1# Image prompting
2
3> For the complete documentation index, see [llms.txt](/llms.txt). Markdown versions of documentation pages are available by appending `.md` to the page URL.
4
5<header className="not-prose mb-8">
6 <h2
7 id="gpt-image-2.5-guide"
8 className="m-0 text-3xl font-semibold text-default"
9 >
10 {"GPT Image 2.5 prompting guide"}
11 </h2>
12
13
14 Choose a model, write effective prompts, and preserve details across
15 edits.
16
17
18 </header>
19
20
21## Overview
22
23Start with the image you need, then describe the subject, composition, style, and constraints. For edits, identify what should change and what must stay the same. Refine one thing at a time and inspect the result.
24
25GPT Image 2.5 includes two model choices. GPT Image 2.5 Flare is the small model, optimized for speed, with image quality comparable to GPT Image 2. GPT Image 2.5 Sunburst is the base model, optimized for quality, with higher image quality than GPT Image 2. Both models offer improvements in precise editing and subject preservation.
26
27For API setup and request examples, see the [image generation guide](https://developers.openai.com/api/docs/guides/image-generation).
28
29## Choose a model
30
31For a new workflow, start with GPT Image 2.5 Flare when speed is the priority, or GPT Image 2.5 Sunburst when demanding quality requirements are the priority. Once the output meets your requirements, look for opportunities to reduce latency.
32
33For migrating from a current image model, use your current image quality as the starting point. Both models support image generation, editing, and transparent backgrounds.
34
35| Your current workflow | Start by testing |
36| ----------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------- |
37| An existing, validated GPT Image 2 workflow already meets your quality requirements | GPT Image 2.5 Flare. Check whether you can retain acceptable quality while reducing latency. |
38| A complex use case where GPT Image 2 does not meet your quality requirements | GPT Image 2.5 Sunburst. First establish that it delivers the quality you need. |
39
40If GPT Image 2.5 Sunburst meets your quality requirements, then test GPT Image 2.5 Flare with the same prompts and inputs. Switch to GPT Image 2.5 Flare if it also meets those requirements and improves latency. Keep GPT Image 2.5 Sunburst when its quality advantage is necessary for your workflow.
41
42Measure response time and quality on your own workload. Results depend on your prompts, reference images, output dimensions, and quality settings; a speed improvement on one workload doesn't establish a fixed improvement on another.
43
44## Model parameters
45
46Set API parameters separately from the prompt.
47
48| Parameter | GPT Image 2.5 settings |
49| ------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
50| `model` | `gpt-image-2.5-flare` (small model) or `gpt-image-2.5-sunburst` (base model) |
51| `quality` | `auto` (default), `low`, `medium`, `high`, `xhigh`, or `max` |
52| `size` | `auto` or a custom resolution. Common sizes: `1024x1024` (square), `1536x1024` (landscape), `1024x1536` (portrait), `2048x2048` (2K square), `2048x1152` (2K landscape), `3840x2160` (4K landscape), and `2160x3840` (4K portrait). |
53| `background` | `auto`, `opaque`, or `transparent` |
54
55For a custom resolution, use `WIDTHxHEIGHT` and follow these constraints:
56
57- Each edge must be no more than 3,840 pixels.
58- Both edges must be multiples of 16 pixels.
59- The ratio of the longer edge to the shorter edge must not exceed 3:1.
60- The total pixel count must be between 655,360 and 8,294,400.
61
62Outputs with more than 3,686,400 total pixels (`2560x1440`) are experimental.
63
64Choose the model using the workflow above before tuning `quality`. For the first comparison, keep an explicitly selected quality setting unchanged when both models support it, along with the prompt, reference images, and output dimensions. The same quality label does not imply the same image quality or response time across models.
65
66If the output falls short, test a higher quality setting. Once it meets your requirements, test lower settings to see whether they preserve acceptable quality while reducing latency. Use `xhigh` or `max` only when they improve an unmet quality requirement within your latency budget. A higher setting doesn't guarantee a better result for every prompt.
67
68For transparent assets, explicitly request `background="transparent"` and use PNG or WebP. Check the decoded image's alpha channel, including hair, glass, shadows, and object edges. Use `output_compression` only for JPEG or WebP output, not PNG.
69
70## Migrate an existing workflow
71
721. **Save a baseline.** Collect representative production prompts and reference images, including difficult edits, exact text, faces, product geometry, and transparent assets. Record the current model, request settings, and results.
732. **Choose the first candidate.** If GPT Image 2 already meets your quality requirements, start with GPT Image 2.5 Flare and test for a latency improvement. If GPT Image 2 falls short on a complex use case, start with GPT Image 2.5 Sunburst and first establish that it meets your quality requirements. Keep the prompt, references, dimensions, and output format unchanged for the first comparison.
743. **Check the complete result.** Compare instruction following, identity and product preservation, text accuracy, unwanted changes, and transparency. Repeat requests to measure consistency. For editing workflows, test the complete sequence of edits as well as individual steps.
754. **Test for a latency gain after quality passes.** If you started with GPT Image 2.5 Sunburst and it meets your quality requirements, evaluate GPT Image 2.5 Flare against the same requirements. Switch only if the quality remains acceptable and latency improves; otherwise, keep GPT Image 2.5 Sunburst.
765. **Tune one setting at a time.** Compare quality levels before rewriting the prompt. Measure typical and slow responses, failures, retries, and cost per accepted image. Confirm current pricing rather than assuming the faster model costs less.
776. **Roll out by workflow.** Once the released model passes your acceptance criteria, move a small share of traffic, monitor the same measures, and expand gradually. Keep the previous model available for rollback while it remains supported.
78
79When migrating from GPT Image 1 or 1.5, use the reference tabs to check parameter differences and shutdown dates. Test the candidate model's supported request settings rather than copying older settings unchanged. For GPT Image 2, keep your existing resolution and transparency requirements in the comparison.
80
81Repeated edits can still change details you intended to preserve. Restate those constraints and inspect each result. If a region must remain pixel-identical, composite the approved edit into the original image instead of relying on prompting alone.
82
83## Prompting fundamentals
84
851. **Define the result.** Name the subject and intended use, such as a product photograph, advertisement, or diagram. Specify the composition, aspect ratio, and important placement constraints. For complex requests, organize the prompt as scene, subject, details, and constraints, using labeled sections.
862. **Choose a maintainable format.** Short prompts, descriptive paragraphs, JSON-like structures, instructions, and tags can all express the same intent. Choose the format that makes the requirements easiest to read and update rather than relying on special syntax.
873. **Describe visible details.** Name materials, lighting, colors, and the visual medium. Request “photorealistic” or “real photograph” explicitly when that is the goal, and describe framing and texture. Treat camera specifications as cues for appearance, not a guarantee of exact physical simulation. For wide, cinematic, low-light, rainy, or neon scenes, specify scale, atmosphere, and color instead of relying on mood words alone.
884. **Specify people and actions.** Describe body framing, relative scale, gaze, and interaction with objects. Instructions such as “full body visible, feet included,” “looking down at the open book,” or “hands naturally gripping the handlebars” make the intended pose and action clearer.
895. **Specify exact text.** Put required wording in quotes and describe its position and typography. Spell unusual words or brand names letter by letter when needed. Ask for no extra text, then check spelling and legibility in the output. Compare medium or high quality for small text, dense information, or multiple fonts.
906. **Separate changes from constraints.** For edits, say “change only X” and list the details to preserve, such as identity, geometry, layout, lighting, or labels. State exclusions such as unwanted text, logos, or watermarks. For precise local edits, also identify saturation, contrast, arrows, camera angle, and surrounding objects that must remain unchanged.
917. **Assign roles to references.** Identify each input by number and purpose: subject, style, clothing, or background. Explain how the inputs should combine and which elements should move where.
928. **Iterate deliberately.** Pass the previous output as the next edit input, request one change, and repeat the details to preserve. References such as “same style as before” can carry context, but restate critical constraints if the result drifts. Compare results before adding more instructions.
93
94The examples below each demonstrate a different technique. Keep their prompts as starting points and adapt them to your own images and requirements.
95
96## Generate images
97
98### Control style and lighting
99
100Describe a photograph through its subject, framing, light, and texture. This example specifies a candid composition and explicitly excludes heavy retouching.
101
102Generation settings: `size="1024x1536"`, `quality="medium"`.
103
104```text
105Create a photorealistic candid photograph of an elderly sailor standing on a small fishing boat.
106He has weathered skin with visible wrinkles, pores, and sun texture, and a few faded traditional sailor tattoos on his arms.
107He is calmly adjusting a net while his dog sits nearby on the deck. Shot like a 35mm film photograph, medium close-up at eye level, using a 50mm lens.
108Soft coastal daylight, shallow depth of field, subtle film grain, natural color balance.
109The image should feel honest and unposed, with real skin texture, worn materials, and everyday detail. No glamorization, no heavy retouching.
110```
111
112Example outputs:
113
114
115
116 <figure className="m-0 min-w-0">
117 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
118 GPT Image 2.5 Flare
119 </figcaption>
120
121
122
123
124
125 </figure>
126 <figure className="m-0 min-w-0">
127 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
128 GPT Image 2.5 Sunburst
129 </figcaption>
130
131
132
133
134
135 </figure>
136
137
138
139### Explain a process visually
140
141Name the process, audience, and information the image should communicate. For diagrams and information graphics, verify labels and factual relationships as well as appearance.
142
143Generation settings: `size="1024x1536"`, `quality="medium"`.
144
145```text
146Create a detailed Infographic of the functioning and flow of an automatic coffee machine like a Jura.
147From bean basket, to grinding, to scale, water tank, boiler, etc.
148I'd like to understand technically and visually the flow.
149```
150
151Example outputs:
152
153
154
155 <figure className="m-0 min-w-0">
156 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
157 GPT Image 2.5 Flare
158 </figcaption>
159
160
161
162
163
164 </figure>
165 <figure className="m-0 min-w-0">
166 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
167 GPT Image 2.5 Sunburst
168 </figcaption>
169
170
171
172
173
174 </figure>
175
176
177
178### Render exact text
179
180Quote the required copy and tell the model how many times it should appear. Specify the audience and visual treatment without adding unrelated instructions.
181
182Generation settings: `size="1024x1536"`, `quality="medium"`.
183
184```text
185Give me a cool in culture ad / fashion shot for a brand called Thread.
186It's a hip young street brand. The ad shows a group of friends hanging out together with the tagline "Yours to Create."
187Make it feel like a polished campaign image for a youth streetwear audience: stylish, contemporary, energetic, and tasteful.
188Use clean composition, strong color direction, natural poses, and premium fashion photography cues.
189Render the tagline exactly once, clearly and legibly, integrated into the ad layout.
190No extra text, no watermarks, no unrelated logos.
191```
192
193Example outputs:
194
195
196
197 <figure className="m-0 min-w-0">
198 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
199 GPT Image 2.5 Flare
200 </figcaption>
201
202
203
204
205
206 </figure>
207 <figure className="m-0 min-w-0">
208 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
209 GPT Image 2.5 Sunburst
210 </figcaption>
211
212
213
214
215
216 </figure>
217
218
219
220### Design a reusable logo
221
222Describe the brand and the shapes that should define the mark. Specify a clear composition that remains legible at different sizes. Use `n` to request multiple variations.
223
224Generation settings: `size="1024x1536"`, `quality="medium"`, `background="transparent"`, `output_format="png"`, `n=1`.
225
226```text
227Create an original, non-infringing logo for a company called Field & Flour, a local bakery.
228The logo should feel warm, simple, and timeless. Use clean, vector-like shapes, a strong silhouette, and balanced negative space.
229Favor simplicity over detail so it reads clearly at small and large sizes. Flat design, minimal strokes, no gradients unless essential.
230Fully transparent background. Deliver a single centered logo with generous padding, clean alpha edges, and no solid backdrop, scenery, checkerboard, or watermark.
231```
232
233Each row compares one variation from each model.
234
235Example outputs:
236
237
238
239 <figure className="m-0 min-w-0">
240 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
241 GPT Image 2.5 Flare
242 </figcaption>
243
244
245
246
247
248 </figure>
249 <figure className="m-0 min-w-0">
250 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
251 GPT Image 2.5 Sunburst
252 </figcaption>
253
254
255
256
257
258 </figure>
259
260
261
262
263
264 <figure className="m-0 min-w-0">
265 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
266 GPT Image 2.5 Flare
267 </figcaption>
268
269
270
271
272
273 </figure>
274 <figure className="m-0 min-w-0">
275 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
276 GPT Image 2.5 Sunburst
277 </figcaption>
278
279
280
281
282
283 </figure>
284
285
286
287
288
289 <figure className="m-0 min-w-0">
290 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
291 GPT Image 2.5 Flare
292 </figcaption>
293
294
295
296
297
298 </figure>
299 <figure className="m-0 min-w-0">
300 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
301 GPT Image 2.5 Sunburst
302 </figcaption>
303
304
305
306
307
308 </figure>
309
310
311
312
313
314 <figure className="m-0 min-w-0">
315 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
316 GPT Image 2.5 Flare
317 </figcaption>
318
319
320
321
322
323 </figure>
324 <figure className="m-0 min-w-0">
325 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
326 GPT Image 2.5 Sunburst
327 </figcaption>
328
329
330
331
332
333 </figure>
334
335
336
337### Use historical and real-world context
338
339Name the place and date to establish a historical setting. The model can infer contextual details, but inspect clothing, staging, and surroundings for historical accuracy.
340
341Generation settings: `size="1024x1536"`, `quality="medium"`.
342
343```text
344Create a realistic outdoor crowd scene in Bethel, New York on August 16, 1969.
345Photorealistic, period-accurate clothing, staging, and environment.
346```
347
348Example outputs:
349
350
351
352 <figure className="m-0 min-w-0">
353 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
354 GPT Image 2.5 Flare
355 </figcaption>
356
357
358
359
360
361 </figure>
362 <figure className="m-0 min-w-0">
363 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
364 GPT Image 2.5 Sunburst
365 </figcaption>
366
367
368
369
370
371 </figure>
372
373
374
375### Turn a story into a comic strip
376
377For 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.
378
379Generation settings: `size="1024x1536"`, `quality="medium"`.
380
381```text
382Create a short vertical comic-style reel with 4 panels.
383Panel 1: The owner leaves through the front door. The pet is framed in the window behind them, small against the glass, eyes wide, paws pressed high, the house suddenly quiet.
384Panel 2: The door clicks shut. Silence breaks. The pet slowly turns toward the empty house, posture shifting, eyes sharp with possibility.
385Panel 3: The house transformed. The pet sprawls across the couch like it owns the place, crumbs nearby, sunlight cutting across the room like a spotlight.
386Panel 4: The door opens. The pet is seated perfectly by the entrance, alert and composed, as if nothing happened.
387```
388
389Example outputs:
390
391
392
393 <figure className="m-0 min-w-0">
394 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
395 GPT Image 2.5 Flare
396 </figcaption>
397
398
399
400
401
402 </figure>
403 <figure className="m-0 min-w-0">
404 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
405 GPT Image 2.5 Sunburst
406 </figcaption>
407
408
409
410
411
412 </figure>
413
414
415
416### Create an interface preview
417
418Interface previews 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.
419
420Generation settings: `size="1024x1536"`, `quality="medium"`.
421
422```text
423Create a realistic mobile app UI mockup for a local farmers market.
424Show today’s market with a simple header, a short list of vendors with small photos and categories, a small “Today’s specials” section, and basic information for location and hours.
425Design it to be practical, and easy to use. White background, subtle natural accent colors, clear typography, and minimal decoration.
426It should look like a real, well-designed, beautiful app for a small local market.
427Place the UI mockup in an iPhone frame.
428```
429
430Example outputs:
431
432
433
434 <figure className="m-0 min-w-0">
435 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
436 GPT Image 2.5 Flare
437 </figcaption>
438
439
440
441
442
443 </figure>
444 <figure className="m-0 min-w-0">
445 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
446 GPT Image 2.5 Sunburst
447 </figcaption>
448
449
450
451
452
453 </figure>
454
455
456
457### Create scientific and educational visuals
458
459Scientific and educational visuals are strong fits for biology, chemistry, classroom explanations, flat scientific icon systems, diagrams, and learning assets. Prompt them like an instructional design brief: define the audience, lesson objective, visual format, required labels, and scientific constraints. For best results, ask for a clean, flat visual system with consistent icon style, clear arrows, readable labels, and enough white space for students to scan the concept quickly.
460
461When accuracy matters, list the required components explicitly and say what should not be included. Use `quality="high"` for dense labels, diagrams, or assets that will be used in slides or course materials.
462
463Generation settings: `size="1536x1024"`, `quality="high"`.
464
465```text
466Create a simple biology diagram titled "Cellular Respiration at a Glance" for high school students.
467
468Show how glucose turns into energy inside a cell. Include glycolysis, the Krebs cycle, and the electron transport chain.
469Use arrows to connect the steps, and label the main molecules: glucose, pyruvate, ATP, NADH, FADH2, CO2, O2, and H2O.
470Make it look like a clean classroom handout or slide, with a white background, simple icons, clear labels, and easy-to-read text.
471
472Avoid tiny text, extra decoration, or anything that makes the diagram hard to understand.
473```
474
475Example outputs:
476
477
478
479 <figure className="m-0 min-w-0">
480 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
481 GPT Image 2.5 Flare
482 </figcaption>
483
484
485
486
487
488 </figure>
489 <figure className="m-0 min-w-0">
490 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
491 GPT Image 2.5 Sunburst
492 </figcaption>
493
494
495
496
497
498 </figure>
499
500
501
502### Build slides, diagrams, and charts
503
504Productivity visuals work best when the prompt is written like an artifact spec rather than an illustration request. Name the exact deliverable (slide, workflow diagram, chart, page image), define the canvas and hierarchy, provide the real text or data, and describe the visual language. These prompts should include practical constraints: readable typography, polished spacing, no decorative clutter, and no generic stock-photo treatment.
505
506For slides, charts, and diagram-heavy assets, include the numbers and labels directly in the prompt. Use a landscape size for deck-style outputs and `quality="high"` when the image contains small text, legends, axes, or footnotes.
507
508The sample market figures and citations below are fictional design inputs. Replace them with verified data before using the slide.
509
510Generation settings: `size="1536x864"`, `quality="high"`.
511
512```text
513Create one pitch-deck slide titled **"Market Opportunity"** that feels like a real Series A fundraising slide from a YC-backed startup.
514
515Use a clean white background, modern sans-serif typography like Inter, and a crisp, minimal layout. The slide should include:
516
517* A TAM/SAM/SOM concentric-circle diagram in muted blues and grays
518* Specific, believable market sizing numbers:
519
520 * **TAM:** $42B
521 * **SAM:** $8.7B
522 * **SOM:** $340M
523* A clean bar chart below showing market growth from **2021 to 2026**, with a subtle upward trend
524* Small footnotes: **"AGI Research, 2024"** and **"Internal analysis"**
525* A company logo placeholder in the bottom-right corner
526
527The design should look like it belongs in a deck that actually raised money: highly readable text, clear data hierarchy, polished spacing, and professional startup-style visual language.
528
529Avoid clip art, stock photography, gradients, shadows, decorative elements, or anything that feels generic or overdesigned.
530```
531
532Example outputs:
533
534
535
536 <figure className="m-0 min-w-0">
537 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
538 GPT Image 2.5 Flare
539 </figcaption>
540
541
542
543
544
545 </figure>
546 <figure className="m-0 min-w-0">
547 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
548 GPT Image 2.5 Sunburst
549 </figcaption>
550
551
552
553
554
555 </figure>
556
557
558
559## Edit images
560
561Use `client.images.edit` with the referenced input images. For local edits that require a mask, see [editing with a mask](https://developers.openai.com/api/docs/guides/image-generation#edit-an-image-using-a-mask).
562
563### Translate while preserving layout
564
565Use each model's coffee-machine diagram from [Explain a process visually](#explain-a-process-visually) as the input. Ask to replace its text while keeping the design unchanged, then check the translation and any words left in the original language.
566
567Edit settings: `size="1024x1536"`, `quality="high"`.
568
569```text
570Translate the text in the infographic to Spanish. Do not change any other aspect of the image.
571```
572
573Example outputs:
574
575
576
577 <figure className="m-0 min-w-0">
578 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
579 GPT Image 2.5 Flare
580 </figcaption>
581
582
583
584
585
586 </figure>
587 <figure className="m-0 min-w-0">
588 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
589 GPT Image 2.5 Sunburst
590 </figcaption>
591
592
593
594
595
596 </figure>
597
598
599
600### Transfer a visual style
601
602Assign the reference image a specific role: its palette, texture, or visual medium. Describe the new subject separately. Use the pixel-art image below as the input.
603
604Edit settings: `size="1024x1536"`, `quality="medium"`.
605
606```text
607Use the same style from the input image and generate a man riding a motorcycle on a white background.
608```
609
610Input image:
611
612
613
614
615
616
617
618Example outputs:
619
620
621
622 <figure className="m-0 min-w-0">
623 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
624 GPT Image 2.5 Flare
625 </figcaption>
626
627
628
629
630
631 </figure>
632 <figure className="m-0 min-w-0">
633 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
634 GPT Image 2.5 Sunburst
635 </figcaption>
636
637
638
639
640
641 </figure>
642
643
644
645### Preserve identity and change clothing
646
647Use the person photograph and three clothing references below as inputs. State which aspects of the person must remain fixed, and allow only the clothing to change. This pattern also applies to edits where a product or object must remain recognizable.
648
649Edit settings: `size="1024x1536"`, `quality="medium"`.
650
651```text
652Edit the image to dress the woman using the provided clothing images. Do not change her face, facial features, skin tone, body shape, pose, or identity in any way. Preserve her exact likeness, expression, hairstyle, and proportions. Replace only the clothing, fitting the garments naturally to her existing pose and body geometry with realistic fabric behavior. Match lighting, shadows, and color temperature to the original photo so the outfit integrates photorealistically, without looking pasted on. Do not change the background, camera angle, framing, or image quality, and do not add accessories, text, logos, or watermarks.
653```
654
655Input images:
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682Example outputs:
683
684
685
686 <figure className="m-0 min-w-0">
687 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
688 GPT Image 2.5 Flare
689 </figcaption>
690
691
692
693
694
695 </figure>
696 <figure className="m-0 min-w-0">
697 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
698 GPT Image 2.5 Sunburst
699 </figcaption>
700
701
702
703
704
705 </figure>
706
707
708
709### Combine references
710
711Pass the scene photograph as image 1 and the dog photograph as image 2. Specify which element to move, its destination, and what must remain unchanged.
712
713Edit settings: `size="1024x1536"`, `quality="medium"`.
714
715```text
716Place the dog from the second image into the setting of image 1, right next to the woman, use the same style of lighting, composition and background. Do not change anything else.
717```
718
719Input images:
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736Example outputs:
737
738
739
740 <figure className="m-0 min-w-0">
741 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
742 GPT Image 2.5 Flare
743 </figcaption>
744
745
746
747
748
749 </figure>
750 <figure className="m-0 min-w-0">
751 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
752 GPT Image 2.5 Sunburst
753 </figcaption>
754
755
756
757
758
759 </figure>
760
761
762
763
764
765
766### Create a transparent product cutout
767
768Request both an isolated subject in the prompt and `background="transparent"` in the API. Use PNG or WebP, preserve the returned alpha channel, and omit `output_compression` for PNG. A drawn checkerboard is not transparency. For subsequent edits, repeat the requirement to preserve the transparent background. Use the product photograph below as the input.
769
770Edit settings: `size="1024x1536"`, `quality="medium"`, `background="transparent"`, `output_format="png"`.
771
772```text
773Extract the product from the input image and isolate it on a fully transparent background.
774Output: centered product, crisp silhouette, no halos/fringing.
775Preserve product geometry and label legibility exactly.
776Add only light polishing. Do not add a solid backdrop, checkerboard, scenery, or shadow.
777Do not restyle the product; remove the background and preserve clean alpha transparency.
778```
779
780Input image:
781
782
783
784
785
786
787
788Example outputs:
789
790
791
792 <figure className="m-0 min-w-0">
793 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
794 GPT Image 2.5 Flare
795 </figcaption>
796
797
798
799
800
801 </figure>
802 <figure className="m-0 min-w-0">
803 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
804 GPT Image 2.5 Sunburst
805 </figcaption>
806
807
808
809
810
811 </figure>
812
813
814
815### Turn a drawing into a realistic image
816
817Sketch-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.
818
819Edit settings: `size="1024x1536"`, `quality="medium"`.
820
821```text
822Turn this drawing into a photorealistic image.
823Preserve the exact layout, proportions, and perspective.
824Choose realistic materials and lighting consistent with the sketch intent.
825Do not add new elements or text.
826```
827
828Input image:
829
830
831
832
833
834
835
836Example outputs:
837
838
839
840 <figure className="m-0 min-w-0">
841 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
842 GPT Image 2.5 Flare
843 </figcaption>
844
845
846
847
848
849 </figure>
850 <figure className="m-0 min-w-0">
851 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
852 GPT Image 2.5 Sunburst
853 </figcaption>
854
855
856
857
858
859 </figure>
860
861
862
863### Remove an object
864
865Remove one object by naming it explicitly and preserving everything around it. Keep the person, pose, lighting, and composition unchanged so the edit stays local.
866
867Edit settings: `size="1024x1536"`, `quality="medium"`.
868
869```text
870Remove the flower from man's hand. Do not change anything else.
871```
872
873Input image:
874
875
876
877
878
879
880
881Example outputs:
882
883
884
885 <figure className="m-0 min-w-0">
886 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
887 GPT Image 2.5 Flare
888 </figcaption>
889
890
891
892
893
894 </figure>
895 <figure className="m-0 min-w-0">
896 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
897 GPT Image 2.5 Sunburst
898 </figcaption>
899
900
901
902
903
904 </figure>
905
906
907
908### Insert a person into a scene
909
910Insert a person into a new scene while preserving their identity. Specify natural lighting, believable detail, body framing, gaze, and interaction with the scene. State which facial features and proportions must remain unchanged. For `gpt-image-2`, omit `input_fidelity`; image inputs are always processed at high fidelity.
911
912Use the [woman in the museum](https://developers.openai.com/images/platform/guides/image-prompting/woman-in-museum.webp) as the input image.
913
914Edit settings: `size="1024x1536"`, `quality="medium"`.
915
916```text
917Generate a highly realistic action scene where this person is running away from a large, realistic brown bear attacking a campsite. The image should look like a real photograph someone could have taken, not an overly enhanced or cinematic movie-poster image.
918She is centered in the image but looking away from the camera, wearing outdoorsy camping attire, with dirt on her face and tears in her clothing. She is clearly afraid but focused on escaping, running away from the bear as it destroys the campsite behind her.
919The campsite is in Yosemite National Park, with believable natural details. The time of day is dusk, with natural lighting and realistic colors. Everything should feel grounded, authentic, and unstyled, as if captured in a real moment. Avoid cinematic lighting, dramatic color grading, or stylized composition.
920```
921
922Example outputs:
923
924
925
926 <figure className="m-0 min-w-0">
927 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
928 GPT Image 2.5 Flare
929 </figcaption>
930
931
932
933
934
935 </figure>
936 <figure className="m-0 min-w-0">
937 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
938 GPT Image 2.5 Sunburst
939 </figcaption>
940
941
942
943
944
945 </figure>
946
947
948
949## Refine an image across turns
950
951Start with one output, inspect it, and use it as the next input. Keep each follow-up narrow so you can see which change helped.
952
953### Create the starting image
954
955Use the shampoo photograph from [Create a transparent product cutout](#create-a-transparent-product-cutout) as the input for this billboard scene. Quote the label text exactly.
956
957Edit settings: `size="1024x1536"`, `quality="medium"`.
958
959```text
960Create a realistic billboard mockup of the shampoo on a highway scene during sunset.
961Billboard text (EXACT, verbatim, no extra characters):
962"Fresh and clean"
963Typography: bold sans-serif, high contrast, centered, clean kerning.
964Ensure text appears once and is perfectly legible.
965No watermarks, no logos.
966```
967
968Input image:
969
970
971
972
973
974
975
976Example outputs:
977
978
979
980 <figure className="m-0 min-w-0">
981 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
982 GPT Image 2.5 Flare
983 </figcaption>
984
985
986
987
988
989 </figure>
990 <figure className="m-0 min-w-0">
991 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
992 GPT Image 2.5 Sunburst
993 </figcaption>
994
995
996
997
998
999 </figure>
1000
1001
1002
1003### Change one condition
1004
1005Pass each model's billboard output from the previous step into its next edit request. This short follow-up changes the weather while retaining the existing scene.
1006
1007Edit settings: `size="1024x1536"`, `quality="medium"`.
1008
1009```text
1010Make it look like a winter evening with snowfall.
1011```
1012
1013Example outputs:
1014
1015
1016
1017 <figure className="m-0 min-w-0">
1018 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
1019 GPT Image 2.5 Flare
1020 </figcaption>
1021
1022
1023
1024
1025
1026 </figure>
1027 <figure className="m-0 min-w-0">
1028 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
1029 GPT Image 2.5 Sunburst
1030 </figcaption>
1031
1032
1033
1034
1035
1036 </figure>
1037
1038
1039
1040### Keep a character consistent
1041
1042For a book with multiple illustrations, create a reusable character reference to help preserve appearance across scenes, poses, and pages. Change the environment and story while repeating the character’s defining details.
1043
1044#### Establish the character
1045
1046Define the character’s appearance, proportions, outfit, and tone.
1047
1048Generation settings: `size="1024x1536"`, `quality="medium"`.
1049
1050```text
1051Create a children’s book illustration introducing a main character.
1052
1053Character:
1054A young, storybook-style hero inspired by a little forest outlaw,
1055wearing a simple green hooded tunic, soft brown boots, and a small belt pouch.
1056The character has a kind expression, gentle eyes, and a brave but warm demeanor.
1057Carries a small wooden bow used only for helping, never harming.
1058
1059Theme:
1060The character protects and rescues small forest animals like squirrels, birds, and rabbits.
1061
1062Style:
1063Children’s book illustration, hand-painted watercolor look,
1064soft outlines, warm earthy colors, whimsical and friendly.
1065Proportions suitable for picture books (slightly oversized head, expressive face).
1066
1067Constraints:
1068- Original character (no copyrighted characters)
1069- No text
1070- No watermarks
1071- Plain forest background to clearly showcase the character
1072```
1073
1074Example outputs:
1075
1076
1077
1078 <figure className="m-0 min-w-0">
1079 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
1080 GPT Image 2.5 Flare
1081 </figcaption>
1082
1083
1084
1085
1086
1087 </figure>
1088 <figure className="m-0 min-w-0">
1089 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
1090 GPT Image 2.5 Sunburst
1091 </figcaption>
1092
1093
1094
1095
1096
1097 </figure>
1098
1099
1100
1101#### Continue the story
1102
1103Reuse each model's generated character image and describe a new scene. Repeat the appearance constraints so the character stays consistent.
1104
1105Edit settings: `size="1024x1536"`, `quality="medium"`.
1106
1107```text
1108Continue the children’s book story using the same character.
1109
1110Scene:
1111The same young forest hero is gently helping a frightened squirrel
1112out of a fallen tree after a winter storm.
1113The character kneels beside the squirrel, offering reassurance.
1114
1115Character Consistency:
1116- Same green hooded tunic
1117- Same facial features, proportions, and color palette
1118- Same gentle, heroic personality
1119
1120Style:
1121Children’s book watercolor illustration,
1122soft lighting, snowy forest environment,
1123warm and comforting mood.
1124
1125Constraints:
1126- Do not redesign the character
1127- No text
1128- No watermarks
1129```
1130
1131Example outputs:
1132
1133
1134
1135 <figure className="m-0 min-w-0">
1136 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
1137 GPT Image 2.5 Flare
1138 </figcaption>
1139
1140
1141
1142
1143
1144 </figure>
1145 <figure className="m-0 min-w-0">
1146 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
1147 GPT Image 2.5 Sunburst
1148 </figcaption>
1149
1150
1151
1152
1153
1154 </figure>
1155
1156
1157
1158## More workflows
1159
1160### Change furniture in a room
1161
1162Visualize furniture or décor changes in real spaces without recreating 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.
1163
1164Edit settings: `size="1536x1024"`, `quality="medium"`.
1165
1166```text
1167In this room photo, replace ONLY the white chairs with chairs made of wood.
1168Preserve camera angle, room lighting, floor shadows, and surrounding objects.
1169Keep all other aspects of the image unchanged.
1170Photorealistic contact shadows and fabric texture.
1171```
1172
1173Input image:
1174
1175
1176
1177
1178
1179
1180
1181Example outputs:
1182
1183
1184
1185 <figure className="m-0 min-w-0">
1186 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
1187 GPT Image 2.5 Flare
1188 </figcaption>
1189
1190
1191
1192
1193
1194 </figure>
1195 <figure className="m-0 min-w-0">
1196 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
1197 GPT Image 2.5 Sunburst
1198 </figcaption>
1199
1200
1201
1202
1203
1204 </figure>
1205
1206
1207
1208### Design a holiday card
1209
1210For seasonal card concepts, describe the scene, emotional tone, materials, lighting, and exact copy. For a 3D pop-up or photographed-card treatment, specify paper layers, fibers, folds, and soft studio lighting. The example below uses a nostalgic teddy-bear scene.
1211
1212Generation settings: `size="1024x1536"`, `quality="medium"`.
1213
1214```text
1215Create a Christmas holiday card illustration.
1216
1217Scene:
1218a cozy Christmas scene with an old teddy bear sitting inside a keepsake box, slightly worn fur, soft stitching repairs, placed near a window with falling snow outside. The scene suggests the child has grown up, but the memories remain.
1219
1220Mood:
1221Warm, nostalgic, gentle, emotional.
1222
1223Style:
1224Premium holiday card photography, soft cinematic lighting,
1225realistic textures, shallow depth of field,
1226tasteful bokeh lights, high print-quality composition.
1227
1228Constraints:
1229- Original artwork only
1230- No trademarks
1231- No watermarks
1232- No logos
1233
1234Include ONLY this card text (verbatim):
1235"Merry Christmas — some memories never fade."
1236```
1237
1238Example outputs:
1239
1240
1241
1242 <figure className="m-0 min-w-0">
1243 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
1244 GPT Image 2.5 Flare
1245 </figcaption>
1246
1247
1248
1249
1250
1251 </figure>
1252 <figure className="m-0 min-w-0">
1253 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
1254 GPT Image 2.5 Sunburst
1255 </figcaption>
1256
1257
1258
1259
1260
1261 </figure>
1262
1263
1264
1265### Design collectible merchandise
1266
1267Explore merchandise and packaging concepts using product photography cues: materials, packaging, and print clarity. Keep designs original and non-infringing, and compare multiple character or packaging variants.
1268
1269Generation settings: `size="1024x1536"`, `quality="medium"`.
1270
1271```text
1272Create a collectible action figure of a vintage-style toy propeller airplane with rounded wings, a front-mounted spinning propeller, slightly worn paint edges, classic childhood proportions, designed as a nostalgic holiday collectible, in blister packaging.
1273
1274Concept:
1275A nostalgic holiday collectible inspired by the simple toy airplanes
1276children used to play with during winter holidays.
1277Evokes warmth, imagination, and childhood wonder.
1278
1279Style:
1280Premium toy photography, realistic plastic and painted metal textures,
1281studio lighting, shallow depth of field,
1282sharp label printing, high-end retail presentation.
1283
1284Constraints:
1285- Original design only
1286- No trademarks
1287- No watermarks
1288- No logos
1289
1290Include ONLY this packaging text (verbatim):
1291"Christmas Memories Edition"
1292```
1293
1294Example outputs:
1295
1296
1297
1298 <figure className="m-0 min-w-0">
1299 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
1300 GPT Image 2.5 Flare
1301 </figcaption>
1302
1303
1304
1305
1306
1307 </figure>
1308 <figure className="m-0 min-w-0">
1309 <figcaption className="mb-2 min-h-10 text-sm font-semibold">
1310 GPT Image 2.5 Sunburst
1311 </figcaption>
1312
1313
1314
1315
1316
1317 </figure>
1318
1319
1320
1321## Run a complete example
1322
1323This runnable example remains pinned to `gpt-image-2`. Use it as a baseline, then choose an available model and its supported request settings for your evaluation.
1324
1325The examples below generate four logo variations and extract a product onto a transparent background. Install the [OpenAI SDK](https://developers.openai.com/api/docs/libraries#install-an-official-sdk) with `pip install openai` for Python or `gem install openai` for Ruby. Set `OPENAI_API_KEY` and save the [product photograph](https://developers.openai.com/images/platform/guides/image-prompting/shampoo.webp) as `input_images/shampoo.webp`. Live requests incur API usage charges.
1326
1327
1328
1329### View the complete example
1330
1331
1332 Generate and edit transparent assets
1333
1334```python
1335import base64
1336from pathlib import Path
1337
1338from openai import OpenAI
1339
1340client = OpenAI()
1341
1342
1343prompt = """
1344Create an original, non-infringing logo for a company called Field & Flour, a local bakery.
1345The logo should feel warm, simple, and timeless. Use clean, vector-like shapes, a strong silhouette, and balanced negative space.
1346Favor simplicity over detail so it reads clearly at small and large sizes. Flat design, minimal strokes, no gradients unless essential.
1347Fully transparent background. Deliver a single centered logo with generous padding, clean alpha edges, and no solid backdrop, scenery, checkerboard, or watermark.
1348"""
1349
1350result = client.images.generate(
1351 model="gpt-image-2",
1352 prompt=prompt,
1353 size="1024x1536",
1354 quality="medium",
1355 background="transparent",
1356 output_format="png",
1357 n=4, # Generate 4 versions of the logo
1358)
1359
1360# Preserve the returned PNG bytes, including the alpha channel.
1361for index, item in enumerate(result.data, start=1):
1362 Path(f"logo-generation-{index}-gpt-image-2.png").write_bytes(
1363 base64.b64decode(item.b64_json)
1364 )
1365
1366# Extract a product from a reference image.
1367prompt = """
1368Extract the product from the input image and isolate it on a fully transparent background.
1369Output: centered product, crisp silhouette, no halos/fringing.
1370Preserve product geometry and label legibility exactly.
1371Add only light polishing. Do not add a solid backdrop, checkerboard, scenery, or shadow.
1372Do not restyle the product; remove the background and preserve clean alpha transparency.
1373"""
1374
1375result = client.images.edit(
1376 model="gpt-image-2",
1377 image=[
1378 Path("input_images/shampoo.webp"),
1379 ],
1380 prompt=prompt,
1381 size="1024x1536",
1382 quality="medium",
1383 background="transparent",
1384 output_format="png",
1385)
1386
1387Path("extract-product-gpt-image-2.png").write_bytes(
1388 base64.b64decode(result.data[0].b64_json)
1389)
1390```
1391
1392```ruby
1393require "base64"
1394require "openai"
1395require "pathname"
1396
1397client = OpenAI::Client.new
1398result = client.images.generate(
1399 model: "gpt-image-2",
1400 prompt: "Create an original logo for Field & Flour, a local bakery. Use warm, simple shapes on a fully transparent background, with clean alpha edges and no shadow or checkerboard.",
1401 size: "1024x1536", quality: :medium, background: :transparent, output_format: :png, n: 4
1402)
1403Array(result.data).each_with_index do |item, index|
1404 File.binwrite("logo-generation-#{index + 1}-gpt-image-2.png", Base64.strict_decode64(item.b64_json || raise("No PNG returned")))
1405end
1406result = client.images.edit(
1407 model: "gpt-image-2", image: OpenAI::FilePart.new(Pathname("input_images/shampoo.webp"), content_type: "image/webp"),
1408 prompt: "Extract the product onto a fully transparent background. Preserve its geometry and label, with clean edges and no shadow or restyling.",
1409 size: "1024x1536", quality: :medium, background: :transparent, output_format: :png
1410)
1411File.binwrite("extract-product-gpt-image-2.png", Base64.strict_decode64(Array(result.data).fetch(0).b64_json || raise("No PNG returned")))
1412```
1413
1414
1415
1416
1417
1418For additional prompts and complete workflows, see the [original notebook](https://github.com/openai/openai-cookbook/blob/d310dfa05d20fb653caa9c1c4b89ac1a4aeeeae4/examples/multimodal/image-gen-models-prompting-guide.ipynb).
1419
1420## Check the result
1421
1422Check the output against the requirements before using it:
1423
1424- Is required text accurate and legible? Are diagram labels and relationships correct?
1425- Do identities, product shapes, labels, and reference details remain intact?
1426- Did the edit change only what you requested?
1427- If transparency is required, does the file contain an alpha channel rather than a painted background?
1428
1429Compare quality, latency, and cost on representative inputs when changing prompts or models. See [image generation pricing](https://developers.openai.com/api/docs/pricing#image-generation) for current costs.
1430
1431
1432
1433
1434
1435
1436 <header className="not-prose mb-8">
1437 <h2
1438 id="gpt-image-2-guide"
1439 className="m-0 text-3xl font-semibold text-default"
1440 >
1441 {"GPT Image 2 reference"}
1442 </h2>
1443
1444
1445 Overview and request settings for existing GPT Image 2 workflows.
1446
1447
1448 </header>
1449
1450
1451## Overview
1452
1453GPT Image 2 supports image generation and editing, including text rendering, reference-based edits, and flexible output sizes. Use this reference to maintain existing integrations. The [prompting guide](https://developers.openai.com/api/docs/guides/image-prompting?model=gpt-image-2.5) covers shared techniques for composition, text, reference images, and preserving details during edits. Its illustrated examples use GPT Image 2.5 Flare and GPT Image 2.5 Sunburst; outputs can differ across models. For migration, use the guide's [model selection](https://developers.openai.com/api/docs/guides/image-prompting?model=gpt-image-2.5#choose-a-model) and [evaluation workflow](https://developers.openai.com/api/docs/guides/image-prompting?model=gpt-image-2.5#migrate-an-existing-workflow).
1454
1455## Model parameters
1456
1457Use `client.images.generate` for generation and `client.images.edit` for edits. See the [image generation guide](https://developers.openai.com/api/docs/guides/image-generation) for API setup and request examples.
1458
1459| Parameter | GPT Image 2 |
1460| -------------------- | -------------------------------------------------------------------------------------------------------------------- |
1461| `model` | `gpt-image-2` |
1462| `quality` | `low`, `medium`, `high`, or `auto` |
1463| `size` | `auto` or a supported resolution; see [size constraints](https://developers.openai.com/api/docs/guides/image-generation#size-and-quality-options) |
1464| `input_fidelity` | Omit it. Image inputs are always processed at high fidelity. |
1465| `output_format` | `png`, `jpeg`, or `webp` |
1466| `background` | For transparent output, explicitly set `transparent` and use PNG or WebP. |
1467| `output_compression` | Use only for JPEG or WebP output, not PNG. |
1468
1469Transparent backgrounds are available in preview for `gpt-image-2`.
1470
1471For the original prompts, inputs, and runnable workflows, see the pinned [GPT Image 2 notebook](https://github.com/openai/openai-cookbook/blob/d310dfa05d20fb653caa9c1c4b89ac1a4aeeeae4/examples/multimodal/image-gen-models-prompting-guide.ipynb).
1472
1473
1474
1475
1476
1477
1478 <header className="not-prose mb-8">
1479 <h2
1480 id="gpt-image-1.5-guide"
1481 className="m-0 text-3xl font-semibold text-default"
1482 >
1483 {"GPT Image 1.5 reference"}
1484 </h2>
1485
1486
1487 Overview and request settings for existing GPT Image 1.5 workflows.
1488
1489
1490 </header>
1491
1492
1493## Overview
1494
1495**Deprecated model.** `gpt-image-1.5` is scheduled to shut down on December 1,
1496 2026. See the [deprecation
1497 notice](https://developers.openai.com/api/docs/deprecations#2026-06-02-gpt-image-model-deprecations) and
1498 validate existing workflows with `gpt-image-2` before migrating.
1499
1500GPT Image 1.5 supports image generation and editing, including text rendering, photorealistic images, and reference-based edits. Use this reference to maintain existing integrations. The [prompting guide](https://developers.openai.com/api/docs/guides/image-prompting?model=gpt-image-2.5) covers shared techniques for composition, text, reference images, and preserving details during edits. Test those techniques with your model and inputs; outputs can differ across models.
1501
1502## Model parameters
1503
1504Use `client.images.generate` for generation and `client.images.edit` for edits. See the [image generation guide](https://developers.openai.com/api/docs/guides/image-generation) for API setup and request examples.
1505
1506| Parameter | GPT Image 1.5 |
1507| -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1508| `model` | `gpt-image-1.5` |
1509| `quality` | `low`, `medium`, `high`, or `auto` |
1510| `size` | `1024x1024`, `1024x1536`, `1536x1024`, or `auto` |
1511| `output_format` | `png`, `jpeg`, or `webp` |
1512| `output_compression` | 0 to 100, for JPEG or WebP output only |
1513| `background` | Set `transparent` explicitly for transparent output; use PNG or WebP |
1514| `input_fidelity` | `low` or `high`; `high` preserves input details, while `quality` controls output generation. Omit this parameter when migrating to GPT Image 2, which always uses high input fidelity. |
1515
1516
1517
1518
1519
1520
1521 <header className="not-prose mb-8">
1522 <h2
1523 id="gpt-image-1-guide"
1524 className="m-0 text-3xl font-semibold text-default"
1525 >
1526 {"GPT Image 1 reference"}
1527 </h2>
1528
1529
1530 Overview and request settings for existing GPT Image 1 workflows.
1531
1532
1533 </header>
1534
1535
1536## Overview
1537
1538**Deprecated model.** `gpt-image-1` is scheduled to shut down on October 23,
1539 2026. See the [deprecation
1540 notice](https://developers.openai.com/api/docs/deprecations#2026-04-22-legacy-gpt-model-snapshots) and
1541 validate existing workflows with `gpt-image-2` before migrating.
1542
1543GPT Image 1 supports image generation and editing with reference images and masks. Use this reference to maintain existing integrations. For shared techniques such as describing a scene, preserving details, and refining an edit, see the [prompting guide](https://developers.openai.com/api/docs/guides/image-prompting?model=gpt-image-2.5).
1544
1545## Model parameters
1546
1547Use `client.images.generate` for generation and `client.images.edit` for edits. See the [image generation guide](https://developers.openai.com/api/docs/guides/image-generation) for API setup and request examples.
1548
1549| Parameter | GPT Image 1 |
1550| -------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1551| `model` | `gpt-image-1` |
1552| `quality` | `low`, `medium`, `high`, or `auto` |
1553| `size` | `1024x1024`, `1024x1536`, `1536x1024`, or `auto` |
1554| `output_format` | `png`, `jpeg`, or `webp` |
1555| `output_compression` | 0 to 100, for JPEG or WebP output only |
1556| `background` | Set `transparent` explicitly for transparent output; use PNG or WebP |
1557| `input_fidelity` | `low` or `high`; `high` preserves input details, while `quality` controls output generation. High input fidelity uses more image input tokens. Omit this parameter when migrating to GPT Image 2, which always uses high input fidelity. |
