SuperAPI AI Directory

hunyuan-image

Design & creation

View repository

Updated 10-16 08:41

About this skill

Hunyuan Image — Tencent Hunyuan Image Generation (100,000 free image quota)

Call the Tencent Cloud Hunyuan 3.0 image generation model (via the CloudBase AI gateway), supportstext-to-imageandreference image (image-to-image)。Completely free, not a single cent: the quota comes from the WeChat "Mini Program Growth Plan" incentive resource pack——100,000 AI-generated images + 1 billion Tokens, free for developers across all industries, valid for 6 months, the quota is consumed from the resource pack in your own Cloud Development environment.

Visual web version + illustrated tutorial:freeimg.shenzjd.com/hunyuan —— the web page hasthe complete annotated tutorial from claiming the resource pack and creating a key to generating images(Step 0 card-style guide), if you don't want to set up a local environment, just enter your key on the web page and use it; both share the same set of Tencent Cloud credentials.

When to Use

  • The user explicitly wants Hunyuan / Hunyuan / Tencent Cloud image generation, or needsreference image(editing an image with a reference image)
  • The user is in the WeChat Mini Program ecosystem and wants to use the incentive resource pack of the "Mini Program Growth Plan"100,000 free image generation quota
  • The user has already configured Tencent Cloud keys and requests to continue using Hunyuan

When NOT to Use:

  • The user only wants free and fast image generation with zero configuration → use freeimg skill (z-image-turbo, no registration or claiming required)
  • The user is unwilling to spend a few minutes claiming the free resource pack (although not claiming it incurs no cost, without the resource pack it is billed by usage)

Core Pattern

Step 0: First use — claim the free resource pack and configure credentials

Claiming the quota (free, available to developers across all industries; the web version has the same illustrated tutorial card):

  1. Claim the incentive resource pack: claim the resource pack on the WeChat Official Accounts Platform under "Industry Capabilities → Mini Program Growth Plan" (100,000 AI-generated images + 1 billion Tokens, valid for 6 months), click "Go to Use" to create a Cloud Development environment, and note down theenvironment ID——the resource pack is bound to this environment

  2. Create a key: Tencent Cloud console Access Management → API Key Management "Create Key", copy the SecretId and SecretKey

  3. Write the configuration(only once,do not write the key into the repository, logs, or conversation output):

    mkdir -p ~/.hunyuan && printf "TCB_ENV_ID=你的环境ID\nTCB_SECRET_ID=你的SecretId\nTCB_SECRET_KEY=你的SecretKey\n" > ~/.hunyuan/config.env && chmod 600 ~/.hunyuan/config.env
    

The script reads credentials in the following priority order: environment variable TCB_ENV_ID / TCB_SECRET_ID / TCB_SECRET_KEY → configuration file ~/.hunyuan/config.env. If neither exists, it prints the above guidance and exits.

Dependency note: the script uses the official @cloudbase/node-sdk(gateway authentication is a custom signature, do not reimplement it yourself), on first run it automatically installs to ~/.hunyuan/sdk(requires node + npm on the machine, takes a dozen seconds), and reuses it afterwards.

Step 1: Generate an image

# 文生图
scripts/generate.mjs --prompt "提示词" --out 输出.png [--size 1024x1024] [--no-revise] [--footnote "品牌名"]
# 垫图(图生图):--image 接图片路径、base64 或 data URL
scripts/generate.mjs --prompt "提示词" --image 垫图.jpg --out 输出.png
  • --size: only supports 1024x1024 / 1280x720 / 720x1280 / 2048x512 (upstream limit: width and height [512,2048] and area ≤ 1024x1024)
  • --no-revise: disable the model's automatic prompt polishing (enabled by default)
  • --footnote: watermark text in the bottom-right corner ≤16 characters; default is a single space = no watermark (the user is responsible for compliance when removing the watermark)
  • Prompt limit is 4000 characters, Chinese is fine
  • 429/5xx has a built-in 2-second retry once; if it still fails, handle it according to the error message

Step 2: Delivery

  • After generationFirst view the image(Read tool) confirm the quality before delivering to the user; if unsatisfied, change the prompt and regenerate
  • The returned image URL is a signed address that will expire; the script has already downloaded it to disk immediately, so only deliver the local file
  • In image-reference mode, prompts written as image-editing instructions like "keep the composition, replace ×× with ××" work better

Quick Reference

Requirement Parameter Use case
1:1 square image --size 1024x1024 Avatars, icons, knowledge cards
16:9 horizontal image --size 1280x720 PPT illustrations, banners
9:16 vertical image --size 720x1280 Mobile posters, Xiaohongshu
4:1 ultra-wide --size 2048x512 WeChat Official Account header images, banners

Environment variables:TCB_ENV_ID、TCB_SECRET_ID、TCB_SECRET_KEY(credentials), HUNYUAN_CONFIG(custom configuration file path),HUNYUAN_SDK_DIR(custom SDK installation directory).

Common Mistakes

  • Commit the key into the repository or paste it into the conversation: SecretId/SecretKey and the like have the same account permissions, so only put them in ~/.hunyuan/config.env(chmod 600) or environment variables
  • Use an unsupported size: for example, 1536x2048 will be rejected; you can only choose one of the four (see Quick Reference)
  • 422 is still retrying: 422 means the prompt triggered content moderation; resending the same content will inevitably fail again, so change the wording
  • Generate directly without a resource pack: this will incur pay-as-you-go charges; guide the user to first claim the "Mini Program Growth Plan" incentive resource pack for free (100,000 image generation credits) and bind it to the environment in use
  • Wrong environment ID entered: the resource pack is bound to the environment created when it was claimed; the environment corresponding to the credentials must have a resource pack
  • Deliver without checking after generation: Read and view it first before giving it to the user