Back to Details

giggle-generation-video

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Giggle Video Generation

Giggle 视频生成

Source: giggle-official/skills · API: giggle.pro
Generates AI videos via giggle.pro's Generation API. Supports text-to-video and image-to-video. Submit task → query when ready. No polling, no Cron, no file writes—all operations via exec.
来源: giggle-official/skills · API: giggle.pro
通过giggle.pro的生成API生成AI视频。支持文本转视频和图片转视频。提交任务→就绪后查询。无需轮询、无需Cron、无需写入文件——所有操作均通过exec执行。

Installation Requirements

安装要求

RequirementValue
Binary
python3
Environment
GIGGLE_API_KEY
(required; obtain from https://giggle.pro/)
Pip
requests
Set 
GIGGLE_API_KEY
before use. The script will prompt if not configured.
No Retry on Error: If script execution encounters an error, do not retry. Report the error to the user directly and stop.
要求项取值
二进制程序
python3
环境变量
GIGGLE_API_KEY
（必填；从https://giggle.pro/获取）
依赖包
requests
使用前请设置
GIGGLE_API_KEY
环境变量。若未配置，脚本会进行提示。
错误时不重试：若脚本执行遇到错误，请勿重试。直接向用户报告错误并停止操作。

Supported Models

支持的模型

ModelSupported Durations (s)DefaultDescription
grok6, 106Strong overall capability, recommended
grok-fast6, 106grok fast version
sora24, 8, 124OpenAI Sora 2
sora2-pro4, 8, 124Sora 2 Pro
sora2-fast10, 1510Sora 2 Fast
sora2-pro-fast10, 1510Sora 2 Pro Fast
kling255, 105Kling video model
seedance15-pro4, 8, 124Seedance Pro (with audio)
seedance15-pro-no-audio4, 8, 124Seedance Pro (no audio)
veo314, 6, 84Google Veo 3.1 (with audio)
veo31-no-audio4, 6, 84Google Veo 3.1 (no audio)
minimax2366MiniMax model
wan255, 100Wanxiang model
Note: 
--duration
must be chosen from the model's supported durations, otherwise the API will error.
模型支持时长（秒）默认值描述
grok6, 106综合能力强，推荐使用
grok-fast6, 106grok 快速版本
sora24, 8, 124OpenAI Sora 2
sora2-pro4, 8, 124Sora 2 Pro
sora2-fast10, 1510Sora 2 Fast
sora2-pro-fast10, 1510Sora 2 Pro Fast
kling255, 105Kling 视频模型
seedance15-pro4, 8, 124Seedance Pro（带音频）
seedance15-pro-no-audio4, 8, 124Seedance Pro（无音频）
veo314, 6, 84Google Veo 3.1（带音频）
veo31-no-audio4, 6, 84Google Veo 3.1（无音频）
minimax2366MiniMax 模型
wan255, 100万象模型
注意：
--duration
必须选择模型支持的时长，否则API会报错。

Frame Reference (Image-to-Video)

帧参考（图片转视频）

For image-to-video, 
--start-frame
and 
--end-frame
support three mutually exclusive formats:
MethodFormatExample
asset_id
asset_id:<ID>
asset_id:lkllv0yv81
url
url:<URL>
url:https://example.com/img.jpg
base64
base64:<DATA>
base64:iVBORw0KGgo...
Each frame parameter can only use one of these methods.
对于图片转视频，
--start-frame
和
--end-frame
支持三种互斥格式：
方式格式示例
asset_id
asset_id:<ID>
asset_id:lkllv0yv81
url
url:<URL>
url:https://example.com/img.jpg
base64
base64:<DATA>
base64:iVBORw0KGgo...
每个帧参数只能使用其中一种方式。

Execution Flow: Submit and Query

执行流程：提交与查询

Video generation is asynchronous (typically 60–300 seconds). Submit a task to get 
task_id
, then query when the user wants to check status. All commands run via 
exec
; API key from system env.
视频生成为异步操作（通常需要60–300秒）。提交任务以获取
task_id
，之后当用户想要查看状态时进行查询。所有命令通过
exec
运行；API密钥从系统环境变量获取。

Step 1: Submit Task

步骤1：提交任务

First send a message to the user: "Video generation submitted. Usually takes 1–5 minutes. You can ask me about the progress anytime."
bash
undefined
首先向用户发送消息："视频生成任务已提交，通常需要1-5分钟。你可以随时询问我进度。"
bash
undefined

Text-to-video (default grok-fast)

文本转视频（默认使用grok-fast）

python3 scripts/generation_api.py
--prompt "Camera slowly pushes forward, person smiling in frame"
--model grok-fast --duration 6
--aspect-ratio 16:9 --resolution 720p
python3 scripts/generation_api.py
--prompt "Camera slowly pushes forward, person smiling in frame"
--model grok-fast --duration 6
--aspect-ratio 16:9 --resolution 720p

Image-to-video - use asset_id as start frame

图片转视频 - 使用asset_id作为起始帧

python3 scripts/generation_api.py
--prompt "Person slowly turns around"
--start-frame "asset_id:lkllv0yv81"
--model grok-fast --duration 6
--aspect-ratio 16:9 --resolution 720p
python3 scripts/generation_api.py
--prompt "Person slowly turns around"
--start-frame "asset_id:lkllv0yv81"
--model grok-fast --duration 6
--aspect-ratio 16:9 --resolution 720p

Image-to-video - use URL as start frame

图片转视频 - 使用URL作为起始帧

python3 scripts/generation_api.py
--prompt "Scenery from still to motion"
--start-frame "url:https://example.com/img.jpg"
--model grok-fast --duration 6
python3 scripts/generation_api.py
--prompt "Scenery from still to motion"
--start-frame "url:https://example.com/img.jpg"
--model grok-fast --duration 6

Image-to-video - both start and end frame

图片转视频 - 同时设置起始和结束帧

python3 scripts/generation_api.py
--prompt "Scene transition"
--start-frame "asset_id:abc123"
--end-frame "url:https://example.com/end.jpg"
--model grok --duration 6

Response example:
```json
{"status": "started", "task_id": "55bf24ca-e92a-4d9b-a172-8f585a7c5969"}
Store task_id in memory (
addMemory
):
giggle-generation-video task_id: xxx (submitted: YYYY-MM-DD HH:mm)
python3 scripts/generation_api.py
--prompt "Scene transition"
--start-frame "asset_id:abc123"
--end-frame "url:https://example.com/end.jpg"
--model grok --duration 6

响应示例：
```json
{"status": "started", "task_id": "55bf24ca-e92a-4d9b-a172-8f585a7c5969"}
将task_id存储到内存（
addMemory
）：
giggle-generation-video task_id: xxx (submitted: YYYY-MM-DD HH:mm)

Step 2: Query When User Asks

步骤2：用户询问时查询

When the user asks about video progress (e.g. "is my video ready?", "progress?"), run:
bash
python3 scripts/generation_api.py --query --task-id <task_id>
Output handling:
stdout patternAction
Plain text with video links (视频已就绪)Forward to user as-is
Plain text with errorForward to user as-is
JSON 
{"status": "processing", "task_id": "..."}
Tell user "Still in progress, please ask again in a moment"
Link return rule: Video links in results must be full signed URLs (with Policy, Key-Pair-Id, Signature query params). Keep as-is when forwarding.
当用户询问视频进度时（例如"我的视频好了吗？"、"进度如何？"），执行：
bash
python3 scripts/generation_api.py --query --task-id <task_id>
输出处理：
标准输出模式操作
包含视频链接的纯文本（视频已就绪）直接转发给用户
包含错误信息的纯文本直接转发给用户
JSON格式 
{"status": "processing", "task_id": "..."}
告知用户"视频仍在生成中，请稍后再问"
链接返回规则：结果中的视频链接必须是完整的签名URL（包含Policy、Key-Pair-Id、Signature查询参数）。转发时请保持原样。

New Request vs Query Old Task

新请求与旧任务查询

When the user initiates a new video generation request, must run Step 1 to submit a new task. Do not reuse old task_id from memory.
Only when the user explicitly asks about a previous task's progress should you query the old task_id from memory.
当用户发起新的视频生成请求时，必须执行步骤1提交新任务。请勿复用内存中的旧task_id。
只有当用户明确询问之前任务的进度时，才从内存中查询旧task_id。

Parameter Reference

参数参考

ParameterDefaultDescription
--prompt
requiredVideo description prompt
--model
grokSee "Supported Models" table
--duration
model defaultMust choose from model's supported durations
--aspect-ratio
16:916:9, 9:16, 1:1, 3:4, 4:3
--resolution
720p480p, 720p, 1080p
--start-frame
-Image-to-video start frame: 
asset_id:ID
, 
url:URL
, or 
base64:DATA
--end-frame
-Image-to-video end frame, same format as start
Note: base64 parameter supports base64-encoded images. Pass the raw Base64 string directly, do not add the 
data:image/xxx;base64,
prefix.
参数默认值描述
--prompt
必填视频描述提示词
--model
grok参考「支持的模型」表格
--duration
模型默认值必须选择模型支持的时长
--aspect-ratio
16:916:9、9:16、1:1、3:4、4:3
--resolution
720p480p、720p、1080p
--start-frame
-图片转视频的起始帧：
asset_id:ID
、
url:URL
或
base64:DATA
--end-frame
-图片转视频的结束帧，格式与起始帧相同
注意：base64参数支持base64编码的图片。直接传递原始Base64字符串，无需添加
data:image/xxx;base64,
前缀。

Interaction Guide

交互指南

When the user request is vague, guide per the steps below. If the user has provided enough info, run the command directly.
当用户的请求模糊时，请按照以下步骤引导。若用户已提供足够信息，请直接执行命令。

Step 1: Model Selection (required)

步骤1：选择模型（必填）

Before generating, must introduce available models and let the user choose. Display the model list from "Supported Models" table. Wait for explicit user choice before continuing.
生成前必须向用户介绍可用模型并让用户选择。展示「支持的模型」表格中的模型列表。等待用户明确选择后再继续。

Step 2: Video Duration

步骤2：视频时长

For the chosen model, show supported duration options. Default to the model's default duration.
针对用户选择的模型，展示支持的时长选项。默认使用模型的默认时长。

Step 3: Generation Mode

步骤3：生成模式

Question: "Do you need reference images as start/end frame?"
Options: No - text-to-video only / Yes - image-to-video (set start/end frame)
问题："是否需要将参考图片作为起始/结束帧？"
选项：否 - 仅文本转视频 / 是 - 图片转视频（设置起始/结束帧）

Step 4: Aspect Ratio

步骤4：宽高比

Question: "What aspect ratio do you need?"
Options: 16:9 - Landscape (recommended) / 9:16 - Portrait / 1:1 - Square
问题："需要什么宽高比？"
选项：16:9 - 横屏（推荐） / 9:16 - 竖屏 / 1:1 - 正方形

Step 5: Execute and Display

步骤5：执行与展示

Follow the flow: send message → Step 1 submit → user asks → Step 2 query. Forward exec stdout to the user as-is.
遵循流程：发送提示消息→步骤1提交任务→用户询问→步骤2查询。将exec的标准输出直接转发给用户。