ian-xiaohei-cat-illustrations

Ian little black cat grotesque body illustration

Core positioning

Design and generate 16:9 horizontal body illustrations for Chinese articles. The goal is not to make commercial illustrations, PPT infographics, or cute cartoons, but to turn the key judgments, processes, structures, states, or metaphors in the article into a clean, grotesque, creative, readable but non-instructional hand-drawn explanatory image.

The default visual IP is the "little black cat": the cat-shaped replacement version of the old version of Xiaohei, with a large and slightly tilted black cat head, a smaller black body, two large white oval eyes that take up a large portion of the face, black pupils offset in the same direction, pointed ears, short and thick limbs, a blank expression, seriously doing one absurd but valid thing. The little black cat must participate in the core action of the image and cannot just stand beside it as decoration.

The little black cat is not an ordinary black cat, nor is it upgraded into a complex new cartoon. By default, the complexity should be close to the original Xiaohei material: one little black cat, one core action, 1-2 main objects, 3-5 short labels, and a large amount of blank space. But the character image must give priority to matching the original little black cat in past videos: big head and small body, huge white oval eyes, black pupils offset in the same direction, short and thick limbs, no mouth and no whiskers, deadly serious, slightly grotesque. What is reduced is the complexity of the scene, not the recognizability of the character.

First read these references

Read according to the needs of the task; do not stuff the context all at once:

• references/style-dna.md: style DNA, colors, text, taboos.
• references/xiaohei-cat-ip.md: the image, personality, action library, and taboos of the little black cat IP.
• references/composition-patterns.md: structure types, original metaphor methods, and anti-copying rules.
• references/prompt-template.md: prompt template for a single image generation.
• references/qa-checklist.md: post-generation checking and iteration rules.
• assets/ip-reference/00-source-safety-audit-cat.png: authoritative character reference cropped from the original image of the old video. Every image generation must pass it as the first character reference image to image_gen; only lock the character, do not reproduce the list, buttons, or machine.
• assets/ip-reference/01-approved-simple-funnel-cat.png: a low-complexity composition reference confirmed by the user; only calibrate scene density and blank space, do not use it as the true source of the character's appearance, and do not reproduce the funnel composition.
• assets/examples/15-fact-vs-guess-cat.png、16-content-handoff-door-cat.png: a positive sample that passed cross-scene identity verification; only calibrate character stability and simplicity, and do not reproduce the scale or door.
• assets/examples/: use the original Xiaohei material to calibrate low complexity, line density, blank space, and the way the character participates in the action; only replace the character with the little black cat. Do not copy the compositions, objects, or labels of these cases.

Workflow

1. Digest the body text

First read the body text, link, Notion page, Markdown file, or screenshot content provided by the user. Extract:

• What is the core viewpoint
• Which paragraphs carry the cognitive turning points
• Which content is suitable for explanation with images
• Which places are only suitable for text and do not need images

Do not distribute illustrations evenly. Prioritize selecting "cognitive anchors", for example: core judgments, two breakpoints, input-output closed loop, branching, before-and-after comparison, one fish many ways, handoff paths, common pitfalls, character state changes.

2. First produce the illustration strategy

If the user only says "analyze how to arrange illustrations / think about which places need illustrations", first provide a shot list. For each image, write clearly:

• Which paragraph it is placed after
• Image theme
• Core meaning
• Structure type
• What the little black cat is doing in the image
• Suggested elements
• Suggested Chinese annotation words

Default 4-8 images. When the article is very short, 1-3 images; for long articles, do not easily exceed 9 images. Enough is enough; avoid turning the main text into a picture album.

3. Single image generation

If the user explicitly requests "generate / output / make an image / help me generate," do not stop to wait for confirmation; use the built-in image_gen Generate each image separately. Do not combine multiple images into one.

Each image should explain only one core structure. The prompt must include:

• 16:9 horizontal Chinese main text illustration
• Pure white background
• Black hand-drawn line art
• A small amount of red/orange/blue Chinese handwritten annotations
• Lots of white space
• The little black cat as the core action subject
• Use assets/ip-reference/00-source-safety-audit-cat.png as the character reference image input
• The little black cat must have a large, slightly tilted cat head, a smaller body, huge white oval eyes, black pupils offset in the same direction, short thick limbs, no mouth and no whiskers, and a dead-serious temperament
• Prohibit PPT, commercial illustration, childish cuteness, complex architecture, complex machines, multi-panel screens, and type titles in the upper-left corner

Do not replicate past cases. Cases only provide style density and ways for the little black cat to participate; do not directly reuse existing compositions such as "conveyor belt breakpoint / little black cat pulling a line / material fish / stamping toolbox / common pitfall path" unless the user explicitly requests replicating a certain image. Each time, reinvent a strange but valid metaphor from the current article.

4. Check and iterate

After generation, check references/qa-checklist.md. If the following problems appear, prioritize regeneration or local editing:

• The little black cat is only decoration
• The weighted similarity between the little black cat and the authoritative character reference is below 90%
• The little black cat looks like an ordinary black cat, lacking a big head and small body, huge white eyes, offset pupils, and an eerie temperament
• The image is too crowded
• The little black cat or scene is overly complex, like a complete video page
• Too much like a flowchart/PPT
• Too much Chinese or serious typos
• Titles such as "Common Pitfalls/Flowchart/System Architecture Diagram" appear in the upper-left corner
• The art style is too cute, childish, or rigid
• The background is not a clean white background

5. Save and deliver

If the user is working inside the workspace, copy the final images to:

assets/<article-slug>-illustrations/

Name them in order:

01-topic-name.png
02-topic-name.png

Keep the original generated files; do not overwrite existing assets unless the user explicitly requests replacement.

Output specification

The strategy output before generation should be short and accurate. The delivery after generation should include:

• How many images were generated
• The purpose of each image
• Save path
• Which images are the most stable, and which are optional

Do not give long explanations of style theory; let the images speak for themselves.