agentsclimarketplace

Sub2api 4k image generator ts

Skill fengyunzaidushi/sub2api-4k-image-generator-ts/sub2api-4k-image-generator-ts

Codex skill and TypeScript CLI for 4K AI image generation through self-hosted sub2api OpenAI-compatible endpoints, with streaming, SSE, partial image capture, and Cloudflare 524 timeout mitigation.

Install
npx -y skills add fengyunzaidushi/sub2api-4k-image-generator-ts --skill sub2api-4k-image-generator-ts

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 12 stars12 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

TypeScript-only skill for generating and debugging high-resolution AI images through sub2api OpenAI-compatible APIs. Use this whenever the user wants a TS/Node sub2api image generator, 4K image generation, stream=true /v1/images/generations or /v1/responses image generation, Cloudflare 524 timeout avoidance, partial image capture, or SUB2API_BASE_URL/SUB2API_API_KEY based image generation.

SKILL.md

2.2 KB, as published. Nobody here has run it

sub2api 4K Image Generator TS

Use this skill when the user wants TypeScript/Node image generation through sub2api rather than Codex's built-in image tool.

Workflow

  1. Work from the skill root that contains this SKILL.md.
  2. Ensure .env or the process environment provides:
SUB2API_BASE_URL=https://your-sub2api.example.com
SUB2API_API_KEY=sk-...
  1. Prefer the compiled JS entrypoint for normal use:
node .\dist\openai_4k_image_generator.js `
  "剑仙，云海，发光长剑，无文字无水印" `
  --size 3840x2160 `
  --quality high `
  --output-dir output
  1. For development, run the TypeScript source:
npx tsx .\scripts\openai_4k_image_generator.ts "test prompt" --dry-run
  1. If Node/TypeScript is inconvenient, use the bundled Python request script:
python .\openai_4k_image_request.py "test prompt" --dry-run

Install python-dotenv first if Python reports that dotenv is missing.

  1. Report final image paths, partial image paths, and any Cloudflare/SSE diagnostic in plain language. Never print full API keys.

Notes

  • Replace SUB2API_BASE_URL with the user's own deployed sub2api domain.
  • Treat 4K as explicit pixel sizes: 3840x2160 or 2160x3840.
  • Streaming is enabled by default to avoid Cloudflare 524 during slow 4K generation.
  • *-partial-XX.png files are diagnostics only; final images are saved as <prefix>-XX.png.
  • openai_4k_image_request.py is a standalone Python fallback that supports /v1/images/generations, /v1/responses, --input-image, streaming SSE, and --dry-run.
  • Run npm test after editing the skill.
  • The bundled dist/ directory is enough for normal use; use scripts/ only for development or debugging.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.