Sub2api 4k image generator ts

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

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.From its SKILL.md

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.

3 things to look at

reads credentialsReads from 3 credential sources: `.env` and 2 more.
11 stars11 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.
runs commandsInstructs the agent to run 4 commands, including `node .\dist\openai_4k_image_generator.js` and 3 more.

SKILL.md

2.2 KB, 475 tokens by cl100k_base, 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

Work from the skill root that contains this SKILL.md.
Ensure .env or the process environment provides:

SUB2API_BASE_URL=https://your-sub2api.example.com
SUB2API_API_KEY=sk-...

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

For development, run the TypeScript source:

npx tsx .\scripts\openai_4k_image_generator.ts "test prompt" --dry-run

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.

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.

What ships with it: 16 files

40.8 KB alongside SKILL.md, 12 of them executable

agents/

openai.yaml224 B

scripts/

args.tsruns5.8 KB
cli.tsruns2.6 KB
env.tsruns995 B
errors.tsruns120 B
openai_4k_image_generator.tsruns394 B
payload.tsruns2.2 KB
request.tsruns2.6 KB
save.tsruns2.1 KB
sse.tsruns3.9 KB
test.tsruns4.3 KB
types.tsruns1.1 KB