Baoyu Image Gen

Image Generation (AI SDK)

User Input Tools

When this skill prompts the user, follow this tool-selection rule (priority order):

1. Prefer built-in user-input tools exposed by the current agent runtime — e.g., AskUserQuestion, request_user_input, clarify, ask_user, or any equivalent.
2. Fallback: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number/answer for each question.
3. Batching: if the tool supports multiple questions per call, combine all applicable questions into a single call; if only single-question, ask them one at a time in priority order.

Concrete AskUserQuestion references below are examples — substitute the local equivalent in other runtimes.

Script Directory

{baseDir} = this SKILL.md's directory; scripts/... paths are relative to it. Main script: {baseDir}/scripts/main.ts. Batch payload helper: {baseDir}/scripts/build-batch.ts. Resolve ${BUN_X}: prefer bun; else npx -y bun; else suggest brew install oven-sh/bun/bun.

Step 0: Load Preferences (blocking)

No image generation until EXTEND.md exists. Check in order; first hit wins:

Path	Scope
.baoyu-skills/baoyu-image-gen/EXTEND.md	Project
${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-image-gen/EXTEND.md	XDG
$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md	User home

• Found → load and apply. If default_model.[provider] is null → ask model only.
• Not found → run first-time setup (references/config/first-time-setup.md) via AskUserQuestion to collect provider + model + quality + save location. Save EXTEND.md, then continue.

Legacy: if .baoyu-skills/baoyu-imagine/EXTEND.md exists and the new path doesn't, the runtime renames it to baoyu-image-gen. If both exist, the runtime leaves them alone and uses the new path.

EXTEND.md keys: default provider, quality, aspect ratio, image size, OpenAI image API dialect, default models, batch worker cap, provider-specific batch limits. Schema: references/config/preferences-schema.md.

Usage

More examples (per provider, batch file format): references/usage-examples.md.

${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image cat.png
${BUN_X} {baseDir}/scripts/main.ts --prompt "A landscape" --image out.png --ar 16:9 --quality 2k
${BUN_X} {baseDir}/scripts/main.ts --promptfiles system.md content.md --image out.png
${BUN_X} {baseDir}/scripts/main.ts --prompt "Make blue" --image out.png --ref source.png
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider dashscope --model qwen-image-2.0-pro
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider codex-cli --ar 16:9   # Codex login, no OPENAI_API_KEY; needs `codex` on PATH

# Batch; build the payload from outline.md + prompts/ (e.g. baoyu-article-illustrator output)
${BUN_X} {baseDir}/scripts/build-batch.ts --outline outline.md --prompts prompts --output batch.json --images-dir attachments
${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json --jobs 4

Reference-Image Identity Preservation

When a real person/character/object must be preserved from reference images:

• Use short, hard identity language instead of a long generic description: "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. Keep the face/proportions/hair/key accessories/overall identity from the references." With multiple refs, say they are the same subject and jointly define identity.
• Long feature descriptions ("young East Asian woman, oval face, clear eyes...") make the model synthesize a new matching person instead.
• Prefer 2–4 curated existing source refs; many or multi-megabyte refs can destabilize streaming providers.
• Don't use newly generated outputs as refs unless the user asks (drift compounds).
• Too polished/influencer-like → reduce stylized refs, add anti-beautification constraints (no face slimming, eye enlargement, heavy makeup, commercial travel shoot, over-smoothing).
• Younger/older look → keep the face; express age via clothing, posture, scene, styling. Never ask to change facial identity.

Options

Option	Description
--prompt <text>, -p	Prompt text
--promptfiles <files...>	Read prompt from files (concatenated)
--image <path>	Output image path (required in single-image mode)
--batchfile <path>	JSON batch file for multi-image generation
--jobs <count>	Worker count for batch mode (default: auto, max from config, built-in default 10)
--provider google|openai|azure|openrouter|dashscope|zai|minimax|jimeng|seedream|replicate|codex-cli|agnes	Force provider (default: auto-detect; codex-cli is never auto-selected — must be pinned via CLI or EXTEND.md)
--model <id>, -m	Model ID — see provider references for defaults and allowed values
--ar <ratio>	Aspect ratio (16:9, 1:1, 4:3, …)
--size <WxH>	Explicit size (e.g., 1024x1024; for gpt-image-2.5-* and gpt-image-2, width/height must be multiples of 16, max edge 3840px, ratio no wider than 3:1)
--quality normal|2k	Quality preset (default: 2k)
--imageSize 1K|2K|4K	Image size for Google/OpenRouter (default: from quality)
--imageApiDialect openai-native|ratio-metadata	OpenAI-compatible endpoint dialect — use ratio-metadata for gateways that expect aspect-ratio size plus metadata.resolution
--ref <files...>	Reference images. Supported by Google multimodal, OpenAI GPT Image edits, Azure OpenAI edits (PNG/JPG only), OpenRouter multimodal models, Replicate supported families, MiniMax subject-reference, Seedream 5.0/4.5/4.0, DashScope wan2.7-image-pro/wan2.7-image. Not supported by Jimeng, Seedream 3.0, SeedEdit 3.0, or any DashScope model outside the wan2.7-image* family
--n <count>	Number of images. Replicate requires --n 1 (single-output save semantics)
--json	JSON output

Environment Variables

Variable	Description
OPENAI_API_KEY	OpenAI API key
AZURE_OPENAI_API_KEY	Azure OpenAI API key
OPENROUTER_API_KEY	OpenRouter API key
GOOGLE_API_KEY	Google API key
DASHSCOPE_API_KEY	DashScope API key
ZAI_API_KEY (alias BIGMODEL_API_KEY)	Z.AI API key
MINIMAX_API_KEY	MiniMax API key
REPLICATE_API_TOKEN	Replicate API token
JIMENG_ACCESS_KEY_ID, JIMENG_SECRET_ACCESS_KEY	Jimeng (即梦) Volcengine credentials
ARK_API_KEY	Seedream (豆包) Volcengine ARK API key
<PROVIDER>_IMAGE_MODEL	Per-provider model override (OPENAI_IMAGE_MODEL, GOOGLE_IMAGE_MODEL, DASHSCOPE_IMAGE_MODEL, ZAI_IMAGE_MODEL/BIGMODEL_IMAGE_MODEL, MINIMAX_IMAGE_MODEL, OPENROUTER_IMAGE_MODEL, REPLICATE_IMAGE_MODEL, JIMENG_IMAGE_MODEL, SEEDREAM_IMAGE_MODEL, AGNES_IMAGE_MODEL)
AZURE_OPENAI_DEPLOYMENT (alias AZURE_OPENAI_IMAGE_MODEL)	Azure default deployment
<PROVIDER>_BASE_URL	Per-provider endpoint override
AZURE_API_VERSION	Azure image API version (default 2025-04-01-preview)
JIMENG_REGION	Jimeng region (default cn-north-1)
OPENAI_IMAGE_API_DIALECT	openai-native | ratio-metadata
OPENROUTER_HTTP_REFERER, OPENROUTER_TITLE	Optional OpenRouter attribution
BAOYU_IMAGE_GEN_MAX_WORKERS	Override batch worker cap
BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY	Per-provider concurrency (e.g., BAOYU_IMAGE_GEN_REPLICATE_CONCURRENCY; for codex-cli use BAOYU_IMAGE_GEN_CODEX_CLI_CONCURRENCY)
BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS	Per-provider start-gap
BAOYU_CODEX_IMAGEGEN_BIN	Override the codex-imagegen wrapper path for the codex-cli provider (default: bundled scripts/codex-imagegen/main.ts; accepts .ts or legacy .sh/binary)
BAOYU_CODEX_IMAGEGEN_CACHE_DIR	Enable idempotency cache for the codex-cli provider (off by default)
BAOYU_CODEX_IMAGEGEN_TIMEOUT_MS	Per-attempt codex exec timeout for the codex-cli provider (default: 300000 ms)
BAOYU_CODEX_IMAGEGEN_RETRIES	Wrapper-side retry attempts on retryable errors for the codex-cli provider (default: 2)
BAOYU_CODEX_IMAGEGEN_LOG_FILE	Append JSONL diagnostic log for the codex-cli provider

Load priority: CLI args > EXTEND.md > env vars > <cwd>/.baoyu-skills/.env > ~/.baoyu-skills/.env

Codex/ChatGPT OAuth Is Not an OpenAI API Key

--provider openai calls the standard OpenAI Images API (/v1/images/generations, /v1/images/edits) and requires OPENAI_API_KEY. A Codex/ChatGPT login is a different entitlement: never paste a Codex OAuth token into OPENAI_API_KEY or just point OPENAI_BASE_URL at a Codex backend. Do not modify the openai provider to silently consume Codex OAuth.

To use a Codex subscription without an API key:

• Codex runtime: native imagegen skill/tool.
• Non-Codex runtime with codex CLI installed and logged in: --provider codex-cli (preferred; same retry/cache/batch flow). It spawns the bundled scripts/codex-imagegen/main.ts (upstream: packages/baoyu-codex-imagegen/src/main.ts).
• Hermes runtime with native image_generate: use as fallback; state whether refs were passed directly or reconstructed from extracted traits.

Fallback: if --provider openai fails only because OPENAI_API_KEY is missing and one of the backends above is available, use it rather than leaving the user waiting, and say whether it was true reference-image generation or a text reconstruction from visual traits. Details: references/codex-oauth-vs-openai-api-key.md, references/codex-image2-fallback.md.

Model Resolution

Priority for every provider: CLI --model <id> > EXTEND.md default_model.[provider] > env <PROVIDER>_IMAGE_MODEL > built-in default.

• OpenAI: default gpt-image-2.5-flare (fastest). gpt-image-2.5-sunburst is most capable for complex scenes and precise edits; gpt-image-2, gpt-image-1.5, gpt-image-1 and dated snapshots (e.g. gpt-image-2.5-flare-2026-09-08, gpt-image-2-2026-04-21) stay selectable.
• Google: default gemini-3-pro-image. gemini-3.1-flash-image is faster/cheaper; gemini-3.1-flash-lite-image is cheapest and 1K-only (--quality 2k / --imageSize 2K|4K clamp to 1K with a warning).
• DashScope: default qwen-image-2.0-pro; qwen-image-3.0-pro is the newest flagship with the same sizing rules.
• Azure: --model / default_model.azure is the deployment name (AZURE_OPENAI_DEPLOYMENT, alias AZURE_OPENAI_IMAGE_MODEL). Use gpt-image-2.5-flare if the deployment is named after the model, else the exact custom name.

Before each generation, display:

• Using [provider] / [model]
• Switch model: --model <id> | EXTEND.md default_model.[provider] | env <PROVIDER>_IMAGE_MODEL

OpenAI-Compatible Gateway Dialects

provider=openai only means OpenAI-compatible auth/routing, not native image semantics. Set default_image_api_dialect (EXTEND.md), OPENAI_IMAGE_API_DIALECT, or --imageApiDialect:

• openai-native: pixel size (1536x1024) and native quality fields — OpenAI and strict clones
• ratio-metadata: aspect-ratio size (16:9) + metadata.resolution (1K|2K|4K) + metadata.orientation — gateways fronting Gemini or similar. Text-to-image only; reference edits need openai-native or a provider with first-class edit support.

Provider-Specific Guides

Read when the user picks that provider or asks for non-default behavior:

Provider	Reference
DashScope (Qwen-Image families, custom sizes)	references/providers/dashscope.md
Z.AI (GLM-Image, cogview-4)	references/providers/zai.md
MiniMax (image-01, subject-reference)	references/providers/minimax.md
OpenRouter (multimodal models, /chat/completions flow)	references/providers/openrouter.md
Replicate (nano-banana, Seedream, Wan)	references/providers/replicate.md
Codex CLI (wraps bundled scripts/codex-imagegen/; Codex login, no OPENAI_API_KEY)	references/providers/codex-cli.md
Agnes (agnes-image-2.5-flash, reference-image support)	references/providers/agnes.md

Provider Selection

1. --ref provided + no --provider → auto-select Google → OpenAI → Azure → OpenRouter → Replicate → Seedream → MiniMax → Agnes (MiniMax subject reference is specialized for character/portrait consistency)
2. --provider specified → use it (with --ref, must be google/openai/azure/openrouter/replicate/seedream/minimax/codex-cli/agnes)
3. Only one API key present → that provider
4. Multiple keys → Google → OpenAI → Azure → OpenRouter → DashScope → Z.AI → MiniMax → Replicate → Jimeng → Seedream → Agnes
5. codex-cli is never auto-selected — pin via default_provider: codex-cli or --provider codex-cli. Runs codex exec through the bundled scripts/codex-imagegen/main.ts (with bun) on the user's Codex subscription; requires codex on PATH with an active codex login.

Quality Presets

Preset	Google imageSize	OpenAI size	OpenRouter size	Replicate resolution	Use case
normal	1K	1024px target	1K	1K	Quick previews
2k (default)	2K	2048px target	2K	2K	Covers, illustrations, infographics

Google/OpenRouter imageSize can be overridden with --imageSize 1K|2K|4K.

OpenAI native gpt-image-2.5-* / gpt-image-2: normal → quality=medium + low-latency valid size near the ratio; 2k → quality=high + 2048px-class sizes (2048x2048, 2048x1152, 1152x2048). Use explicit --size for custom or 4K (e.g. 3840x2160).

Aspect Ratios

Supported: 1:1, 16:9, 9:16, 4:3, 3:4, 2.35:1.

• Google multimodal: imageConfig.aspectRatio
• OpenAI: gpt-image-2.5-* / gpt-image-2 use the closest valid custom size; older GPT Image and DALL·E use the closest fixed size
• OpenRouter: imageGenerationOptions.aspect_ratio; with only --size <WxH>, the ratio is inferred
• Replicate: model-specific — google/nano-banana* uses aspect_ratio, bytedance/seedream-* uses documented Replicate ratios, Wan 2.7 maps --ar to a concrete size
• MiniMax: official aspect_ratio values; --size <WxH> without --ar sends width/height for image-01

Generation Mode

Default: sequential. Batch parallel: automatic when --batchfile has 2+ pending tasks.

Situation	Prefer
One image, or 1-2 simple images	Sequential
Multiple images with saved prompt files	Batch (--batchfile) — shared throttling/retries
Each image still needs its own reasoning / prompt writing / style exploration	Subagents
Input is outline.md + prompts/ (e.g. from baoyu-article-illustrator)	Batch, payload built with {baseDir}/scripts/build-batch.ts

Once prompt files are saved and the task is "generate all of these", prefer batch over subagents.

Parallel behavior: worker count auto, capped by config (built-in default 10), override with --jobs <count>; provider-specific throttling applies only in batch mode; each image retries up to 3 attempts; final output reports success count, failure count, and per-image failure reasons.

Error Handling

• Missing API key → error with setup instructions (for OpenAI see the Codex fallback above)
• Generation failure → auto-retry up to 3 attempts per image
• Invalid aspect ratio → warning, proceed with default
• Reference images with unsupported provider/model → error with fix hint

Extension Support

Custom configurations via EXTEND.md. See Step 0 for paths and schema.