GoodCase.aiAI News · Radar↗AI Map↗Course · LearnPrompt↗
ProjectsGoodCase.aiAI News Radar ↗AI Map ↗LearnPrompt ↗
GoodCase.aiGoodCase.aiAI Prompt Case Collection
GoodCase.ai
RankingsCasesSkillsFavoritesSubmitDailyJoin us
中文EN
Agent Access →

Projects

AI News · Radar ↗AI Map ↗Course · LearnPrompt ↗
GoodCase.aiGoodCase.aiAI Prompt Case Collection
RankingsCasesSkillsFavoritesSubmitDailyJoin us
中文EN
Agent Access →

Loading…

GoodCase.ai · AI Prompt Case Collection
DSH PluginsChangelogFeedback
ModelsCreatorsSeedance 2.5Seedance 2.0GPT Image 2GeminiNano Banana ProClaudeClaude Opus 5.5Grok ImagineVeoKlingQwen ImageGPT Image 1.5MiniMax H3
Character Identity Reference Sheet

Character Identity Reference Sheet

Creator · Mrpinecone888

AI ImageX2026-07-30Added 08/04/2026Independently retested#human-reviewed
More tags (1)
GPT Image 2
View original source ↗
Source ♥ 1.1k

Prompt

Based on the attached original character image, create a "Character Identity Fixed Reference Chart": landscape orientation 16:10, light gray-white background, professional visual reference board layout. The primary goal is for all panels to instantly read as the exact same character, not several similar-looking people.

Treat the character identity from the reference image as a hard, unchangeable constraint. Strictly lock:
- Facial width-to-height ratio, cheekbones, cheeks, jaw, and chin
- Eye contour, eye spacing, eyelid structure, and gaze quality
- Eyebrow arch, thickness, color, and brow-to-eye distance
- Nose bridge, nose tip, nostrils, and profile nose shape
- Upper and lower lip thickness, cupid's bow, mouth corners, and natural lip color
- Skin tone, pores, blood undertone, and natural skin texture
- Hairline, part, bangs, side hair, back hair length, and hair flow direction
- Age impression, bone structure, shoulder width, limb length, and overall body type
- Original outfit, original art style, lighting texture, and overall atmosphere

In the center of the frame, display in larger panels:
- Full body front
- Full body side
- Full body back
- Face front
- Left profile
- Right profile
- Left three-quarter
- Right three-quarter
- Back of head

Each angle must maintain an identical skull structure, relative facial feature positions, hair volume, and body proportions. The side profile must accurately continue the nose bridge, lips, chin, and forehead structure from the front view — generating a side profile that reads as a different person is prohibited.

On the right side, arrange a small expression matrix:
- Neutral
- Smiling
- Serious
- Surprised
- Shy
- Thinking
- Troubled
- Slightly sad
- Calm

Keep the same pupils, base eye size, nose shape, lip shape, and face shape. The smile should be natural and restrained, without changing the character's age or temperament.

At the bottom, arrange fine-grained identity anchors:
- Left eye
- Right eye
- Eyebrows
- Nose front
- Nose side
- Lips
- Ears
- Jawline
- Skin texture
- Bangs structure
- Side hair structure
- Back hair structure
- Hair-tip flow
- Hands

On the left side, add 5-7 accurate color swatches: hair color, eye color, skin tone, lip color, outfit color, shadow color, and overall tone. Add a minimal "fixed points" note: face shape fixed, eye area fixed, nose shape fixed, lips fixed, bangs fixed, body type fixed, outfit unified, same character prioritized.

Clean background, soft even lighting, no cinematic lighting, strong depth of field, or decorative elements. For photorealistic characters, preserve natural pores, fine hairs, and subtle skin-tone variation; for non-photorealistic characters, strictly preserve the original lines, color blocks, shadows, and materials — do not switch styles on your own.

All labels must use clear Simplified Chinese only, moderate font size, not covering the character. If layout space is insufficient, prioritize keeping identity anchors and the main angles, reduce duplicate panels, and do not shrink text or sacrifice character consistency to force everything to fit.

Negative prompt: different person, similar face but not the same person, identity drift, face swap between panels, face shape drift, eye spacing change, pupil change, eyebrow shape change, nose bridge change, nose tip change, lip shape change, chin change, hairline change, bangs change, part change, hair color change, hair length change, body type change, age change, outfit change, excessive beautification, skin smoothing, plastic skin, baby face, sexualization, underwear, swimwear, magazine photoshoot look, cinematic lighting, exaggerated poses, props, complex background, English text, garbled text, fake Chinese characters, watermark, logo, signature, extra fingers, missing fingers, fused hands, misplaced facial features, broken side profile, overlapping faces, body distortion, style shift, layout chaos.
≡Provenance · verifiedPublished prompts are human-checked against the original post; platform-reconstructed prompts are not accepted.Compare with source ↗

Models & stability

Recommended models

GPT Image 2
Stability
74 / 100
Cost
Medium
Related SkillsCharacter and style consistency ↗

Independent retest evidence

See what the same prompt generated in our test.

Retest output · not the creator's original
ImageGenerated evidenceAI judged

Grok Imagine

Sep 2, 2026

Retest score74
Generated retest result
claude-sonnet-5 · 73.7gpt-5.6-sol · 74.3gap · 0.6
  • Cross-model retest: the recommended model is GPT Image 2, and this run used Grok Imagine. The result shows how the same prompt carries over to Grok Imagine; it does not show what the creator got with the original model.
  • The retest score is the mean of two AI judges (0–100) for this single generation. No person has reviewed it, and it is not a success rate.

The requested model is recorded, but the generation receipt did not expose a verifiable underlying model ID.

ImageGenerated evidenceAI judgedIndependent run 2/2

GPT Image 2

Aug 9, 2026

Retest score77.6
Generated retest result
claude-sonnet-5 · 85.1gpt-5.6-sol · 70.1gap · 15
  • Same model family as recommended (GPT Image 2). Settings the creator used beyond the prompt are not known.
  • The retest score is the mean of two AI judges (0–100) for this single generation. No person has reviewed it, and it is not a success rate.

The requested model is recorded, but the generation receipt did not expose a verifiable underlying model ID.

GPT Image 2: 2 independent runs · show 1 earlier
ImageGenerated evidenceIndependent run 1/2

GPT Image 2

Aug 6, 2026

Generated retest result
  • Same model family as recommended (GPT Image 2). Settings the creator used beyond the prompt are not known.

The requested model is recorded, but the generation receipt did not expose a verifiable underlying model ID.

Keep exploring

Explore related cases.

View all AI Image Case →
Character Combat Action Sprite Sheet
AI ImageXAdded 09/15/2026

Character Combat Action Sprite Sheet

A prompt for creating animation-ready pixel art sprites. It tells the model to produce a 16-frame grid of combat actions such as punches and kicks from a character image reference.

Skill · Character and style consistency

Prompt

このキャラクターの戦闘モーションのスプライトシートを作って。{argument name="サイズ" default="128px"}の簡略化された{argument name="画風" default="pixelart"}、4x4=16コマ、背景は透過。{argument name="アクション内容" default="構え4/パンチ4/キック4/被弾4

Source heat · X
93
Stability
62
View case →
Watercolor-Style Editorial Illustration Poster
AI ImageXAdded 08/30/2026

Watercolor-Style Editorial Illustration Poster

A GPT Image 2 prompt that transforms each uploaded photo into a split-screen design, with the original image on top and a vintage watercolor illustration below.

Skill · Character and style consistencySkill · Poster information hierarchy

Prompt

Turn each photo I upload into a separate premium design poster. Do not combine multiple images; output each photo separately. Use an overall 3:4 vertical composition divided into two regions with a strict 1:1 height ratio, each occupying 50

Source heat · X
86
Stability
66
View case →
Tribal Fantasy Warrior Woman With an Owl Portrait
AI ImageXAdded 09/01/2026

Tribal Fantasy Warrior Woman With an Owl Portrait

A highly detailed fantasy prompt for a portrait of a tribal woman warrior with a giant, majestic owl against a mysterious forest background.

Skill · Character and style consistencySkill · Editorial portrait composition

Prompt

A detailed portrait of a fierce tribal fantasy warrior woman leaning close to a massive, majestic great horned owl, cinematic lighting, dark moody atmosphere. The woman has {argume

Source heat · X
43
Stability
89
View case →

Same model

Latest with GPT Image 2 →

  • A Photograph Flows into an Ivory Paper Collage WorldAI Image · GPT Image 2.5 · 2026-11-03
  • Cartoon Young Man with Black Glasses on a Mustard Yellow BackgroundAI Image · GPT Image 2.5 · 2026-11-01
  • Playful Selfies of a Black-Haired Woman in a Phone GalleryAI Image · GPT Image 2.5 · 2026-11-01
  • Retro Cartoon Teen with Glasses and a CameraAI Image · GPT Image 2.5 · 2026-11-01
  • Close Portrait of a Woman in White and a Baseball Cap by the SeaAI Image · GPT Image 2.5 · 2026-10-29
  • Woman in Sunglasses Stands in Platform Wind as a Train Rushes PastAI Image · GPT Image 2.5 · 2026-10-28

Each detail page keeps the original result, the prompt, and retest evidence in one reading path.