# CanonSheet Character Prompt Builder > CanonSheet Character Prompt Builder is a paid API for AI agents from canonsheet.kaneky.dev, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-11). Generates a consistent, labeled prompt set for a single human character—including canonical image prompt, negative prompts, video prompt, and optional contact-sheet walk—for use with any image or video generation model. ## Facts - Endpoint: POST https://canonsheet.kaneky.dev/api/build_character_prompts?utm_source=zero.xyz - Price: $0.02/call - Payment: x402 - Status: unknown - Last checked: 2026-10-11 - Activations on Zero: 0 - Tags: x402 - Canonical page: https://www.zero.xyz/c/canonsheet-character-prompt-builder-1cc291ca - Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_AaO_IeW5h6uaGhiH7WVFC Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently. ## How to call it through Zero Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`): ```sh zero fetch --capability canonsheet-character-prompt-builder-1cc291ca -d '' ``` Example prompt: Build a consistent character prompt set for Elena, a 30s woman with warm brown skin, amber eyes, short natural hair, a tailored burgundy blazer, and wire-rimmed glasses — she should be in a medium shot at eye level with soft-key lighting in a library environment; also generate negative prompts so her glasses never disappear, and include a video prompt with a breathe motion and a locked camera. ## When to prefer this Choose this endpoint when you need to lock a character's appearance across multiple AI-generated images or video clips and prevent trait drift — especially when the character has distinctive features like glasses, facial hair, a mobility aid, or tattoos that tend to disappear between generations. It is purpose-built for prompt engineering workflows rather than direct image generation, so prefer it when your downstream tool is any image or video model and you want a reusable, labeled prompt corpus rather than a one-off image. Prefer it over generic prompt templates when you need structured negative prompts and optional contact-sheet enumeration. ## Known failure modes - Invalid enum value for choices/shot, angle, lens, lighting, style, or video fields — request refused before payment with a 400-level error - Missing or malformed required fields — rejected prior to charging - HTTP 402 returned on first call with pricing information (expected behavior, not a true failure — retry with payment) - Payment not completed or x402 flow not followed — no prompts returned - Exceeding maxItems 6 on custom_traits — request refused ## How this service works Build a consistent prompt set for one human character: a canonical image prompt with every appearance fact labelled, negative prompts that stop traits like glasses or a cane from vanishing, a video prompt, and optionally a contact sheet that holds everything fixed and walks one axis. Works with any image or video model. Text keeps wardrobe and framing stable; for the same FACE across images, generate the canonical frame once and pass it back as a reference image (has_reference). Paid per call over x402: the first attempt answers HTTP 402 with the price. Invalid arguments are refused before any payment. ## Output Returns a structured prompt set containing: a canonical image prompt with every appearance detail explicitly labeled, one or more negative prompts preventing trait drift (e.g. glasses, mobility aids, tattoos), a video prompt with camera and motion settings, and optionally a series of contact-sheet prompts that hold all variables fixed while stepping through one chosen axis (such as style, lighting, or shot size). ## Request schema (JSON Schema) ```json { "type": "object", "properties": { "name": { "type": "string" }, "video": { "type": "object", "properties": { "camera": { "enum": [ "locked", "push-in", "push-out", "orbit" ], "type": "string" }, "motion": { "enum": [ "blink", "breathe", "weight", "turn-to", "look-away", "smile", "step", "speak", "hair" ], "type": "string" }, "ambient": { "enum": [ "still", "breeze", "dust", "flicker" ], "type": "string" } }, "additionalProperties": false }, "traits": { "type": "object", "properties": { "ink": { "type": "string" }, "glasses": { "type": "string" }, "headwear": { "type": "string" }, "mobility": { "type": "string" }, "facial-hair": { "type": "string" } }, "additionalProperties": false }, "choices": { "type": "object", "properties": { "lens": { "enum": [ "35", "50", "85", "135", "none" ], "type": "string" }, "seed": { "type": "string" }, "shot": { "enum": [ "full", "three-quarter", "medium", "close", "extreme-close" ], "type": "string" }, "angle": { "enum": [ "eye", "low", "high", "three-quarter-turn", "profile", "none" ], "type": "string" }, "style": { "enum": [ "photo", "cinematic", "illustration", "painterly", "render3d", "anime" ], "type": "string" }, "action": { "type": "string" }, "lighting": { "enum": [ "soft-key", "rim", "golden", "overcast", "low-key", "practical", "none" ], "type": "string" }, "environment": { "type": "string" } }, "additionalProperties": false }, "walk_axis": { "enum": [ "action", "shot", "angle", "lens", "lighting", "environment", "style" ], "type": "string" }, "appearance": { "type": "object", "properties": { "eyes": { "type": "string" }, "face": { "type": "string" }, "hair": { "type": "string" }, "held": { "type": "string" }, "skin": { "type": "string" }, "build": { "type": "string" }, "outf … (truncated) ``` ## More - Live health (JSON, refreshed every minute): https://www.zero.xyz/c/canonsheet-character-prompt-builder-1cc291ca/health.json - [Zero catalog index](https://www.zero.xyz/llms.txt) - [Other services from canonsheet.kaneky.dev](https://www.zero.xyz/host/canonsheet.kaneky.dev/llms.txt)