RaphaelRaphael AI

GPT IMAGE 2.6 Prompts

130+ curated examples · copy and generate

Reference Images (Optional)
0 / 10,000
AI Enhance
Model
Aspect Ratio
Output Number
Resolution
Quality
Planning intensity
Output Format
  • Native GIF output
  • SVG vector output
  • Up to 4K
  • Up to 16 reference images
  • Accurate text rendering
  • Consistent characters
  • Mark-up edits

Prompts that move

GIF LAB

Stickers, product loops and pixel animations. Pick one and generate it in Raphael.

View all GIFs
TOP 1

Roaring duck

@ailingqu

Pixel knight run cycle

@ailingqu

Confused shiba head tilt

@ailingqu

Cat typing furiously

@ailingqu

Pixel art campfire

@ailingqu

Pelican riding a bicycle

@SSHCodes

Dwarf game model rotating 360 degrees

@xikhar

Penguin facepalm

@ailingqu

White bunny reaction sticker set

@ailingqu

Sneaker colorway flash

@ailingqu

Markup edits prompts

Total 10
Markup editsCommunity

Photo-to-folk-art Christmas greeting cards

@Goodmanprotocol

Transform the uploaded photograph into a beautiful, contemporary hand-drawn naïve Christmas illustration, inspired by premium vintage holiday greeting cards and modern folk-art poster design. ART STYLE: - Authentic hand-drawn illustration with a charming, playful naïve-art aesthetic. - Slightly exaggerated, whimsical proportions. - Imperfect, irregular outlines and organic hand-drawn contours. - Simplified shapes with carefully selected decorative details. - Flat, bold, contrasting colours with a warm Christmas palette. - Subtle vintage paper texture with a refined printed-card finish. - Delicate hand-drawn decorative marks, patterns and festive accents. - Minimalist yet visually rich composition. COLOUR PALETTE: Use traditional Christmas colours: deep forest green, warm red, cream, muted beige, golden yellow and earthy brown. Maintain strong colour contrast and a cohesive vintage aesthetic. PRESERVE THE ORIGINAL PHOTOGRAPH: Retain the person's recognisable facial features, hairstyle, clothing, pose, expression and body proportions. Preserve the main objects, their arrangement and the essential details of the original environment. Translate everything into the illustrated style rather than replacing it with unrelated elements. DESIGN & COMPOSITION: Create an elegant, charming Christmas postcard illustration. Simplify the background into tasteful decorative shapes while retaining recognizable elements from the original photograph. Add small festive decorative details only where they naturally complement the existing scene. STRICT VISUAL RULES: - No photorealism. - No 3D rendering. - No realistic lighting or shadows. - No gradients. - No glossy or metallic effects. - No artificial digital painting appearance. - No excessive detail or visual clutter. The final result should look like an authentic, professionally illustrated Christmas greeting card, with the charm of handmade folk art and the sophistication of a premium designer postcard. FORMAT: A6 portrait orientation, 2:3 aspect ratio, print-ready composition.

Markup editsCommunity

Circle markup edit adding Santa hat and gift

@IHayato

Red circle with Santa hat, blue circle book into gift

Markup editsOfficial

Recolor a marked vase

@OpenAI

Recolor the striped vase inside the red circle to solid cobalt blue ceramic. Keep its shape, the dried stems, and the rest of the kitchen unchanged. Remove the red circle from the finished photo.

Markup editsOfficial

Translate an infographic into Spanish

@OpenAI

Translate the text in the infographic to Spanish. Do not change any other aspect of the image.

Markup editsOfficial

Transfer a pixel-art style

@OpenAI

Use the same style from the input image and generate a man riding a motorcycle on a white background.

Markup editsOfficial

Combine pets across images

@OpenAI

Place 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.

Markup editsOfficial

Turn a sketch into a realistic scene

@OpenAI

Turn this drawing into a photorealistic image. Preserve the exact layout, proportions, and perspective. Choose realistic materials and lighting consistent with the sketch intent. Do not add new elements or text.

Markup editsOfficial

Remove a held flower

@OpenAI

Remove the flower from man's hand. Do not change anything else.

Markup editsOfficial

Change the billboard scene to a snowy night

@OpenAI

Make it look like a winter evening with snowfall.

Markup editsCommunity

Webinar date replacement comparison

@石原

Replace the date and time with 「2027年1月21日（木）」. Do not change anything else.

GPT Image 2.6 prompt collection

130 GPT Image 2.6 prompts with their real outputs, collected from OpenAI's documentation, launch materials and community creators, and synced from the open-source awesome-gpt-image-2-6 repository.

Cases come from the authors' published original prompts and are localized into your language while keeping in-image text unchanged — never descriptions reverse-engineered from images. Cards mark whether a case is official or from the community, and each detail view lets you inspect the original prompt and source.

Use it in Raphael

Copy a prompt and swap in your own subject and style. For cases marked "Needs an image", add your own image first. The generator at the top of this page uses GPT Image 2.6 Sunburst by default.

Try the generator →

Sunburst or Flare?

VersionBest for
GPT Image 2.6 SunburstDetailed creation and photo editing, such as adjusting objects, lighting and scene details. The generator on this page uses it by default.
GPT Image 2.6 FlareEveryday creation and quick drafts, such as portraits, explainer diagrams and presentation visuals; it can also edit from reference images.

Both support text-to-image and image-to-image, up to 4K, five quality levels, three planning levels and up to 16 reference images.

Editing photos and backgrounds

Before editing a portrait or product shot, decide what must not change, such as facial features, the product's shape or the text on its packaging, and say so in the prompt. Start detail-heavy edits with Sunburst.

Text in posters and images

Put the exact words in quotes and say where they go and in what style. Shorter text is easier to get right. Both versions can render text; still proofread every word before publishing.

Making GIFs and SVGs

Click "Try now" on any GIF case to load the prompt straight into the generator above in GIF mode (2 to 16 frames at 0.2 seconds each); for vector files, use the AI SVG Generator to output SVG directly.

Actual results and generation time depend on the request. The generate button shows the credits a request needs before you run it.

FAQ

Common questions about GPT Image 2.6 prompts and generation

1

Are these the original prompts? Where do they come from?

Yes. Cases come from OpenAI's documentation, launch materials and community creators, curated in the open-source awesome-gpt-image-2-6 repository. Prompts are localized into your language while keeping in-image text intact, and every detail view lets you toggle the author's original prompt and open its source link.

2

Why does my result look different from the example?

The same prompt gives a different result every time, and the author may have used other quality settings or reference images. Generate a few times, or swap in your own subject and style. For multi-step cases, follow the steps in order and use each result as the reference for the next step.

3

How do I use cases marked "Needs an image"?

These prompts were written around reference images, for example placing the person from a photo into a poster. Upload your own images in the generator first (up to 16), then paste the prompt. The detail view shows the references the author used.

4

How do I make a GIF with GPT Image 2.6?

Click "Try now" on any case in GIF Lab or any GIF card on this page — the prompt loads straight into the generator at the top in GIF mode, where you can pick 2 to 16 frames (0.2 seconds each) and generate, or start from scratch in the AI GIF Generator.

5

How can I get more accurate text in images?

Put the words in quotes, keep them short, and say where they go and in what font style; avoid too many text blocks in one image. Proofread the result, and fix a single wrong word with a local edit.

6

How many credits does a generation cost?

It depends on quality, size and the number of reference images, and for GIFs on the frame count. The generate button shows the exact credits before you run it.

More tools

READY TO CREATE?

Use an example prompt or enter your own idea to generate images with GPT Image 2.6 in Raphael.

Start generating →