How many reference images can I use with GPT Image 1.5?

GPT Image 1.5 / Upload limit / Runtime — Up to 16 images, 10 MB each

GPT Image 1.5 is deprecated, so should I still use high?

GPT Image 1.5 / The official model status has changed — Deprecation does not mean high will stop working immediately, but GPT Image 1.5 should not be the default starting point for new work. Choose high only for compatibility or regression testing of an existing 1.5 workflow, and only when the same-input test shows that the result is worth increasing the cost from 4 to 22 credits. For new work, compare current models such as GPT Image 2 at the same time.

AI image model

OpenAI

GPT Image

GPT Image 1.5

Q: Does GPT Image 1.5 support image-to-image editing on Kyeo AI?

GPT Image 1.5 / Capabilities / Runtime — GPT Image 1.5 on Kyeo supports text-to-image and image-to-image with three aspect ratios and medium/high quality. Image editing accepts up to 16 JPG, PNG, or WebP references at 10 MB each. Medium costs 4 credits and high costs 22 credits.

GPT Image 1.5 on Kyeo supports text-to-image and image-to-image with three aspect ratios and medium/high quality. Image editing accepts up to 16 JPG, PNG, or WebP references at 10 MB each. Medium costs 4 credits and high costs 22 credits. GPT Image 1.5 is OpenAI's deprecated previous image model. Kyeo retains generation and editing access, but that availability does not make it OpenAI's current default choice.

Use this model View credit pricing Back to Model Hub

Capabilities

Text-to-image, image-to-image

Credit cost

4–22 credits per request

Prompt limit

No published character limit

Upload limit

Up to 16 images, 10 MB each

30-second overview

GPT Image 1.5 / Capabilities — GPT Image 1.5 on Kyeo supports text-to-image and image-to-image with three aspect ratios and medium/high quality. Image editing accepts up to 16 JPG, PNG, or WebP references at 10 MB each. Medium costs 4 credits and high costs 22 credits.
GPT Image 1.5 / Aspect ratio — Kyeo exposes only `aspect_ratio` and `quality`, not the full set of controls in OpenAI's direct API.
GPT Image 1.5 / Upload limit — Up to 16 images, 10 MB each
GPT Image 1.5 / Credit cost — Medium and high currently cost 4 and 22 credits; changing tiers does not guarantee result quality.

Popular searches: using GPT Image 1.5 on Kyeo · GPT Image 1.5 editing upload requirements · GPT Image 1.5 generation controls

Examples

Visual concept

Ultra-realistic lifestyle portrait of a cheerful young woman with fair porcelain skin, medium-length straight black hair with wispy curtain bangs gently blown by the wind, bright genuine smile, almond-shaped dark brown eyes, and natural soft makeup. She wears an oversized white graphic T-shirt with colorful landscape prints, a delicate silver necklace with a small green butterfly pendant, and a white wireless earbud. She casually holds a transparent cup of iced orange juice with a brown straw and a cute smiling face logo. Captured from a dramatic low-angle wide-angle perspective against a clear blue sky, illuminated by bright natural midday sunlight with soft shadows and vibrant colors. Fresh, youthful, carefree summer atmosphere, candid lifestyle photography, minimalist composition, natural skin texture, realistic hair strands, HDR, cinematic color grading, DSLR quality, sharp focus, ultra-photorealistic, editorial style, masterpiece, 8K.

Visual concept

Create image Create a high-end studio fashion portrait inspired by the uploaded blue-background reference photograph. Recreate the original composition with matching framing, focal length feel, camera position, subject scale, perspective, and overall visual balance while maintaining a realistic photographic appearance. Replace the reference model with a beautiful young Japanese/Korean woman. Preserve authentic East Asian facial features, natural proportions, realistic skin texture, eye shape, facial structure, and cultural authenticity. Avoid exaggerated beauty filters, unrealistic facial modifications, or doll-like features. Maintain a natural, believable fashion-model appearance. Match the original body language closely: upper torso visible, shoulders relaxed, chin slightly elevated, eyes directed upward beyond the camera, conveying quiet confidence, sophistication, and contemplation. Maintain the same sense of presence and spatial positioning within the frame. Retain the rich cobalt-blue studio backdrop and the refined editorial atmosphere. Reproduce the original lighting setup with soft directional illumination, subtle facial highlights, realistic reflections on eyewear and jewelry, and smooth shadow transitions around the jawline, neck, and clothing folds. Preserve depth, dimensionality, and professional studio realism. Appearance: Young Japanese/Korean woman in her early-to-mid 20s Clear luminous skin with natural texture Soft almond-shaped eyes Elegant facial structure Healthy natural makeup with subtle editorial refinement Glossy neutral lips Long dark hair styled in soft layers or gentle waves Sophisticated yet approachable expression Style the model in contemporary luxury street-fashion apparel. Use an oversized premium knit sweater, relaxed-fit sweatshirt, or fashion-forward minimalist streetwear silhouette with natural fabric draping. Layer with a delicate silver necklace, subtle rings, and lightly tinted translucent eyewear. Wardrobe should feel premium, modern, and suitable for a luxury fashion campaign. Keep the image tightly composed with the same portrait crop and subject placement. Ensure identical camera-to-subject distance and visual weight in the frame. The final result should feel indistinguishable from a genuine professional fashion photoshoot captured in this exact studio environment. Photorealistic editorial photography, luxury fashion campaign, premium Korean/Japanese streetwear styling, deep monochromatic blue backdrop, realistic skin texture, subtle film-grade contrast, detailed fabric rendering, natural lighting falloff, commercial advertising quality, shallow depth of field, magazine-cover aesthetics, fashion-editorial realism, luxury street-fashion branding. Negative Prompt: Do not alter the background color or studio environment. Do not change the framing, crop, perspective, subject distance, or lighting direction. Avoid anime styling, illustration effects, CGI appearance, excessive retouching, artificial skin smoothing, exaggerated facial features, unrealistic eye size, porcelain skin effect, text overlays, logos, watermarks, duplicate subjects, distorted anatomy, extra limbs, or unrealistic clothing physics.

Visual concept

Full-body studio fashion portrait of a female subject with uploaded face as reference, lounging gracefully inside the hollow of a massive, 3D-rendered translucent lime-green glass letter “A” (representing Hania AI). She wears a glossy black puffer vest over a lime-green oversized hoodie, paired with sleek black techwear joggers featuring multiple utility straps, and neon green reflective sneakers. The background is a seamless, deep matte charcoal grey, making the glowing glass structure and vibrant outfit stand out vividly. Lighting is cinematic and directional, with sharp rim lighting outlining her silhouette and enhancing depth. Shot with an 85mm lens, ultra-sharp focus, commercial luxury aesthetic, 8k resolution, with highly photorealistic textures on nylon fabric and glass.

Visual concept

{ "prompt": "Create a hyper-realistic, ultra-detailed cinematic photo featuring a MINIATURE version of the person from the provided reference image (preserve facial likeness, skin tone, hairstyle, and overall identity). The tiny character is relaxing inside an OPEN vintage hard-shell suitcase that is used like a tiny bed. The suitcase sits on a clean stone/tile floor in a bright room with strong natural sunlight casting soft rectangular window shadows across the floor.\n\nONLY VARIABLES:\n1) Character: use the user reference photo for the person’s face and identity.\n2) Theme/Genre: {THEME}\n\nCOMPOSITION & SCALE:\n- The person must be clearly mini-sized (toy-scale) relative to the suitcase, with correct perspective and believable proportions.\n- The open suitcase interior is styled like a cozy miniature scene: pillow, textured blanket or towel, and themed tiny props.\n- Add realistic micro-details: fabric weave, zipper teeth, suitcase latches, scuffs, stitching, subtle dust, realistic contact shadows.\n\nTHEME STYLING (derive everything from {THEME}):\n- Choose a cohesive color palette and make the SUITCASE COLOR match the theme (e.g., beach = warm coral/sand; football = deep green/black or team-inspired; sporty = bold neon accents; cozy-casual = muted cream/tan; luxury = black/ivory/gold).\n- Dress the tiny character in an outfit that fits {THEME}.\n- Place 5–8 tiny theme props neatly inside the suitcase near the character (miniature scale, photoreal materials). Examples by theme:\n • Beach: tiny sunscreen bottle, mini sunglasses, seashells, flip-flops, mini straw hat, folded towel.\n • Football/Soccer: tiny soccer ball, mini jersey/scarf, cleats, shin guards, whistle, small tactic board.\n • Sporty/Fitness: tiny water bottle, mini dumbbell, resistance band, smartwatch, towel, energy bar.\n • Cozy/Casual: tiny book/magazine, mug, knitted throw, headphones, mini candle.\n(If {THEME} is different, invent equivalent props that strongly communicate that theme.)\n\nLIGHTING & CAMERA:\n- Bright natural sunlight, soft realistic shadows, subtle bounce light, HDR-like dynamic range.\n- Photographic realism: shallow depth of field (but keep face and key props sharp), 50–85mm lens look.\n- No text, no logos, no watermarks.\n\nFINAL LOOK:\n- Hyper-real, high detail, clean editorial product-photography vibe, believable miniature diorama realism, crisp textures and natural skin rendering.", "negative_prompt": "cartoon, CGI, illustration, anime, plastic-looking skin, uncanny face, distorted anatomy, extra fingers, deformed hands, duplicated limbs, wrong perspective, unrealistic scale, blurry, low-res, noisy, harsh artifacts, over-smoothed, bad shadows, floating objects, cluttered scene, messy background, text, watermark, logo, brand names, extra people, face not matching reference", "variables": { "THEME": "beach | football | sporty | cozy-casual | luxury | etc.", "USER_IMAGE": "reference photo uploaded by the user (required)" } }

Visual concept

High-fashion futuristic sportswear editorial poster, full-body female model in dynamic wide-leg stance, oversized white minimalist sweatshirt with voluminous sleeves, glossy translucent parachute pants, chunky white-orange athletic sneakers, sleek messy updo hairstyle, gold statement earrings, soft natural makeup, confident editorial expression, studio fashion photography, centered composition, smooth neutral beige gradient background with large abstract glossy red-pink organic 3D inflatable blob shapes behind model, bold oversized white typography “just” partially behind subject, premium athletic brand campaign aesthetic, ultra-clean lighting, soft diffused studio shadows, luxury streetwear advertisement, contemporary magazine cover design, minimalist layout, subtle futuristic graphic microtext, highly polished commercial fashion retouching, sharp focus, cinematic soft contrast, photorealistic, high detail, 8k

Visual concept

{ "type": "image_generation_prompt", "style": "ultra-realistic professional photography, VOGUE magazine editorial", "resolution": "8K", "camera": { "mode": "portrait", "framing": "close-up portrait with visible upper body", "angle": "straight-on", "focus": "woman in sharp focus", "lens_look": "professional portrait lens", "depth_of_field": "shallow, natural" }, "identity_preservation": { "use_reference_image": true, "alter_face": false, "strict_identity_lock": true, "notes": "Do not change or distort facial features, proportions, expression, or skin texture. Preserve the woman’s face exactly as in the reference image." }, "subject": { "gender": "female", "appearance": { "hair": { "style": "very long, straight, thick hair falling forward", "color": "unchanged from reference" }, "eyes": "beautiful, expressive", "expression": "light, natural smile", "skin": "highly detailed, natural texture, no plastic look" }, "wardrobe": { "outfit": "pastel pink cotton pajama set", "top": "classic button-up pajama shirt", "bottom": "loose-fit pajama pants", "footwear": "soft pastel pink furry slippers", "headwear": "pink sleep mask worn as a headband" }, "pose": { "position": "standing on the floor", "interaction": [ "leaning against a tall decorative glass champagne bottle", "holding a champagne glass in one hand" ], "gaze": "looking directly into the camera" } }, "environment": { "background": { "color": "clean white", "details": "soft shadow cast from a panoramic window" }, "props": { "champagne_bottle": { "brand_style": "Moët-style decorative prop", "description": "tall transparent glass bottle with golden liquid, visually identical to a real champagne bottle but decorative" }, "pillows": { "placement": "on the floor around the woman", "colors": "multiple shades of pink", "size": "large, soft cushions" } } }, "lighting": { "type": "natural soft daylight", "direction": "from panoramic window", "effects": [ "face and body evenly lit", "soft realistic shadows", "no artificial highlights" ] }, "text_overlay": { "content": "Sania X content creator", "language": "English", "style": { "color": "pink paint-like lettering", "look": "hand-painted, clear and accurate", "emphasis": "strong focus on letters and spacing" }, "position": "above the woman", "constraints": [ "no other text", "no watermarks" ] }, "aesthetic": { "mood": "soft, elegant, festive, editorial", "palette": [ "pastel pink", "white", "soft gold" ] }, "quality_constraints": { "prohibitions": [ "do not alter facial expression", "do not redraw or replace facial features", "do not over-blur or plasticize skin or hair", "do not change hairstyle or color", "no artificial filter look", "no hand or finger distortions", "no extra or merged fingers", "no incorrect body proportions", "no duplicate subjects", "no watermarks or unwanted text", "no unnatural anatomy or noise" ] }, "output_goal": "Create an ultra-realistic 8K Vogue-style editorial portrait of a woman in pastel pink pajamas, standing in a clean white studio environment with champagne-themed props, preserving her exact facial identity, featuring the text 'Sania X content creator' above her in pink paint lettering." }

At a glance

Is this model right for you?

When choosing GPT Image 1.5, first confirm whether you need compatibility with existing 1.5 results or want to retest an older prompt. Kyeo puts text-to-image and image-to-image on one page and exposes aspect ratios, medium/high credit tiers, and the reference-image limit. Because OpenAI has marked 1.5 as a deprecated previous-generation model, new work should also be compared with a current model such as GPT Image 2 using the same input.

What it does best: GPT Image 1.5 is OpenAI's deprecated previous image model. Kyeo retains generation and editing access, but that availability does not make it OpenAI's current default choice.
Who it is for: It is relevant when a team must preserve a 1.5 baseline, rerun established prompts, or test targeted edits and multi-reference requests against existing acceptance criteria.
Why use it on Kyeo AI: GPT Image 1.5 / Integration — When choosing GPT Image 1.5, first confirm whether you need compatibility with existing 1.5 results or want to retest an older prompt. Kyeo puts text-to-image and image-to-image on one page and exposes aspect ratios, medium/high credit tiers, and the reference-image limit. Because OpenAI has marked 1.5 as a deprecated previous-generation model, new work should also be compared with a current model such as GPT Image 2 using the same input.

Key facts

Quickly evaluate whether this model fits your business use case.

Other names

The same model may have different names in official documentation, community discussions, and API integrations. This section brings them together for you.

gpt-image-1.5

gpt-image-1.5-2025-12-16

Common questions

These practical questions focus on the task, input conditions, and result requirements you should confirm before choosing.

using GPT Image 1.5 on Kyeo

GPT Image 1.5 editing upload requirements

GPT Image 1.5 generation controls

choosing GPT Image 1.5 medium or high

GPT Image 1.5 Kyeo credit cost

GPT Image 1.5 image count and file size

compare GPT Image 1.5 with 4o Image

compare GPT Image 1.5 with Nano Banana Pro

is GPT Image 1.5 deprecated

When to keep GPT Image 1.5 instead of moving to a newer image model

Decision guide

Still deciding? Start with these key decision points.

Prioritize it for an established 1.5 workflow

For a new project, compare the same inputs with OpenAI's current GPT Image 2 rather than treating a deprecated model as the default.

GPT Image: Best for fine control

Kyeo's 4o Image page is a lower-credit generation-only route, while Nano Banana Pro has different aspect-ratio, resolution, and reference limits. Test the same brief and choose by success rate, latency, and credits.

Use the minimum validation path

First confirm that the edit is understood, preserved regions remain intact, and the direction is correct. Then rerun the same input at `high` to see whether the improvement justifies the extra 18 credits.

Popular comparisons

Compare common alternatives on the same task to clarify differences in inputs, controls, and cost.

What is the difference between GPT Image 1.5 and 4o Image?

GPT Image 1.5 vs 4o Image

What is the difference between GPT Image 1.5 and Nano Banana Pro?

GPT Image 1.5 vs Nano Banana Pro

What is the difference between GPT Image 1.5 and Flux 2 Pro?

GPT Image 1.5 vs Flux 2 Pro

Model comparison table

Not sure which model to choose? Compare the key differences between this model and its alternatives at a glance.

Model status and Kyeo capability

GPT Image 1.5

OpenAI's deprecated previous model; Kyeo still offers generation and editing

4o Image

Text-to-image only on Kyeo, at a fixed 3 credits

Nano Banana Pro

Generation and editing with more aspect ratios and resolution choices

Reference-image support

GPT Image 1.5

Up to 16 JPEG, PNG, or WebP images at 10 MB each

4o Image

The current Kyeo page does not accept reference images

Nano Banana Pro

Up to 8 references; consistency still requires testing

Controls available on Kyeo

GPT Image 1.5

3 aspect ratios plus medium and high quality tiers

4o Image

3 size options

Nano Banana Pro

11 aspect ratios plus resolution selection

Current Kyeo credits

GPT Image 1.5

4 credits at medium quality; 22 at high quality

4o Image

A fixed 3 credits per request

Nano Banana Pro

1K / 2K / 4K cost 8 / 8 / 14 credits

Reason to choose it

GPT Image 1.5

Maintaining an existing 1.5 workflow or benchmarking the previous model

4o Image

A low-credit text-to-image comparison

Nano Banana Pro

A Google-based comparison with more aspect ratios

Real-world experience

Practical guidance based on public sources, current on-site limits, and representative tasks.

The official model status has changed

GPT Image 1.5 / The official model status has changed — OpenAI now lists GPT Image 1.5 as a deprecated previous image model and GPT Image 2 as the current image model. Any 1.5 overview should state that lifecycle status instead of calling it the flagship option.

Direct OpenAI controls are not Kyeo controls

GPT Image 1.5 / Direct OpenAI controls are not Kyeo controls — Kyeo exposes 3 aspect ratios and two quality tiers, not every control in OpenAI's direct image API.

Capabilities

Does GPT Image 1.5 support image-to-image editing on Kyeo AI? / GPT Image 1.5

Does GPT Image 1.5 support image-to-image editing on Kyeo AI? / GPT Image 1.5 — GPT Image 1.5 on Kyeo supports text-to-image and image-to-image with three aspect ratios and medium/high quality. Image editing accepts up to 16 JPG, PNG, or WebP references at 10 MB each. Medium costs 4 credits and high costs 22 credits.

Documented reference-image limits

Documented reference-image limits — Up to 16 images, 10 MB each

Quality also selects the credit tier

Quality also selects the credit tier — Generation and editing both offer `medium / high` at 4 / 22 Kyeo credits. Quality is a request and billing setting, not a warranty of accuracy, consistency, or production readiness.

Use cases

GPT Image: Everyday creation

Create social graphics, concept frames, or product mockups from a written brief, then inspect text, layout, and brand details before use.

Targeted edits to an existing image

Test object replacement, background changes, palette adjustments, or recomposition, then inspect text, preserved regions, and layout manually.

Multi-reference experiments

Provide separate sources for a subject, material, palette, or setting, starting with the minimum needed and verifying how the model interprets each one.

Prompt tips

Write edits in preserve, replace, and add order

List elements that must stay unchanged before replacements and additions, including positions and relationships. Inspect the result for unintended changes.

Assign a role to every reference image

Refer to upload order and state which image controls the subject, clothing, background, or material.

Compare medium and high with fixed inputs

Keep the prompt and references identical, then record differences in detail, text, composition, and failure rate. Upgrade only if the evidence supports the extra 18 credits.

Why choose it

Runtime / GPT Image 1.5 — GPT Image 1.5 on Kyeo supports text-to-image and image-to-image with three aspect ratios and medium/high quality. Image editing accepts up to 16 JPG, PNG, or WebP references at 10 MB each. Medium costs 4 credits and high costs 22 credits.

Upload limit — Up to 16 images, 10 MB each

Credit cost — Medium and high credits are explicit, enabling controlled cost comparisons with identical inputs.

Integration / GPT Image 1.5 — The previous model remains useful for regression tests against established 1.5 workflows.

What to know first

Runtime / GPT Image 1.5 — OpenAI marks GPT Image 1.5 as a deprecated previous model; new work should also evaluate a current model.

GPT Image 1.5 / Aspect ratio — Kyeo exposes 3 aspect ratios and two quality tiers, not every control in OpenAI's direct image API.

Credit cost — The high tier costs substantially more, so it is not suitable for large batches of trial-and-error from the outset.

Integration / GPT Image 1.5 — GPT Image can still miss exact text, cross-generation consistency, or precise layouts; high does not remove those limits.

Adjustable settings

Quickly evaluate whether this model fits your business use case.

Aspect ratio

Optional

Parameter type: Select

Default: 1:1

1:1

2:3

3:2

Quality

Optional

Parameter type: Select

Default: medium

medium (standard)

high (high quality)

Credit cost

4–22 credits per request

Kyeo AI charges 4 credits for `medium` and 22 credits for `high`.

Credit-saving tip

Before generating images or videos in bulk, run an A/B test with the same input on this model and similar alternatives. Confirm the result first to avoid wasting credits.

Frequently asked questions

Related models

Still deciding? Take a quick look at these similar alternatives.

4o Image

4o Image / Capabilities — This page offers only three aspect ratios—`1:1 / 3:2 / 2:3`—at a fixed 3 credits per request and does not accept reference images.

AI image model

3 credits per request

View details Use now

Nano Banana Pro

Nano Banana Pro supports text-to-image generation and reference-image editing on Kyeo AI, with 1K, 2K, or 4K output. Each 1K or 2K request costs 8 credits, while 4K costs 14. Resolution is an output-size tier, not a guarantee of quality, accuracy, or detail.

AI image generation and editing model

8–14 credits per request

View details Use now

Flux 2 Pro

Flux 2 Pro / Capabilities — Flux 2 Pro — Text-to-image and editing use the same resolution pricing: 5 credits for 1K or 7 credits for 2K. 3–5,000 characters; Up to 8 images.

AI image model

5–7 credits per request

View details Use now