IP
Three Character Asset Comparison Board preview image
Primary reference image
GPT Image 2 casePortrait & CharacterMulti Image to Image1 ref

Three Character Asset Comparison Board

Generates a 16:9 comparison board of three realistic character asset sheets across two model columns, useful for visual AI output comparisons.

This is a GPT Image 2 prompt case for Portrait & Character. Use the copy-ready prompt below to generate similar visuals, and review Awesome GPT Image 2 Prompts attribution plus commercial-use rights before reuse.

Need the full prompt set? Use the Portrait & Character topic hub for more related examples, or open the GPT Image 2 prompt library for the full example index, reusable structures, and source attribution.

This prompt is designed for multiple reference images. We will open Dovoo with the prompt and the available preview image; add the remaining references in Dovoo before generating.

Free 1K preview

Generate one preview image instantly, no sign-up required.

…

Free text preview doesn’t preserve reference-image consistency.

3452/4000
Continue on Dovoo

Prompt

Copy-ready prompt

Objective: Create a dark-background comparison project showcasing character asset sheets of three professionally dressed individuals, side-by-side comparison of two image generation systems.

Canvas: 16:9 landscape demonstration image, resolution approximately 2048×1152, using a dark navy-black background, simple white text, and 6 large white image panels arranged in a 3-row, 2-column grid.

Title Text: Place a large Chinese title {argument name="headline text" default="3 sets of female character assets · Comparison with the same prompt"} in the upper left corner. Add a smaller subtitle line below it: {argument name="comparison subtitle" default="Left: Historical GPT Image 2    Right: ChatGPT Images 2.5 Web"}.

Layout: Use 6 rectangular white panels with narrow spacing: the left column represents the old model, and the right column represents the new model. There are 3 rows of characters: Clara, Julian, and Evelyn. Each row has a small Chinese row label above the left panel: “Pure Text Character Asset - Clara”, “Pure Text Character Asset - Julian”, and “Pure Text Character Asset - Evelyn”. Each of the 6 panels contains 4 character depictions on a white studio background: 1 large head and shoulder close-up on the left, and 3 smaller full-body turnarounds on the right: front view, side view, and back view. The total number of visible character depictions: exactly 24.

Row 1 Subject Details: Clara, a young, fair-skinned woman with long wavy dark brown hair, subtle natural makeup, a neutral and serious expression, wearing a cream-colored ribbed turtleneck sweater, a brown short blazer, high-waisted wide-leg cream-colored trousers, a black belt, and low heels. Show 4 views in each Clara panel: head close-up, full body front, full body side, full body back.

Row 2 Subject Details: Julian, a young, slender, fair-skinned man with light brown/golden side-parted hair, wearing rectangular glasses, a calm and serious expression, wearing a beige linen suit, a white open-collar shirt, slim-fit trousers, a brown belt, and brown loafers. Show 4 views in each Julian panel: head close-up, full body front, full body side, full body back.

Row 3 Subject Details: Evelyn, a middle-aged woman, medium skin tone, dark hair styled in a low bun, a steady and neutral expression, wearing a black business suit, a dark gray shirt, a small gold necklace, small earrings, black trousers, and black flats. Show 4 views in each Evelyn panel: head close-up, full body front, full body side, full body back.

Visual Style: Realistic photographic style character asset sheet, clean studio lighting, white seamless background within each panel, consistent professional clothing styling, neutral expressions, no decorative graphics except for the dark project background and labels. The left and right columns should look similar but not identical, as if comparing the outputs of two systems.

Footer Text: Add two Chinese annotations in the lower left corner: {argument name="footer note one" default="Historical finished product 2048×1152 / Web new image 1672×941 · Only layout scaling, no retouching, no upscaling."} and {argument name="footer note two" default="The prompt body is the same, with only 16:9 aspect ratio added to both pages."}.

Constraints: Maintain the precise 3-row, 2-column comparison layout, exactly 3 named characters, exactly 6 panels, exactly 4 depictions per panel, no watermarks, no extra logos, and no other characters.

Prompt variables

Editable argument placeholders found in the prompt, with their default values.

4
Variable
headline text
Default
3 sets of female character assets · Comparison with the same prompt
Variable
comparison subtitle
Default
Left: Historical GPT Image 2 Right: ChatGPT Images 2.5 Web
Variable
footer note one
Default
Historical finished product 2048×1152 / Web new image 1672×941 · Only layout scaling, no retouching, no upscaling.
Variable
footer note two
Default
The prompt body is the same, with only 16:9 aspect ratio added to both pages.

Best for

  • - Portrait & Character visual exploration
  • - Image generation and reference-image edits
  • - Reusable briefs that keep source attribution visible

Change these parts

  • - Subject, product, character, or scene
  • - Aspect ratio, camera, lighting, and background
  • - Brand, text, color, and output constraints

Recommended model and settings

  • - Model: gpt-image-2
  • - Input mode: Multi Image to Image
  • - Aspect ratio: source
  • - Commercial status: review original source

How to use this prompt

  1. 1. Copy the prompt and preserve its structure for the first test.
  2. 2. Replace the subject, context, and publishing channel.
  3. 3. Change one camera, lighting, or style variable per iteration.
  4. 4. Inspect the output, source, text, and rights before reuse.

Limitations, source, and reuse cautions

  • - Generated output is an editable draft, not factual, legal, or rights evidence.
  • - Review the linked source, people, brands, logos, text, and third-party media before commercial use.
Imported from Awesome GPT Image 2 Prompts. Attribution is required. Commercial-use status is allowed; review source rights before paid usage.

More cases in this category

Prioritized by category, input mode compatibility, quality, and lower risk.

6

Reuse and source notes

Use this prompt safely after previewing the case.

  1. 1.Copy the prompt or open it directly in Dovoo with the generation button.
  2. 2.Adjust variables, aspect ratio, and reference images for your own use case.
  3. 3.Before publishing or paid usage, verify source rights, attribution requirements, and brand or likeness risks.

Can I use this prompt commercially?

Commercial-use status is allowed. Review the original source, license, brand constraints, and legal requirements before paid usage.

Where does this case come from?

This case is imported from Awesome GPT Image 2 Prompts; keep attribution visible and check the source URL before reuse.

Adults only

Want uncensored prompts, chat, and generation?

Everything on this site stays safe-for-work. For no-filter NSFW AI chat and image / video generation, continue on Stella AI.

No-filter AI chat, image, and video generation on Stella AI.