Chenyu AIGC - AI Video & Image Generation
Generate videos and images using AI models through the Chenyu Studio AIGC orchestration API.
When to Use
- - User wants to generate a video from text prompt
- User wants to generate a video from an image (first/last frame)
- User wants to extend or remix a video
- User wants to generate AI images
- User wants to check status of a generation task
- User wants to list available AI models
When NOT to Use
- - User wants to analyze or understand existing videos (use video-analysis skill)
- User wants to download videos from social platforms (use video-fetch skill)
- User wants to manage digital humans or clone voices (use chenyu-core skill)
Authentication
CODEBLOCK0
Base URL: $CHENYU_BASE_URL (default: https://chenyu.pro)
Workflow
- 1. Discover recipes — list available AI models (see below)
- Get recipe schema — check what inputs/parameters the recipe accepts
- Execute — submit a generation task → see execute-recipe.md
- Poll & manage — track status, get output, cancel → see manage-tasks.md
Step 1: List Available Recipes
CODEBLOCK1
Each recipe represents an AI model capability. Key response fields:
- -
recipe_id — use this ID when executing - INLINECODE3 — human-readable identifier (e.g.
volcengine-seedance-v1-pro) - INLINECODE5 — what it produces:
video, image, INLINECODE8
Step 2: Get Recipe Schema
CODEBLOCK2
The schema tells you:
- -
typed_inputs_schema.definitions — accepted input types and their fields - INLINECODE10 — available parameters with constraints (min/max/enum)
- INLINECODE11 /
credit_cost_rules — how many credits it costs
After getting the schema, read execute-recipe.md for execution details.
Chenyu AIGC - AI视频与图像生成
通过Chenyu Studio AIGC编排API，使用AI模型生成视频和图像。
使用场景
- - 用户希望通过文本提示生成视频
- 用户希望通过图像（首帧/尾帧）生成视频
- 用户希望扩展或混剪视频
- 用户希望生成AI图像
- 用户希望查看生成任务的状态
- 用户希望列出可用的AI模型
不适用场景
- - 用户希望分析或理解现有视频（请使用视频分析技能）
- 用户希望从社交平台下载视频（请使用视频获取技能）
- 用户希望管理数字人或克隆声音（请使用chenyu-core技能）
身份认证
Authorization: Bearer $CHENYUAPIKEY
基础URL：$CHENYUBASEURL（默认值：https://chenyu.pro）
工作流程
- 1. 发现配方 — 列出可用的AI模型（见下文）
- 获取配方架构 — 检查配方接受的输入/参数
- 执行 — 提交生成任务 → 参见 execute-recipe.md
- 轮询与管理 — 跟踪状态、获取输出、取消 → 参见 manage-tasks.md
第一步：列出可用配方
bash
curl -s $CHENYUBASEURL/api/v1/aigc/recipes \
-H Authorization: Bearer $CHENYUAPIKEY | jq .data[] | {recipeid, name, slug, description, outputtype}
每个配方代表一种AI模型能力。关键响应字段：
- - recipeid — 执行时使用此ID
- slug — 人类可读标识符（例如 volcengine-seedance-v1-pro）
- outputtype — 输出类型：video（视频）、image（图像）、audio（音频）
第二步：获取配方架构
bash
curl -s $CHENYUBASEURL/api/v1/aigc/recipes/{recipe_id}/schema \
-H Authorization: Bearer $CHENYUAPIKEY | jq .data
架构信息包含：
- - typedinputsschema.definitions — 接受的输入类型及其字段
- parametersschema — 可用参数及其约束条件（最小值/最大值/枚举值）
- creditcost / creditcostrules — 消耗的积分数
获取架构后，请阅读 execute-recipe.md 了解执行详情。
