← 返回
未分类 Key

Nova Canvas

Generate images using Amazon Nova Canvas via AWS Bedrock. Supports multiple AWS auth methods: environment variables, credentials file, named profiles, IAM in...
通过 AWS Bedrock 使用 Amazon Nova Canvas 生成图像。支持多种 AWS 认证方式:环境变量、凭证文件、命名配置文件、IAM ...
wujiaming88 wujiaming88 来源
未分类 clawhub v1.1.0 1 版本 100000 Key: 需要
★ 0
Stars
📥 312
下载
💾 0
安装
1
版本
#latest

概述

Nova Canvas

Generate images via Amazon Nova Canvas on AWS Bedrock.

AWS Auth Methods

MethodHow to Use
--------------------
Bearer tokenAWS_BEARER_TOKEN_BEDROCK env var or --bearer-token
Environment variablesSet AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY
Credentials fileConfigure ~/.aws/credentials
Named profile--profile my-profile or AWS_PROFILE env var
Direct keys--access-key AKIA... --secret-key ...
Temporary credentialsAdd --session-token with direct keys
IAM instance roleAuto-detected on EC2/ECS/Lambda
AWS SSORun aws sso login first

Auto-detection order: direct keys → profile → bearer token → env vars → credentials file → instance role → SSO.

Quick Start

python3 {baseDir}/scripts/generate.py "your prompt" -o output.png
python3 {baseDir}/scripts/generate.py "your prompt" -o output.png --profile work
python3 {baseDir}/scripts/generate.py "your prompt" -o output.png --access-key AKIA... --secret-key ...

Parameters

FlagDefaultDescription
----------------------------
promptText description of the image
-o, --outputoutput.pngOutput file path
-W, --width1024Width 512-4096, divisible by 64
-H, --height1024Height 512-4096, divisible by 64
-n, --count1Number of images (1-5)
-q, --qualitystandardstandard or premium
-s, --seedrandomSeed for reproducibility
--negativeNegative prompt (what to avoid)
--cfg8.0CFG scale 1.1-10.0
--regionus-east-1AWS region
--profileAWS named profile
--access-keyAWS Access Key ID
--secret-keyAWS Secret Access Key
--session-tokenAWS Session Token
--bearer-tokenBearer token (overrides env)

Workflow

  1. Craft a detailed English prompt (Nova Canvas performs best in English).
  2. Choose size: square 1024×1024, landscape 1280×768, portrait 768×1280.
  3. Run generate.py with timeout=120.
  4. Send resulting image to user via message tool.

Prompt Tips

  • Detailed English prompts yield best results.
  • Specify style: "oil painting", "watercolor", "3D render", "photograph", "anime".
  • Use --negative "blurry, low quality, text, watermark" to exclude unwanted elements.

版本历史

共 1 个版本

  • v1.1.0 当前
    2026-05-07 08:15 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

design-media

Openai Whisper

steipete
使用 Whisper CLI 进行本地语音转文字(无需 API 密钥)
★ 335 📥 94,526
design-media

UI/UX Pro Max

xobi667
提供 UI/UX 设计智能与实现指导,帮助打造精美界面。适用于 UI 设计、UX 流程、信息架构、视觉风格、设计系统/标记、组件规格、文案/微文案、无障碍及前端 UI(HTML/CSS/JS、React、Next.js、Vue、Svelte
★ 224 📥 48,594
office-efficiency

PPT from Template

wujiaming88
通过从参考模板中提取视觉风格,并使用 PptxGenJS 从头重新创建幻灯片来生成演示文稿。适用场景:用户提供 PPT……
★ 0 📥 4,237