mcpField
A
apimart-image-gen

apimart-image-gen

github.com/kangarookingCreative & media68847 installsUpdated 7w ago
Repository

About apimart-image-gen

APIMart Image Gen is a skill for generating images with GPT-Image-2 through APIMart. It submits asynchronous jobs, checks their status, and downloads results; it supports text prompts and URL or local-file references.

Key features

  1. 01Submit GPT-Image-2 image jobs
  2. 02Generate images from text prompts
  3. 03Use URL and local-file references
  4. 04Poll task status and download results
  5. 05Validate request shape with dry-run

Use cases

  1. 01Create an image from a text description
  2. 02Transform or combine reference images
  3. 03Check an existing job and download its output
  4. 04Validate image-generation parameters before submission

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/kangarooking/kangarooking-skills --skill apimart-image-gen

After installing, type/apimart-image-genin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
references/
api.md
scripts/
apimart_image_gen.py

Details

From the project README

APIMart Image Gen

Use this skill to submit GPT-Image-2 image jobs to APIMart, poll the async task result, and download returned image URLs.

Credential Rule

Read the API key from an environment variable. Do not hardcode API keys in prompts, scripts, skill files, zip packages, commits, or shell history.

Preferred variable:

export APIMART_API_KEY="..."

The helper also accepts APIMART_TOKEN as a fallback.

Quick Start

Use the bundled helper for normal requests:

python scripts/apimart_image_gen.py generate \
  --prompt "一只橘猫坐在窗台上看夕阳，水彩画风格" \
  --size "16:9" \
  --resolution "2k" \
  --output-dir ./outputs/apimart-image-gen

The script submits POST /v1/images/generations, waits before the first poll, queries GET /v1/tasks/{task_id}, and downloads completed image URLs into --output-dir.

Workflows

Text-to-image:

python scripts/apimart_image_gen.py generate \
  --prompt "a corgi astronaut on the moon, cinematic" \
  --size "16:9" \
  --resolution "2k"

Image-to-image with public URLs:

python scripts/apimart_image_gen.py generate \
  --prompt "把参考图变成水彩画风格" \
  --image-url "https://example.com/photo.jpg" \
  --size "4:3" \
  --resolution "2k"

Image-to-image with local files:

python scripts/apimart_image_gen.py generate \
  --prompt "融合这些参考图，生成一张公众号封面" \
  --image-file ./reference-a.png \
  --image-file ./reference-b.jpg \
  --size "21:9" \
  --resolution "2k"

Check an existing task:

python scripts/apimart_image_gen.py status \
  --task-id task_01KPQ7J7DWB7QZ3WCEK3YVPBRA \
  --download \
  --output-dir ./outputs/apimart-image-gen

Validate request shape without calling the API:

python scripts/apimart_image_gen.py generate \
  --prompt "星空下的古老城堡" \
  --size "16:9" \
  --resolution "4k" \
  --dry-run

Defaults And Limits

  • Model is fixed to gpt-image-2.
  • n is fixed to integer 1; do not send "1" as a string.
  • Valid resolution values are 1k, 2k, and 4k.
  • Valid ratio values are auto, 1:1, 3:2, 2:3, 4:3, 3:4, 5:4, 4:5, 16:9, 9:16, 2:1, 1:2, 3:1, 1:3, 21:9, and 9:21.
  • Pixel sizes such as 1881x836 or 887x1774 are also accepted.
  • Up to 16 reference images can be supplied across --image-url and --image-file.
  • Prefer putting aspect ratio in --size, not in the prompt, to avoid conflicting instructions.
  • Result URLs should be downloaded promptly because APIMart reports an expires_at timestamp.

Reference

Read references/api.md when you need endpoint details, status values, error handling, or the size/resolution map.

Comments

Markdown supported