Jim Liu 宝玉
c3cbce9ce3
BREAKING CHANGE: removed `baoyu-imagine` and `baoyu-image-cards`. All functionality now lives under `baoyu-image-gen` and `baoyu-xhs-images` respectively. Cross-skill `## Image Generation Tools` examples updated across baoyu-article-illustrator, baoyu-comic, baoyu-cover-image, baoyu-infographic, and baoyu-slide-deck. Migration: existing `~/.baoyu-skills/baoyu-imagine/EXTEND.md` configs are auto-renamed to `…/baoyu-image-gen/EXTEND.md` on first run via the legacy-path resolver in `scripts/main.ts`.
1.9 KiB
Codex OAuth vs OpenAI API key for baoyu-image-gen
baoyu-image-gen --provider openai uses the standard OpenAI Images API and requires OPENAI_API_KEY. It calls OpenAI-compatible image endpoints such as /images/generations and /images/edits.
Codex / ChatGPT login is different. Codex image generation is driven by Codex OAuth and the Codex runtime's image_gen capability, not by the public OpenAI Images API key path. A Codex OAuth token is not a drop-in replacement for OPENAI_API_KEY, and setting OPENAI_BASE_URL to a Codex backend will not make baoyu-image-gen's existing openai provider work because the auth, route, and payload shape differ.
What to use instead
- If running inside Codex and the native
imagegenskill/tool is available, use it directly. - If running outside Codex but the
codexCLI is installed and logged in, use the repo-levelscripts/codex-imagegen.shwrapper when the calling skill supports it. The wrapper invokescodex execand the Codeximage_gentool; noOPENAI_API_KEYis required. - If running inside Hermes and a native
image_generatetool is available, use that as a runtime-native fallback. Be explicit about whether reference images are passed directly or only reconstructed from extracted traits. - If the user wants
baoyu-image-genitself to support Codex OAuth, add a distinct provider such asopenai-codexrather than modifying the existingopenaiprovider.
Reference-image prompting note
When using actual reference images for identity preservation, avoid long generic descriptions of the subject. Long descriptions can cause the model to synthesize a new similar-looking person/object. Prefer direct wording:
Use the person/object in the reference image(s) as the same identity. Do not redesign it or create a similar-looking new subject. Only change scene, clothing, pose, lighting, rendering style, and composition.