{"id":2353,"date":"2026-06-02T09:00:00","date_gmt":"2026-06-02T09:00:00","guid":{"rendered":"https:\/\/wiro.ai\/blog\/?p=2353"},"modified":"2026-09-27T23:28:34","modified_gmt":"2026-09-27T23:28:34","slug":"gpt-image-1-5-text-edits-in-6-prompt-tests","status":"publish","type":"post","link":"https:\/\/wiro.ai\/blog\/gpt-image-1-5-text-edits-in-6-prompt-tests\/","title":{"rendered":"GPT Image 1.5: Text + Edits in 6 Prompt Tests"},"content":{"rendered":"<h2>Model link<\/h2>\n<p><a href=\"https:\/\/wiro.ai\/models\/openai\/gpt-image-1-5\">openai\/gpt-image-1-5 on Wiro<\/a><\/p>\n<h2>What GPT Image 1.5 does<\/h2>\n<p>GPT Image 1.5 generates images from text prompts, and it can also edit an existing image when a reference image gets provided. The tests below focus on two practical things: clean text rendering (labels, posters, signs) and controlled edits (keeping the subject while changing clothing or the scene).<\/p>\n<p>OpenAI&#8217;s <a href=\"https:\/\/developers.openai.com\/api\/docs\/models\/gpt-image-1.5\" target=\"_blank\" rel=\"noopener\">official model documentation<\/a> lists text and image inputs, which matches the generation and edit workflows tested here.<\/p>\n<h2>Test setup<\/h2>\n<table>\n<tr>\n<td>Output size<\/td>\n<td>3:2 (1536&#215;1024)<\/td>\n<\/tr>\n<tr>\n<td>Quality<\/td>\n<td>Medium<\/td>\n<\/tr>\n<tr>\n<td>Format<\/td>\n<td>WEBP (compression 90)<\/td>\n<\/tr>\n<tr>\n<td>Images 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 setting<\/td>\n<td>Input fidelity: High<\/td>\n<\/tr>\n<tr>\n<td>Wiro run cost used here<\/td>\n<td>$0.05 per 3:2 image at medium quality<\/td>\n<\/tr>\n<\/table>\n<p>OpenAI&#8217;s <a href=\"https:\/\/developers.openai.com\/cookbook\/examples\/multimodal\/image-gen-1.5-prompting_guide\" target=\"_blank\" rel=\"noopener\">GPT Image 1.5 prompting guide<\/a> also covers controlled creative workflows, including text rendering and edits.<\/p>\n<h2>6 prompt tests (with real outputs)<\/h2>\n<h3>1) Clean product label text<\/h3>\n<p><strong>Goal:<\/strong> Check if short typography stays sharp and centered on packaging.<\/p>\n<p><strong>Prompt:<\/strong> Studio product photo of a cobalt blue energy drink can on a white seamless background. Clean label with the exact text PULSE on the top line and CITRUS ZING on the second line. Sans serif, sharp edges, centered. Softbox reflections. 85mm lens, high detail.<\/p>\n<figure>\n  <img loading=\"lazy\" decoding=\"async\" width=\"1536\" height=\"1024\" class=\"wp-image-2345\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-1.webp\" alt=\"Blue energy drink can on a white background with the label text PULSE and CITRUS ZING\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-1.webp 1536w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-1-510x340.webp 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-1-900x600.webp 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-1-768x512.webp 768w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-1-1200x800.webp 1200w\" sizes=\"auto, (max-width: 1536px) 100vw, 1536px\" \/><figcaption>Prompt: Studio product photo of a cobalt blue energy drink can on a white seamless background. Clean label with the exact text PULSE on the top line and CITRUS ZING on the second line. Sans serif, sharp edges, centered. Softbox reflections. 85mm lens, high detail.<\/figcaption><\/figure>\n<p><strong>Result:<\/strong> The label text reads exactly as requested, and the shot looks like a clean catalog photo.<\/p>\n<h3>2) Motion + detail in food photography<\/h3>\n<p><strong>Goal:<\/strong> See how it handles fine liquid textures and depth of field.<\/p>\n<p><strong>Prompt:<\/strong> Ultra detailed macro photo of espresso being poured into cold milk in a clear glass on a rustic wooden table. Realistic swirling gradients and micro foam. Morning window light from the left. Shallow depth of field, sharp focus on the swirl, soft bokeh.<\/p>\n<figure>\n  <img loading=\"lazy\" decoding=\"async\" width=\"1536\" height=\"1024\" class=\"wp-image-2346\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-2.webp\" alt=\"Macro photo of coffee being poured into milk creating swirling patterns in a glass\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-2.webp 1536w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-2-510x340.webp 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-2-900x600.webp 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-2-768x512.webp 768w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-2-1200x800.webp 1200w\" sizes=\"auto, (max-width: 1536px) 100vw, 1536px\" \/><figcaption>Prompt: Ultra detailed macro photo of espresso being poured into cold milk in a clear glass on a rustic wooden table. Realistic swirling gradients and micro foam. Morning window light from the left. Shallow depth of field, sharp focus on the swirl, soft bokeh.<\/figcaption><\/figure>\n<p><strong>Result:<\/strong> The swirl and condensation details look natural, with a believable shallow depth of field.<\/p>\n<h3>3) Poster layout with two lines of text<\/h3>\n<p><strong>Goal:<\/strong> Stress-test big headline text plus a smaller tagline.<\/p>\n<p><strong>Prompt:<\/strong> Minimalist movie poster. Background: foggy pine forest at dawn, cool tones, subtle paper texture. Big title text reads MIRAGE. Small tagline below reads CLEAN EDITS FAST. Centered layout, lots of negative space, print ready, sharp edges.<\/p>\n<figure>\n  <img loading=\"lazy\" decoding=\"async\" width=\"1536\" height=\"1024\" class=\"wp-image-2347\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-3.webp\" alt=\"Minimal poster with foggy forest background and the text MIRAGE and CLEAN EDITS FAST\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-3.webp 1536w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-3-510x340.webp 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-3-900x600.webp 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-3-768x512.webp 768w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-3-1200x800.webp 1200w\" sizes=\"auto, (max-width: 1536px) 100vw, 1536px\" \/><figcaption>Prompt: Minimalist movie poster. Background: foggy pine forest at dawn, cool tones, subtle paper texture. Big title text reads MIRAGE. Small tagline below reads CLEAN EDITS FAST. Centered layout, lots of negative space, print ready, sharp edges.<\/figcaption><\/figure>\n<p><strong>Result:<\/strong> Both text lines come out clean and readable, and the negative-space layout stays intact.<\/p>\n<h3>4) Neon sign text inside a complex scene<\/h3>\n<p><strong>Goal:<\/strong> Check typography inside a busy, cinematic image.<\/p>\n<p><strong>Prompt:<\/strong> Cinematic night street in Tokyo in the rain. Wet asphalt reflections, shallow depth of field, neon sign reads LANTERN BAR in clear block letters. People with umbrellas in the background, bokeh lights, 35mm photo look, high detail.<\/p>\n<figure>\n  <img loading=\"lazy\" decoding=\"async\" width=\"1536\" height=\"1024\" class=\"wp-image-2348\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-4.webp\" alt=\"Rainy neon-lit street scene with a sign that reads LANTERN BAR\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-4.webp 1536w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-4-510x340.webp 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-4-900x600.webp 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-4-768x512.webp 768w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-4-1200x800.webp 1200w\" sizes=\"auto, (max-width: 1536px) 100vw, 1536px\" \/><figcaption>Prompt: Cinematic night street in Tokyo in the rain. Wet asphalt reflections, shallow depth of field, neon sign reads LANTERN BAR in clear block letters. People with umbrellas in the background, bokeh lights, 35mm photo look, high detail.<\/figcaption><\/figure>\n<p><strong>Result:<\/strong> The sign reads exactly &#8220;LANTERN BAR&#8221; and the scene keeps a convincing film look.<\/p>\n<h3>5) Outfit swap edit (keep the person and background)<\/h3>\n<p><strong>Goal:<\/strong> Edit clothing while keeping identity, pose, and location consistent.<\/p>\n<p><strong>Input image:<\/strong><\/p>\n<figure>\n  <img loading=\"lazy\" decoding=\"async\" width=\"1376\" height=\"768\" class=\"wp-image-2351\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input-1.jpg\" alt=\"Man standing outdoors in a park path wearing casual clothing\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input-1.jpg 1376w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input-1-510x285.jpg 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input-1-900x502.jpg 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input-1-768x429.jpg 768w\" sizes=\"auto, (max-width: 1376px) 100vw, 1376px\" \/><figcaption>Input image used as reference for the edit.<\/figcaption><\/figure>\n<p><strong>Prompt:<\/strong> Replace only the clothing with a tailored navy blue suit, white dress shirt, red tie, and brown leather dress shoes. Do not change the face, hair, skin tone, body shape, pose, background, lighting, or camera angle. Keep everything else identical.<\/p>\n<figure>\n  <img loading=\"lazy\" decoding=\"async\" width=\"1536\" height=\"1024\" class=\"wp-image-2349\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-5.webp\" alt=\"Man in the same outdoor scene now wearing a navy suit and red tie\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-5.webp 1536w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-5-510x340.webp 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-5-900x600.webp 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-5-768x512.webp 768w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-5-1200x800.webp 1200w\" sizes=\"auto, (max-width: 1536px) 100vw, 1536px\" \/><figcaption>Prompt: Replace only the clothing with a tailored navy blue suit, white dress shirt, red tie, and brown leather dress shoes. Do not change the face, hair, skin tone, body shape, pose, background, lighting, or camera angle. Keep everything else identical.<\/figcaption><\/figure>\n<p><strong>Result:<\/strong> The outfit changes while the background and the subject stay consistent, which makes this useful for quick wardrobe variations.<\/p>\n<h3>6) Product photo edit (change surface + mood)<\/h3>\n<p><strong>Goal:<\/strong> Keep the product, change the scene styling.<\/p>\n<p><strong>Input image:<\/strong><\/p>\n<figure>\n  <img loading=\"lazy\" decoding=\"async\" width=\"1376\" height=\"768\" class=\"wp-image-2352\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input-2.jpg\" alt=\"Stainless steel wristwatch on a white background\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input-2.jpg 1376w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input-2-510x285.jpg 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input-2-900x502.jpg 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-edit-input-2-768x429.jpg 768w\" sizes=\"auto, (max-width: 1376px) 100vw, 1376px\" \/><figcaption>Input image used as reference for the edit.<\/figcaption><\/figure>\n<p><strong>Prompt:<\/strong> Keep the watch exactly the same. Place it on a dark slate surface with realistic water droplets around it. Add dramatic side lighting and soft shadow under the watch. Luxury product photography look. Do not change the watch shape, dial text, or hands.<\/p>\n<figure>\n  <img loading=\"lazy\" decoding=\"async\" width=\"1536\" height=\"1024\" class=\"wp-image-2350\" src=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-6.webp\" alt=\"Wristwatch on a dark slate surface with water droplets and dramatic lighting\" srcset=\"https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-6.webp 1536w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-6-510x340.webp 510w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-6-900x600.webp 900w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-6-768x512.webp 768w, https:\/\/wiro.ai\/blog\/wp-content\/uploads\/2026\/04\/gpt-image-1-5-test-6-1200x800.webp 1200w\" sizes=\"auto, (max-width: 1536px) 100vw, 1536px\" \/><figcaption>Prompt: Keep the watch exactly the same. Place it on a dark slate surface with realistic water droplets around it. Add dramatic side lighting and soft shadow under the watch. Luxury product photography look. Do not change the watch shape, dial text, or hands.<\/figcaption><\/figure>\n<p><strong>Result:<\/strong> The watch stays readable and consistent while the background turns into a moodier product scene.<\/p>\n<h2>Quick takeaways<\/h2>\n<ul>\n<li>Short, high-contrast text (labels, posters, neon signs) comes out clean in these tests.<\/li>\n<li>Edits work best when the prompt clearly lists what must NOT change.<\/li>\n<li>For product edits, specify the surface, lighting direction, and shadow behavior to avoid &#8220;floating&#8221; objects.<\/li>\n<\/ul>\n<h2>Try it<\/h2>\n<p>Run GPT Image 1.5 here: <a href=\"https:\/\/wiro.ai\/models\/openai\/gpt-image-1-5\">openai\/gpt-image-1-5<\/a><\/p>\n<p>If the goal is fast marketing variations, start from a strong base image, then request one change at a time (outfit, background, lighting) while explicitly locking the rest.<\/p>\n<p>For related GPT Image 1.5 tests, see <a href=\"https:\/\/wiro.ai\/blog\/gpt-image-1-5-5-prompts-for-clean-layouts\/\">GPT Image 1.5 for Clean Layouts<\/a>, <a href=\"https:\/\/wiro.ai\/blog\/8-prompts-for-product-photography-with-gpt-image-1-5\/\">product photography prompts with GPT Image 1.5<\/a>, and <a href=\"https:\/\/wiro.ai\/blog\/seedream-v5-lite-image-editing-tests\/\">image editing tests<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Model link openai\/gpt-image-1-5 on Wiro What GPT Image 1.5 does GPT Image 1.5 generates images from text prompts, and it can also&hellip;<\/p>\n","protected":false},"author":4,"featured_media":2344,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[52],"tags":[200,61,92,81],"class_list":["post-2353","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-model-reviews","tag-gpt-image-1-5","tag-image-editing","tag-openai","tag-text-to-image"],"_links":{"self":[{"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/posts\/2353","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=2353"}],"version-history":[{"count":2,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/posts\/2353\/revisions"}],"predecessor-version":[{"id":4347,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/posts\/2353\/revisions\/4347"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/media\/2344"}],"wp:attachment":[{"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/media?parent=2353"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/categories?post=2353"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wiro.ai\/blog\/wp-json\/wp\/v2\/tags?post=2353"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}