Tell us anything

An idea, a bug, something you love. We read every note.

⌘↵ to send. The page you're on comes along.

Dark UI Character Sheet Evaluation

Made with GPT Image 2 in ChatGPT by Library Explainers. Promptclay never generates images.

Did it work?

No reports yet. Tell others if it worked for you.

No comments yet. Be the first.

    Dark UI Character Sheet Evaluation

    GPT Image 2AI-generated

    Prompt

    4 blanks to fill

    Using REFERENCE_0 as the source material, create a dark-mode Japanese evaluation report slide that compares attempts to generate a character sheet while preserving the same rough watercolor/ink illustration style. Goal: Turn the reference into a structured experiment-summary dashboard titled 「M2 ステップ2—ムードボードを見本に GPT でキャラクターシート」. Keep the subject as the small armored child character from the reference, but present the result as an analysis screen rather than a single illustration. Canvas and style: Use a wide 16:9 dark UI layout with charcoal background, thin dividers, rounded cards, small Japanese UI text, orange/green accent labels, and embedded white image panels. Make it look like a screenshot of an internal comparison report. Top section: Create exactly 3 comparison cards across the top. Each card contains a white character-sheet panel showing the same character in multiple views and a small detached head/bust crop. Use these card titles and edge scores: 1. 「経路A:GPT ムードボード経由」 with 「エッジ 57.6」 2. 「経路B:grok ムードボード経由」 with 「エッジ 52.6」 3. 「参考:grok キャラ直接(B-5)」 with 「エッジ 48.8」 Under each card add one short Japanese note line; the third card should mention that it is the softest and inherits the sample’s green cloth. Middle section: Add a comparison table with exactly 4 columns labeled 「条件」, 「エッジ強度」, 「コントラスト」, 「見本の欠陥」. Include exactly 7 data rows: 1. 「grok(目標)」 — 47.2 — 82.4 — 「—」 2. 「1) 共通のみ」 — 53.6 — 90.8 — 「—」 3. 「2) + 筆致(言葉)」 — 52.0 — 88.4 — 「なし」 4. 「3) + grok キャラ見本」 — 「48.8 ← 最良」 — 85.4 — 「緑の布を継承」 5. 「4) + GPT ムードボード」 — 「57.6 ← 最悪」 — 84.5 — 「なし」 6. 「5) + grok ムードボード」 — 52.6 — 87.3 — 「なし」 7. 「素材 image3.png(参考)」 — 58.8 — 69.1 — 「—」 Bottom section: Add several short Japanese conclusion lines beginning with 「結論1」 through 「結論5」, explaining that moodboard routes are not very effective, direct character reference works better, and the practical workaround is to avoid moodboards and use the Grok output with cropping. Finish with a collapsible dark bar labeled 「プロンプト(ステップ2の冒頭:ムードボードの役割指定)」. Constraints: Preserve the character identity and rough painted look from REFERENCE_0 in the embedded panels, but do not recreate the full original reference screenshot. Do not add unrelated characters. Use crisp UI typography and readable Japanese labels. The main title topic may be customized as {report_title}; the three route labels may be customized as {route_labels}; the character-sheet subject may be customized as {character_subject}; the table metric emphasis may be customized as {best_and_worst_edge_notes}.

    Works in
    ChatGPT, Gemini
    Status
    Free to copy
    0
    DetailsVersions, settings and questions

    Written for

    What's in the prompt

    Subject
    Model
    GPT Image 2

    If your face changes

    keep my face exactly the same

    Questions

    Does this work in the ChatGPT app?
    Yes. Paste the prompt and attach your photo if it uses one.
    It changed my face. What do I do?
    Add "keep my face exactly the same" to the end and run it again.
    Can I use the images I make?
    Check the terms of the app you use. Promptclay never generates images and claims nothing you make.

    Similar prompts

    See more
    • Anime Model Comparison Dashboard
    • Anime Character Generation Workflow
    • Anime TCG Card Illustration Prompt
    • Character Sheet and Illustration Generation for Bakumatsu Agents
    • Storyboard Re-Render Workflow UI
    • Image Adjustment Prompt for Nano Banana
    • Anime Story Generation Prompt Template
    • AI Chat Screenshot with Ad Design Grids
    • System Prompt for Nano Banana Pro Image Prompt Deconstruction
    • Japanese AI Prompt Gallery UI
    • Creative Dashboard UI Screenshot
    • Generating Multiple Runnable Modes/States
    • Personality Diagnostic UI Generator
    • Grok Instruction for Generating Nano Banana Pro Image Prompts
    • LLMFIT Model Loadout Dashboard
    • Japanese Plush Goods Ad Poster
    • ChatGPT Analysis Diagnosis Card
    • Improving Asymmetrical Element Identification in GPT Image 1.5
    • Cyberpunk City Parkour MV
    • LINE sticker sheet from an attached image
    • Neon Japanese AI IDE Landing Poster
    • Web3 Ecosystem Food Chain
    • Burgundy Anime Street Silhouette
    • Gritty VOTOMS-Style War Poster

    Show more

    Run it on your phone

    1. Prompt copiedRead it

      Using REFERENCE_0 as the source material, create a dark-mode Japanese evaluation report slide that compares attempts to generate a character sheet while preserving the same rough watercolor/ink illustration style. Goal: Turn the reference into a structured experiment-summary dashboard titled 「M2 ステップ2—ムードボードを見本に GPT でキャラクターシート」. Keep the subject as the small armored child character from the reference, but present the result as an analysis screen rather than a single illustration. Canvas and style: Use a wide 16:9 dark UI layout with charcoal background, thin dividers, rounded cards, small Japanese UI text, orange/green accent labels, and embedded white image panels. Make it look like a screenshot of an internal comparison report. Top section: Create exactly 3 comparison cards across the top. Each card contains a white character-sheet panel showing the same character in multiple views and a small detached head/bust crop. Use these card titles and edge scores: 1. 「経路A:GPT ムードボード経由」 with 「エッジ 57.6」 2. 「経路B:grok ムードボード経由」 with 「エッジ 52.6」 3. 「参考:grok キャラ直接(B-5)」 with 「エッジ 48.8」 Under each card add one short Japanese note line; the third card should mention that it is the softest and inherits the sample’s green cloth. Middle section: Add a comparison table with exactly 4 columns labeled 「条件」, 「エッジ強度」, 「コントラスト」, 「見本の欠陥」. Include exactly 7 data rows: 1. 「grok(目標)」 — 47.2 — 82.4 — 「—」 2. 「1) 共通のみ」 — 53.6 — 90.8 — 「—」 3. 「2) + 筆致(言葉)」 — 52.0 — 88.4 — 「なし」 4. 「3) + grok キャラ見本」 — 「48.8 ← 最良」 — 85.4 — 「緑の布を継承」 5. 「4) + GPT ムードボード」 — 「57.6 ← 最悪」 — 84.5 — 「なし」 6. 「5) + grok ムードボード」 — 52.6 — 87.3 — 「なし」 7. 「素材 image3.png(参考)」 — 58.8 — 69.1 — 「—」 Bottom section: Add several short Japanese conclusion lines beginning with 「結論1」 through 「結論5」, explaining that moodboard routes are not very effective, direct character reference works better, and the practical workaround is to avoid moodboards and use the Grok output with cropping. Finish with a collapsible dark bar labeled 「プロンプト(ステップ2の冒頭:ムードボードの役割指定)」. Constraints: Preserve the character identity and rough painted look from REFERENCE_0 in the embedded panels, but do not recreate the full original reference screenshot. Do not add unrelated characters. Use crisp UI typography and readable Japanese labels. The main title topic may be customized as {report_title}; the three route labels may be customized as {route_labels}; the character-sheet subject may be customized as {character_subject}; the table metric emphasis may be customized as {best_and_worst_edge_notes}.

    2. Open your app

      This prompt is long, so it is copied instead of sent in the link. Paste it in the app.

    3. Paste and run

      Press and hold the message box, then tap Paste. Add your photo first if the prompt uses one. You may need to sign in.

    Dark UI Character Sheet Evaluation