Goal: Create a vertical Chinese promotional infographic poster about unlocking comic creation logic with GPT-2, using a playful hand-drawn editorial style.
Fields you can change: headline text, subheadline text, tagline, card one label.
Full prompt
Goal: Create a vertical Chinese promotional infographic poster about unlocking comic creation logic with GPT-2, using a playful hand-drawn editorial style.
Canvas: Portrait 3:4 poster, warm off-white textured paper background, soft pastel palette, slightly grainy risograph print texture, rounded friendly shapes, dark teal headline typography, coral accent text, pale green/yellow/pink/lavender section cards.
Layout: Left side is a bold text-heavy headline and feature list; right side is a large illustration of an open padlock with a glowing keyhole releasing comics, sketches, speech bubbles, arrows, and diary pages. Bottom right has an open comic book, with pages and comic panels swirling upward from it into the lock area. Keep generous margins and a lively but readable composition.
Text content: Use a large Chinese headline at top left: {argument name="headline text" default="漫画的\n创作逻辑"}. Under it, add smaller bold Chinese copy: {argument name="subheadline text" default="就这么水灵灵的被\nGPT-2 解锁了"}, with “GPT-2” in large coral red and the rest in dark teal/black. Add a green underline and smaller line: {argument name="tagline" default="这个思路,真是让人好生喜欢"}. Include small decorative coral sparkle marks and a hand-drawn heart near the tagline.
Feature cards: Place exactly 4 rounded horizontal cards stacked vertically on the lower left, each with one circular icon on the left and bold Chinese label on the right. Card 1 is pale green with an open notebook and pencil icon, label {argument name="card one label" default="日记转"}. Card 2 is pale yellow with a lightbulb rising from an open book icon, label “知识转”. Card 3 is pale peach with a steaming mug icon containing a heart, label “鸡汤转”. Card 4 is pale lavender with a paper airplane icon, label “各种转换,\n玩的飞起”. From each of the 4 cards, draw one dotted arrow pointing right toward the flying comic materials; use matching muted arrow colors.
Right-side subject details: Draw exactly 1 oversized open padlock in muted green-gray, positioned upper right, with chalk-like doodles on its body: tiny speech bubbles, comic thumbnails, and simple character sketches. Insert exactly 1 golden key into the keyhole; the key has a fountain-pen nib as its handle, symbolizing writing unlocking comics. Make the keyhole glow with warm yellow light.
Flying comic materials: Show exactly 6 loose paper/comic elements floating from the open book toward the lock: 1 small portrait sketch sheet, 1 four-panel comic page, 1 single-page layout with a yellow image block, 1 two-character dialogue comic page, 1 small pink note page, and 1 larger horizontal comic strip page. Add curved motion trails, sparkles, tiny hearts, arrows, and speech bubbles around them, but keep the main count of loose sheets exactly 6.
Bottom illustration: Draw exactly 1 open comic book at the lower right with visible comic panels and a cute simple character on the left page; use thin dark teal linework and pale yellow highlights. Add soft cloud-like pale green shapes along the bottom edge of the poster.
Visual style: Cute Chinese social-media poster aesthetic, hand-drawn line art, rounded sans-serif Chinese typography, vintage print grain, pastel accents, clean hierarchy, whimsical educational tone.
Constraints: Maintain the exact 4 feature cards and exact 6 loose flying paper/comic elements. Do not add extra major sections, extra logos, watermarks, QR codes, or English explanatory text beyond “GPT-2”.
Analyze the entire composition of the input image. Identify all key subjects present (whether a single person, group/couple, vehicle, or specific object) and their spatial relationships/interactions.
Generate a coherent 3×3 “contact sheet” grid that shows 9 different shots of exactly these subjects within the same environment.
You must adapt standard cinematic shot types to fit the content (for example, if it’s a group, keep the group together; if it’s an object, frame the entire object):
Row 1 (establishing the environment):
Extreme long shot (ELS): the subject appears small within a vast environment.
Long shot (LS): the full subject or group is visible from top to bottom (head to toe / wheels to roof).
Medium long shot (American shot / three-quarter): framed from above the knees (for people) or a 3/4 view (for objects).
Row 2 (core coverage):
4. Medium shot (MS): framed from the waist up (or the central core of an object). Focus on interaction/action.
5. Medium close-up (MCU): framed from the chest up. An intimate framing of the main subject.
6. Close-up (CU): tightly framed on the face or the “front” of the object.
Row 3 (details and angles):
7. Extreme close-up (ECU): intense focus on key features (eyes, hands, signs, textures) with macro-like detail.
8. Low-angle shot (worm’s-eye): look up at the subject from ground level (epic/heroic feeling).
9. High-angle shot (bird’s-eye): look down on the subject from above.
Ensure strict consistency: the same person/object, same clothing, and same lighting must appear in all 9 panels. Depth of field should vary realistically (with background blur in close-up shots).
Create a professional 3×3 cinematic storyboard grid with 9 panels.
The grid should present a specific subject/scene from the input image across a full range of focal lengths.
Top row: wide environmental shot, full-body view, 3/4 cropped (knees-up).
Middle row: waist-up view, chest-up view, face/front close-up.
Bottom row: macro details, low angle, high angle.
All frames must have photo-realistic textures, consistent cinematic color grading, and correct framing tailored to the number and type of subjects or objects being analyzed.
Put this whole text, verbatim, into a photo of a glossy magazine article on a desk, with photos, beautiful typography design, pull quotes, and bold formatting. The text: {argument name="article_text_en" default="[paste the full unformatted article here]"}
Create decorative text based on the word "{argument name="word" default=""}". Write the specified word largely and create decorative text designs associated with the image of the word. Create original designs with flexible ideas, without being constrained by existing fonts. The background should be a single color, white or black, matching the design.