Tools

Codex App image generation (api-image skill)

Install the community api-image skill in Codex App to restore image generation in API mode — with LMU AI just keep auth.json, then ask in plain language for text-to-image, image-to-image and inpainting.

api-image is a community skill (MIT licensed): the Codex App in API mode has no built-in imagegen, and once this skill is installed it can generate images through the OpenAI-compatible image endpoint you configure yourself. It reuses the key and endpoint in your ~/.codex, and one sentence in the conversation is enough.

Third-party community skill

It runs on your machine, reads the key from ~/.codex/auth.json, and sends your prompt and reference images to the provider — make sure you're comfortable with that before installing. The author also notes compatibility varies between providers, so treat real error messages as the source of truth.

Prep: keep auth.json

This skill reads the key from ~/.codex/auth.json (on Windows, %USERPROFILE%\.codex\auth.json). The updated Codex App guide now puts the key in a request header in config.toml and no longer needs auth.json, but to use this skill you need to keep one, holding the same key:

{
  "OPENAI_API_KEY": "your sk- key generated in the console"
}

If you already created auth.json with the old guide, just leave it as is.

Install: one sentence to Codex

Open the Codex App and just say:

Install the skill at https://github.com/yc-duan/api-image — I want to generate images with the OpenAI image 2 standard API; see the usage instructions at https://github.com/yc-duan/api-image

Codex puts the repo into ~/.codex/skills/api-image itself (%USERPROFILE%\.codex\skills\api-image on Windows); restart the Codex App afterwards.

Manual install works too:

git clone https://github.com/yc-duan/api-image.git ~/.codex/skills/api-image

Use: still one sentence

You wantSay this
Text to imageUse api-image to generate a 2048x1152 cinematic photo: a rainy Tokyo street at night, neon reflections, realistic photography style
Image to imageUsing this image's composition and pose as a reference, generate a warm illustration — keep the subject's pose, don't copy the original
InpaintingChange the red cup in this image to green, keeping the original shape, composition and lighting
Explicit optionsUse api-image to generate a 1024x1024 flat illustration, quality low, two images, saved to ./public/cover.png

The defaults are gpt-image-2, 2048x1152, quality high, one image; size, quality, count and output path can all be changed right in the conversation. Output lands in the current working directory by default (provider-image-<timestamp>.png).

Notes

  • For LMU AI, just keep auth.json: the skill reads auth.json (key) and config.toml (endpoint), corresponding to the full endpoints https://api.lmuai.com/v1/images/generations and /v1/images/edits
  • model_not_found / 403: your key's group doesn't include the image model — check "Available models" in the console or switch groups
  • gpt-image-2 doesn't support transparent backgrounds; the upstream may normalize requested sizes, so trust the actual output

Last updated:

京ICP备2020034311号-7

Codex App (Desktop)

Configure the LMU AI API base URL and key in the Codex App desktop client — works on both Windows and Mac.

CC Switch one-click import

Use the CC Switch desktop tool to import your LMU AI API config into Claude Code in one click, skipping the manual settings.json edit.

On this page

Prep: keep auth.jsonInstall: one sentence to CodexUse: still one sentenceNotes