w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-5-510x340.jpg 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-5-900x600.jpg 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-5-768x512.jpg 768w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-5-1200x800.jpg 1200w\" sizes=\"auto, (max-width: 1536px) 100vw, 1536px\" \/><figcaption>Prompt: Children book illustration, clean ink lines and soft watercolor fills. A raccoon in a small orange astronaut suit floats in a cozy space station kitchen while making pancakes. Warm light, cute details, readable shapes, simple background, high quality illustration.<\/figcaption><\/figure>\n<h3>6. Watch edit: preserve the subject, replace the scene<\/h3>\n<p>The final test starts with a watch photo. The instruction changes only the background, removes water droplets, adds a soft shadow, and explicitly protects the watch shape, text, hands, and bezel. It finished in 42 seconds, the fastest result in the set. The edited output makes the watch presentation cleaner without turning it into a different object. That is the strongest use case in this group: give the model a clear source image, say what must remain untouched, then list the limited changes.<\/p>\n<table>\n<tbody>\n<tr>\n<td>\n<figure><img loading=\"lazy\" decoding=\"async\" width=\"1376\" height=\"768\" class=\"wp-image-2319\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input.jpg\" alt=\"Original watch product photo used for the GPT Image 1.5 edit\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input.jpg 1376w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input-510x285.jpg 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input-900x502.jpg 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input-768x429.jpg 768w\" sizes=\"auto, (max-width: 1376px) 100vw, 1376px\" \/><figcaption>Input image.<\/figcaption><\/figure>\n<\/td>\n<td>\n<figure><img loading=\"lazy\" decoding=\"async\" width=\"1536\" height=\"1024\" class=\"wp-image-2320\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-output.jpg\" alt=\"GPT Image 1.5 edited watch product photo on a white studio background\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-output.jpg 1536w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-output-510x340.jpg 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-output-900x600.jpg 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-output-768x512.jpg 768w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-output-1200x800.jpg 1200w\" sizes=\"auto, (max-width: 1536px) 100vw, 1536px\" \/><figcaption>Prompt: Keep the watch exactly the same. Change the background to a clean white seamless studio backdrop. Remove all water droplets. Add a soft realistic shadow under the watch. Do not change the watch shape, text, hands, or bezel. Keep a premium product photo look.<\/figcaption><\/figure>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>Timing and cost record<\/h2>\n<table>\n<thead>\n<tr>\n<th>Test<\/th>\n<th>What it checks<\/th>\n<th>Recorded time<\/th>\n<th>Recorded cost<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>1<\/td>\n<td>Product lighting and wet materials<\/td>\n<td>51 seconds<\/td>\n<td>Not recorded<\/td>\n<\/tr>\n<tr>\n<td>2<\/td>\n<td>Short chalkboard text<\/td>\n<td>45 seconds<\/td>\n<td>Not recorded<\/td>\n<\/tr>\n<tr>\n<td>3<\/td>\n<td>Packaging hierarchy and text<\/td>\n<td>45 seconds<\/td>\n<td>Not recorded<\/td>\n<\/tr>\n<tr>\n<td>4<\/td>\n<td>Glass, mirror, and reflections<\/td>\n<td>55 seconds<\/td>\n<td>Not recorded<\/td>\n<\/tr>\n<tr>\n<td>5<\/td>\n<td>Illustration style<\/td>\n<td>54 seconds<\/td>\n<td>Not recorded<\/td>\n<\/tr>\n<tr>\n<td>6<\/td>\n<td>Constrained product edit<\/td>\n<td>42 seconds<\/td>\n<td>Not recorded<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2 id=\"choose\">When to choose GPT Image 1.5<\/h2>\n<p>Choose GPT Image 1.5 when the brief benefits from natural-language control and the output can be reviewed before publication. It fits product concepts, promotional scenes, short display text, early packaging directions, and image edits where the subject must survive a background change. Use high quality when finish matters and leave time for a roughly one-minute result. Use a source image plus explicit preservation rules for edits. Keep exact text short, high contrast, and separate from busy imagery.<\/p>\n<p>Pick another workflow when pixel-perfect typography, approved product dimensions, or repeatable character identity is non-negotiable. Those cases need a design system, source assets, or manual compositing after generation. For more Wiro tests, see <a href=\"https:\/\/wiro.ai\/blog\/gpt-image-1-5-5-prompts-for-clean-layouts\/\">GPT Image 1.5: 5 Prompts for Clean Layouts<\/a>, <a href=\"https:\/\/wiro.ai\/blog\/8-prompts-for-product-photography-with-gpt-image-1-5\/\">8 Prompts for Product Photography with GPT Image 1.5<\/a>, and <a href=\"https:\/\/wiro.ai\/blog\/firered-image-edit-vs-seedream-v5-lite\/\">FireRed Image Edit vs Seedream V5 Lite<\/a>.<\/p>\n<h2>Sources<\/h2>\n<p>OpenAI describes image generation and editing controls in its <a href=\"https:\/\/platform.openai.com\/docs\/guides\/image-generation\" target=\"_blank\" rel=\"noopener\">official image generation documentation<\/a>. Its <a href=\"https:\/\/openai.com\/index\/introducing-4o-image-generation\/\" target=\"_blank\" rel=\"noopener\">image generation announcement<\/a> also discusses text rendering, instruction following, multi-turn work, and known limitations.<\/p>\n<h2>Run GPT Image 1.5<\/h2>\n<p><a href=\"https:\/\/wiro.ai\/models\/openai\/gpt-image-1-5\">Run GPT Image 1.5 on Wiro<\/a> for a text-to-image prompt or a source-image edit.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>GPT Image 1.5 was tested here for the jobs that make image generation useful in production: product photography, short readable text, packaging&hellip;<\/p>\n","protected":false},"author":4,"featured_media":2313,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[52],"tags":[61,60,92,81],"class_list":["post-2321","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-model-reviews","tag-image-editing","tag-image-to-image","tag-openai","tag-text-to-image"],"_links":{"self":[{"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/posts\/2321","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/comments?post=2321"}],"version-history":[{"count":2,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/posts\/2321\/revisions"}],"predecessor-version":[{"id":4309,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/posts\/2321\/revisions\/4309"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/media\/2313"}],"wp:attachment":[{"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/media?parent=2321"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/categories?post=2321"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/tags?post=2321"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}