// STYLE & PROMPTING GUIDE

Image styles for AI agents.

Ten verified prompt recipes, each rendered live by MCP Media Engine itself. Pick a look, copy the fragment into your subject line, and ship. Every recipe was generated on production using a constant subject so the style fragment is the only variable — the fidelity you see is the fidelity you get.

Looking for the API contract? See the API reference. New to MED? Start at the quickstart.

The prompt recipe

Every prompt is the same four parts in order. Style is just the second slot.

subject + style fragment + lighting / mood + constraints
  • subject — what the image is of (the "a lighthouse on a rocky coast at dawn" we used).
  • style fragment — medium + technique (copy from the gallery below).
  • lighting / mood — "dramatic natural light", "soft studio lighting", "atmospheric haze".
  • constraints — exclusions baked into the prompt text, e.g. "no text, no words, no logos".

Important: the Default Image model does not honor a separate negative_prompt field at submit time. Always bake exclusions into the prompt text. The Premium Image model does support it natively if you need it.

aspect_ratio values

Pass aspect_ratio in inputParams. All values below are verified live against production (MED-1127, 2026-07-11).

1:1Avatars, social tiles, square thumbnails.
16:9Default hero / blog banner.
9:16Vertical social, Stories, Reels.
21:9Cinematic ultra-wide.
9:21Vertical ultra-wide.
3:2Classic 35mm still.
2:3Portrait, posters.
5:4Fine-art print.
4:5Instagram portrait.
4:3Classic monitor.
3:4Tall portrait.

Style gallery

Photorealistic style example: Camera-like depth and natural light.

Photorealistic

Default Image · 1 cr · 16:9

Camera-like depth and natural light.

Best for: Hero images, blog headers, social cards.

prompt fragment

photorealistic, dramatic natural light, shallow depth of field

constraints (bake into prompt)

no text, no words, no logos

job: mjob_0ca0371e-180c-46b0-8327-efc908e10d48 · 51,490B webp

Black & White Archival style example: 1930s documentary photograph feel.

Black & White Archival

Default Image · 1 cr · 4:5

1930s documentary photograph feel.

Best for: Editorial portraits, history pieces, somber tones.

prompt fragment

black and white archival photograph, 1930s documentary style, film grain, high contrast

constraints (bake into prompt)

no text, no words, no logos

job: mjob_226ba628-b186-4dc0-bc35-70a179881d73 · 72,344B webp

Pencil Sketch style example: Hand-drawn crosshatching on sketchbook paper.

Pencil Sketch

Default Image · 1 cr · 4:5

Hand-drawn crosshatching on sketchbook paper.

Best for: Concept illustrations, how-to diagrams, dev docs.

prompt fragment

loose pencil sketch, hand-drawn crosshatching, monochrome, sketchbook page

constraints (bake into prompt)

no text, no words, no logos

job: mjob_06008907-819b-40f5-8b3f-818d4bb73074 · 170,692B webp

Cartoon Illustration style example: Bold outlines, flat vibrant colors.

Cartoon Illustration

Default Image · 1 cr · 16:9

Bold outlines, flat vibrant colors.

Best for: Landing-page mascots, explainer graphics, kids content.

prompt fragment

playful cartoon illustration, bold outlines, flat vibrant colors

constraints (bake into prompt)

no text, no words, no logos

job: mjob_b07b099b-80a7-45b1-8aae-78c11b2bfdc2 · 97,122B webp

Watercolor style example: Wet-on-wet washes with paper texture.

Watercolor

Default Image · 1 cr · 4:5

Wet-on-wet washes with paper texture.

Best for: Lifestyle pieces, soft product photography mood.

prompt fragment

soft watercolor painting, wet on wet, paper texture, gentle washes, painterly

constraints (bake into prompt)

no text, no words, no logos

job: mjob_ac97917e-04f5-4a4e-8404-0c3b70776460 · 174,640B webp

Flat Vector / Minimalist style example: Clean geometric shapes, limited palette.

Flat Vector / Minimalist

Default Image · 1 cr · 16:9

Clean geometric shapes, limited palette.

Best for: SaaS landing pages, fintech explainers, dashboard art.

prompt fragment

flat vector illustration, minimalist, clean geometric shapes, limited palette, modern poster style

constraints (bake into prompt)

no text, no words, no logos

job: mjob_898aaced-d3b2-49f8-8ffb-c48f5f00f22b · 15,368B webp

Isometric 3D style example: Low-poly clay diorama, soft studio lighting.

Isometric 3D

Default Image · 1 cr · 16:9

Low-poly clay diorama, soft studio lighting.

Best for: Product mockups, architecture explainers, tech ads.

prompt fragment

isometric 3D render, soft studio lighting, low-poly, clay material, cozy diorama

constraints (bake into prompt)

no text, no words, no logos

job: mjob_1d3f2dee-df90-438a-a57d-395ff47f51be · 39,598B webp

Cinematic Film Still style example: Anamorphic widescreen, teal-and-orange grade.

Cinematic Film Still

Default Image · 1 cr · 21:9

Anamorphic widescreen, teal-and-orange grade.

Best for: Article heroes, video thumbnails, banner ads.

prompt fragment

cinematic film still, anamorphic lens, teal and orange color grade, atmospheric haze, wide shot

constraints (bake into prompt)

no text, no words, no logos

job: mjob_e1735b8a-9652-47cc-b69c-c16913b8c247 · 22,116B webp

Retro Travel Poster style example: 1950s offset print, halftone, heroic composition.

Retro Travel Poster

Default Image · 1 cr · 2:3

1950s offset print, halftone, heroic composition.

Best for: Vertical social posts, posters, event promos.

prompt fragment

vintage travel poster, 1950s offset print, bold flat color blocks, screen-print halftone, heroic composition

constraints (bake into prompt)

no text, no words, no logos

job: mjob_cdb28822-7f3e-4cb8-81f5-be008c52d992 · 156,512B webp

Line Art style example: Single continuous contour, pen on white.

Line Art

Default Image · 1 cr · 1:1

Single continuous contour, pen on white.

Best for: Avatars, favicons, dividers, minimalist branding.

prompt fragment

single continuous line art, minimalist drawing, elegant pen on white, unbroken contour

constraints (bake into prompt)

no shading, no text, no words, no logos

job: mjob_3e887e95-8cc6-484d-8a8e-67f8504a0317 · 21,002B webp

Model selection

Two image models. Pick by budget and need. Discover live at GET /api/models.

Default Image1 cr · fastAll ten recipes above use this model. Honors prompt, aspect_ratio, cfg_scale, steps, input_image, face_swap, inpaint_faces, style, color_grading, film_grain.
Premium Image4 cr · strict adherenceUse for text-in-image, strict prompt adherence, or negative_prompt. Supports prompt, quality, num_images, aspect_ratio, negative_prompt, cfg_scale, steps.

Submit any style with POST /api/jobs — see the API reference for the request shape.

Frequently asked

How do I get a black-and-white archival look?
Append the fragment 'black and white archival photograph, 1930s documentary style, film grain, high contrast' to your subject. Use aspect_ratio 4:5 and the Default Image model (1 credit). Bake the constraint 'no text, no words, no logos' into the prompt itself — the default image model does not accept a separate negative_prompt parameter.
How do I get a photorealistic image?
Use 'photorealistic, dramatic natural light, shallow depth of field' as the style fragment with aspect_ratio 16:9 and the Default Image model. This is the most common hero-image recipe and costs 1 credit.
How do I make a cartoon or illustrated version?
Append 'playful cartoon illustration, bold outlines, flat vibrant colors'. Default Image model, 1 credit, aspect_ratio 16:9 for banners or 4:5 for portraits.
How do I get a watercolor look?
Use the fragment 'soft watercolor painting, wet on wet, paper texture, gentle washes, painterly'. Avoid adding 'illustration' — the painterly quality comes from explicit paper/wash cues.
How do I render a flat vector or minimalist look?
Use 'flat vector illustration, minimalist, clean geometric shapes, limited palette, modern poster style'. Best for SaaS landing pages and dashboard art.
How do I get a 3D isometric look?
Append 'isometric 3D render, soft studio lighting, low-poly, clay material, cozy diorama'. The 'low-poly clay' qualifier keeps the result lightweight instead of photoreal 3D.
How do I make a cinematic film still?
Use 'cinematic film still, anamorphic lens, teal and orange color grade, atmospheric haze, wide shot' with aspect_ratio 21:9. Great for article heroes and video thumbnails.
How do I get a vintage travel-poster feel?
Use 'vintage travel poster, 1950s offset print, bold flat color blocks, screen-print halftone, heroic composition' with aspect_ratio 2:3.
Why can't I just use a negative_prompt parameter?
On the Default Image model, a separate negative_prompt field is accepted at submit but causes the job to fail at generation. Always bake exclusions into the prompt text itself ('no text, no words, no logos'). The Premium Image model (gpt-image-2, 4 credits) does support negative_prompt natively if you need it.
Which model should I use for text-in-image or strict prompt adherence?
Use the Premium Image model (4 credits) — it has stronger prompt adherence and renders in-image text. The Default Image model (1 credit) is faster and cheaper for everything else. See GET /api/models for the live catalog.

Pick a style and ship your next image.