AI image generation with OpenAI GPT Image 2.5, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate and Agnes APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch par

Image Generation (AI SDK) Official API based image generation. Supports OpenAI GPT Image 2.5, Azure OpenAI, Google, OpenRouter, DashScope (阿里通义万象), Z.AI GLM Image, MiniMax, Jimeng (即梦), Seedream (豆包), Replicate and Agnes. 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. All scripts/... paths below are relative to {baseDir} . 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 This step MUST complete before any image generation — generation is blocked until EXTEND.md exists. Check these paths 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, parse, apply. If default model.[provider] is null → ask model only. Not found → run first time setup ( references/config/first time setup.md ) using AskUserQuestion to collect provider + model + quality + save location. Save EXTEND.md, then continue. Do not generate images before this completes. Legacy compatibility: 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, default quality, default aspect ratio, default image size, OpenAI image API dialect, default models, batch worker cap, provider specific batch limits. Schema: references/config/preferences schema.md . Usage Minimum working examples — see references/usage examples.md for the full set including per provider invocations and batch mode. Identity preserving reference prompts When the user wants a real person/character/object preserved from reference images, do not replace the reference with a long generic description. Prefer short, hard identity preservation language: "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." If using multiple references, state that they are the same subject and should jointly define identity. Pitfall: long descriptions like "young East Asian woman, oval face, clear eyes..." can cause the model to synthesize a new person matching the description instead of preserving the referenced person. Reference Image Identity Preservation When the user wants a person/object preserved from reference images: Prefer a small curated set of existing source references (usually 2–4) over many images; large multi megabyte refs can destabilize streaming providers. Make the prompt say the references are the same subject and the output must use that identity. Avoid long generic facial feature descriptions that can cause the model to synthesize a new similar looking person. Do not use newly generated outputs as references unless the user explicitly asks; generated refs compound drift. If results become too polished or influencer like, reduce stylized refs and add explicit anti beautification constraints (no face slimming, eye enlargement, heavy makeup, commercial travel shoot, over smoothing). If the subject should look younger/older, preserve the face and express age through clothing, posture, scene, and styling; do not ask the model 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 model gpt image 2.5 flare uses the standard OpenAI Images API ( /v1/images/generations or /v1/images/edits ) and requires OPENAI API KEY . A Codex or ChatGPT desktop login is a different entitlement and is not a drop in replacement for OPENAI API KEY ; do not paste a Codex OAuth token into OPENAI API KEY or only set OPENAI BASE URL to a Codex backend. If the user wants to use their Codex subscription / GPT Image 2 entitlement without an OpenAI API key, route through a Codex native backend instead of this skill's openai provider: In Codex runtime: use the native imagegen skill/tool. In non Codex runtimes with codex CLI installed and logged in: use baoyu image gen provider codex cli (preferred — it gives you the same retry / cache / batch flow as every other provider). The provider spawns the bundled scripts/codex imagegen/main.ts ; the same code lives upstream at packages/baoyu codex imagegen/src/main.ts for standalone callers. In Hermes runtimes with a native image generate tool: use that tool as a fallback, and state whether reference images were passed directly or reconstructed from extracted traits. Do not modify the existing openai provider to silently consume Codex OAuth. The first class Codex CLI path is the dedicated codex cli provider, which has its own auth (Codex login), route ( codex exec ), request shape, and tests. See references/codex oauth vs openai api key.md . Model Resolution Priority (highest → lowest) applies to every provider: 1. CLI flag model <id 2. EXTEND.md default model.[provider] 3. Env var <PROVIDER IMAGE MODEL 4. Built in default For OpenAI, the built in default is gpt image 2.5 flare (fast, lowest latency). gpt image 2.5 sunburst is the most capable variant for complex scenes and precise edits; gpt image 2 , gpt image 1.5 , gpt image 1 , and dated GPT Image snapshots (e.g. gpt image 2.5 flare 2026 09 08 , gpt image 2 2026 04 21 ) remain selectable with model or OPENAI IMAGE MODEL . For Google, the built in default is gemini 3 pro image . gemini 3.1 flash image is the faster low cost option, and gemini 3.1 flash lite image is the cheapest — it only produces 1K output, so quality 2k / imageSize 2K 4K is clamped to 1K with a warning. For DashScope, the built in default is qwen image 2.0 pro ; qwen image 3.0 pro is the newest flagship and uses the same sizing rules. For Azure, model / default model.azure is the Azure deployment name. AZURE OPENAI DEPLOYMENT is the preferred env var; AZURE OPENAI IMAGE MODEL is kept as a backward compatible alias. If your Azure deployment is named after the underlying model, use gpt image 2.5 flare ; otherwise use the exact custom deployment name. EXTEND.md overrides env vars: if EXTEND.md sets default model.google: "gemini 3 pro image" and the env var sets GOOGLE IMAGE MODEL=gemini 3.1 flash image , EXTEND.md wins. Display model info before each generation : Using [provider] / [model] Switch model: model <id EXTEND.md default model.[provider] env <PROVIDER IMAGE MODEL OpenAI Compatible Gateway Dialects provider=openai means the auth and routing entrypoint is OpenAI compatible. It does not guarantee the upstream image API uses OpenAI native semantics. When a gateway expects a different wire format, set default image

baoyu-image-gen