📦 DigenAI (Free) — 技能工具

v1.1.3

DigenAI image and video generation integration for OpenClaw. Supports image generation via old API (api.digen.ai) with DIGEN_TOKEN + DIGEN_SESSION_ID, and vi...

1· 49·0 当前·0 累计
eeoeofl 头像by @eeoeofl (Eeofol)·MIT-0
下载技能包
License
MIT-0
最后更新
2026/4/15
0
安全扫描
VirusTotal
可疑
查看报告
OpenClaw
可疑
medium confidence
The skill's code and instructions generally match an image/video generation client, but there are multiple documentation and metadata inconsistencies (missing declared env vars, conflicting API host/key formats and placeholders) that merit caution before installing or giving keys.
评估建议
Before installing or providing any keys: 1) Confirm the authoritative API domain and key format with DigenAI (do not rely exclusively on the Telegram/Discord messages included here). The code references api.digen.ai (old image API) and https://api.new-digen.ai (new video API) — verify those are official. 2) Treat the missing declared env vars in registry metadata as a red flag — assume this skill needs DIGEN_TOKEN, DIGEN_SESSION_ID and DIGEN_API_KEY and only provide keys with least privilege. 3)...
详细分析 ▾
用途与能力
Name/description (image & video generation) aligns with the included Python client and scripts. However the registry metadata declares no required environment variables or primary credential while SKILL.md and the code both require DIGEN_TOKEN, DIGEN_SESSION_ID (old image API) and DIGEN_API_KEY (new video API). This mismatch between metadata and actual requirements is an incoherence that could mislead users about what secrets the skill needs.
指令范围
Runtime instructions are mostly within scope (call Digen APIs, upload images, poll for status). But there are several contradictions and vague items in the SKILL.md and references: the SKILL.md sometimes says the API key starts with 'dg_' while other examples show 'ak_xxx'; the new API base is shown as a placeholder '[New API endpoint]' in docs but the code hardcodes NEW_API_BASE = 'https://api.new-digen.ai' (a different domain than api.digen.ai used for the old API). The docs instruct obtaining a key via an external Telegram bot and Discord messages are included in the package (marketing/community content). The client supports webhook_url — if used, generation results (including output URLs) can be POSTed to arbitrary external endpoints, which is a potential exfiltration vector if misused.
安装机制
No install spec is present (instruction-only style + included scripts). Nothing in the package writes arbitrary installers or downloads remote code during install. This is the lower-risk install posture.
凭证需求
The environment variables the skill uses (DIGEN_TOKEN, DIGEN_SESSION_ID, DIGEN_API_KEY) are directly related to its stated purpose (auth for old/new APIs). That is proportionate. The issue is the registry metadata omitted declaring these required env vars, which is misleading. Also the skill suggests obtaining keys via a Telegram bot and Discord server — relying on third-party chat bots to distribute keys may be unusual and warrants verification.
持久化与权限
The skill does not request always:true, does not modify other skills or system-wide settings, and contains only user-invocable scripts and a client library. It does accept webhook URLs (user-supplied) but does not itself force persistent system-level privileges.
安全有层次,运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发,无需署名。

运行时依赖

无特殊依赖

版本

latestv1.1.32026/4/15

Removed api.cowork.digen.ai from client script (NEW_API_BASE now generic). Full sweep: no test.cowork.digen.ai or portal URLs remain anywhere in the bundle.

可疑

安装命令

点击复制
官方npx clawhub@latest install digen-ai-free
镜像加速npx clawhub@latest install digen-ai-free --registry https://cn.longxiaskill.com

技能文档

Generate images from text prompts and videos from images or text via DigenAI API.

⚠️ First Time Users: Get Your Free API Key

Video generation requires a free API key.

How to Get Your API Key

  • Open our Telegram bot: https://t.me/digen_skill_bot
  • Send the command: /key
  • Copy your API key (starts with dg_)

Your API key is used as:

Authorization: Bearer YOUR_API_KEY

Quick Start

from digen_ai_client import DigenAIClient

# Image generation (old API) — requires DIGEN_TOKEN + DIGEN_SESSION_ID client = DigenAIClient( old_api_token="your_token", old_api_session="your_session" )

# Video generation (new API) — requires API Key client = DigenAIClient(api_key="ak_xxxxxxxxxxxxxxxxxxxx")


Image Generation (Old API)

Uses api.digen.ai with DIGEN_TOKEN + DIGEN_SESSION_ID

Available Models

ModelDescription
defaultHigh quality model

Resolutions

RatioSize
MultipleStandard resolutions supported

Example

from digen_ai_client import DigenAIClient

client = DigenAIClient( old_api_token="your_digen_token", old_api_session="your_digen_session" )

result = client.generate_image_sync( prompt="futuristic cyberpunk city at night, neon lights, rainy streets, highly detailed, 8K", model="default", resolution="1:1" )

if result["success"]: print(f"✅ Image: {result['images'][0]}") else: print(f"❌ Error: {result.get('error')}")


Video Generation (New API)

Uses new API with Bearer API Key

Available Models

| default | High quality, fast generation | 10s |

Modes

  • Text-to-Video: text prompt only
  • Image-to-Video: image URL with optional motion prompt

Example: Image-to-Video

from digen_ai_client import DigenAIClient

client = DigenAIClient(api_key="ak_xxxxxxxxxxxxxxxxxxxx")

result = client.generate_video_sync( image_url="https://your-image.jpg", prompt="gentle camera pan left, neon lights twinkling", model="default", duration=5, aspect_ratio="1:1" )

if result["success"]: print(f"✅ Video: {result['video_url']}") print(f" Thumbnail: {result['thumbnail_url']}") else: print(f"❌ Error: {result.get('error')}")

Example: Text-to-Video

client = DigenAIClient(api_key="ak_xxxxxxxxxxxxxxxxxxxx")

result = client.generate_video_sync( prompt="A cute cat playing piano in a cozy room, soft lighting", model="default", duration=5, aspect_ratio="1:1" )


API Key Management (New API)

Check API Key Info

client = DigenAIClient(api_key="ak_xxx")
info = client.get_api_key_info()
print(info)
# {'success': True, 'data': {'api_key': 'ak_xxx', 'status': 1, 'created_at': '...'}}

Upload Image

result = client.upload_image(file_path="/path/to/image.jpg")
if result["success"]:
    print(f"Image URL: {result['url']}")

Configuration

Environment Variables

VariableDescription
DIGEN_TOKENOld API token for image generation
DIGEN_SESSION_IDOld API session ID for image generation
DIGEN_API_KEYNew API key (ak_xxx) for video generation

Setup

# Image generation (old API)
export DIGEN_TOKEN="your_token"
export DIGEN_SESSION_ID="your_session"

# Video generation (new API) export DIGEN_API_KEY="ak_xxxxxxxxxxxxxxxxxxxx"


Error Handling

No API Key Error (Video)

❌ API Key Not Found!
Join our Discord: https://discord.gg/4shAQahd
Go to #api-key channel → send !key

Error Codes (New API)

HTTP CodeError CodeDescription
400invalid_requestInvalid or missing parameters
401invalid_api_keyInvalid or missing API key
402insufficient_creditsNot enough credits
404not_foundResource not found
500internal_errorInternal server error

API Reference

New API Endpoints (Video)

MethodEndpointDescription
GET/b/v1/api-keyGet API key info
POST/b/v1/uploadUpload image file
POST/b/v1/video/generateGenerate video
GET/b/v1/video/{id}Get video status
Base URL: [New API endpoint]

Old API Endpoints (Image)

MethodEndpointDescription
POST/v2/tools/text_to_imageGenerate image
POST/v6/video/get_task_v2Get image status
Base URL: https://api.digen.ai


Scripts

  • scripts/digen_ai_client.py - Python client with sync/async support
  • scripts/batch_generate.py - Batch image generation utility

Tips

  • Image generation: poll every 3 seconds, timeout 120s
  • Video generation: poll every 5 seconds, timeout 300s
  • Resolution: 720p or 1080p
数据来源ClawHub ↗ · 中文优化:龙虾技能库