{"id":"ea4edbca-3c1b-4ff3-9d86-6f5bf2d03643","shortId":"Z9vyqk","kind":"skill","title":"baoyu-imagine","tagline":"AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; us","description":"# Image Generation (AI SDK)\n\nOfficial API-based image generation. Supports OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope (阿里通义万象), Z.AI GLM-Image, MiniMax, Jimeng (即梦), Seedream (豆包) and Replicate.\n\n## User Input Tools\n\nWhen this skill prompts the user, follow this tool-selection rule (priority order):\n\n1. **Prefer built-in user-input tools** exposed by the current agent runtime — e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent.\n2. **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.\n3. **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.\n\nConcrete `AskUserQuestion` references below are examples — substitute the local equivalent in other runtimes.\n\n## Script Directory\n\n`{baseDir}` = this SKILL.md's directory. Main script: `{baseDir}/scripts/main.ts`. Resolve `${BUN_X}`: prefer `bun`; else `npx -y bun`; else suggest `brew install oven-sh/bun/bun`.\n\n## Step 0: Load Preferences ⛔ BLOCKING\n\nThis step MUST complete before any image generation — generation is blocked until EXTEND.md exists.\n\nCheck these paths in order; first hit wins:\n\n| Path | Scope |\n|------|-------|\n| `.baoyu-skills/baoyu-imagine/EXTEND.md` | Project |\n| `${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-imagine/EXTEND.md` | XDG |\n| `$HOME/.baoyu-skills/baoyu-imagine/EXTEND.md` | User home |\n\n- **Found** → load, parse, apply. If `default_model.[provider]` is null → ask model only.\n- **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.\n\nLegacy compatibility: if `.baoyu-skills/baoyu-image-gen/EXTEND.md` exists and the new path doesn't, the runtime renames it to `baoyu-imagine`. If both exist, the runtime leaves them alone and uses the new path.\n\n**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`.\n\n## Usage\n\nMinimum working examples — see `references/usage-examples.md` for the full set including per-provider invocations and batch mode.\n\n```bash\n# Basic\n${BUN_X} {baseDir}/scripts/main.ts --prompt \"A cat\" --image cat.png\n\n# With aspect ratio and high quality\n${BUN_X} {baseDir}/scripts/main.ts --prompt \"A landscape\" --image out.png --ar 16:9 --quality 2k\n\n# Prompt from files\n${BUN_X} {baseDir}/scripts/main.ts --promptfiles system.md content.md --image out.png\n\n# With reference image\n${BUN_X} {baseDir}/scripts/main.ts --prompt \"Make blue\" --image out.png --ref source.png\n\n# Specific provider\n${BUN_X} {baseDir}/scripts/main.ts --prompt \"A cat\" --image out.png --provider dashscope --model qwen-image-2.0-pro\n\n# OpenAI GPT Image 2\n${BUN_X} {baseDir}/scripts/main.ts --prompt \"A cat\" --image out.png --provider openai --model gpt-image-2\n\n# Batch mode\n${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json --jobs 4\n```\n\n## Options\n\n| Option | Description |\n|--------|-------------|\n| `--prompt <text>`, `-p` | Prompt text |\n| `--promptfiles <files...>` | Read prompt from files (concatenated) |\n| `--image <path>` | Output image path (required in single-image mode) |\n| `--batchfile <path>` | JSON batch file for multi-image generation |\n| `--jobs <count>` | Worker count for batch mode (default: auto, max from config, built-in default 10) |\n| `--provider google\\|openai\\|azure\\|openrouter\\|dashscope\\|zai\\|minimax\\|jimeng\\|seedream\\|replicate` | Force provider (default: auto-detect) |\n| `--model <id>`, `-m` | Model ID — see provider references for defaults and allowed values |\n| `--ar <ratio>` | Aspect ratio (`16:9`, `1:1`, `4:3`, …) |\n| `--size <WxH>` | Explicit size (e.g., `1024x1024`; for `gpt-image-2`, width/height must be multiples of 16, max edge 3840px, ratio no wider than 3:1) |\n| `--quality normal\\|2k` | Quality preset (default: `2k`) |\n| `--imageSize 1K\\|2K\\|4K` | Image size for Google/OpenRouter (default: from quality) |\n| `--imageApiDialect openai-native\\|ratio-metadata` | OpenAI-compatible endpoint dialect — use `ratio-metadata` for gateways that expect aspect-ratio `size` plus `metadata.resolution` |\n| `--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| `--n <count>` | Number of images. Replicate requires `--n 1` (single-output save semantics) |\n| `--json` | JSON output |\n\n## Environment Variables\n\n| Variable | Description |\n|----------|-------------|\n| `OPENAI_API_KEY` | OpenAI API key |\n| `AZURE_OPENAI_API_KEY` | Azure OpenAI API key |\n| `OPENROUTER_API_KEY` | OpenRouter API key |\n| `GOOGLE_API_KEY` | Google API key |\n| `DASHSCOPE_API_KEY` | DashScope API key |\n| `ZAI_API_KEY` (alias `BIGMODEL_API_KEY`) | Z.AI API key |\n| `MINIMAX_API_KEY` | MiniMax API key |\n| `REPLICATE_API_TOKEN` | Replicate API token |\n| `JIMENG_ACCESS_KEY_ID`, `JIMENG_SECRET_ACCESS_KEY` | Jimeng (即梦) Volcengine credentials |\n| `ARK_API_KEY` | Seedream (豆包) Volcengine ARK API key |\n| `<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`) |\n| `AZURE_OPENAI_DEPLOYMENT` (alias `AZURE_OPENAI_IMAGE_MODEL`) | Azure default deployment |\n| `<PROVIDER>_BASE_URL` | Per-provider endpoint override |\n| `AZURE_API_VERSION` | Azure image API version (default `2025-04-01-preview`) |\n| `JIMENG_REGION` | Jimeng region (default `cn-north-1`) |\n| `OPENAI_IMAGE_API_DIALECT` | `openai-native` \\| `ratio-metadata` |\n| `OPENROUTER_HTTP_REFERER`, `OPENROUTER_TITLE` | Optional OpenRouter attribution |\n| `BAOYU_IMAGE_GEN_MAX_WORKERS` | Override batch worker cap |\n| `BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY` | Per-provider concurrency (e.g., `BAOYU_IMAGE_GEN_REPLICATE_CONCURRENCY`) |\n| `BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS` | Per-provider start-gap |\n\n**Load priority**: CLI args > EXTEND.md > env vars > `<cwd>/.baoyu-skills/.env` > `~/.baoyu-skills/.env`\n\n## Model Resolution\n\nPriority (highest → lowest) applies to every provider:\n\n1. CLI flag `--model <id>`\n2. EXTEND.md `default_model.[provider]`\n3. Env var `<PROVIDER>_IMAGE_MODEL`\n4. Built-in default\n\nFor OpenAI, the built-in default is `gpt-image-2`. `gpt-image-1.5`, `gpt-image-1`, and GPT Image snapshots remain selectable with `--model` or `OPENAI_IMAGE_MODEL`.\n\nFor 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`; otherwise use the exact custom deployment name.\n\nEXTEND.md overrides env vars: if EXTEND.md sets `default_model.google: \"gemini-3-pro-image-preview\"` and the env var sets `GOOGLE_IMAGE_MODEL=gemini-3.1-flash-image-preview`, EXTEND.md wins.\n\n**Display model info before each generation**:\n\n- `Using [provider] / [model]`\n- `Switch model: --model <id> | EXTEND.md default_model.[provider] | env <PROVIDER>_IMAGE_MODEL`\n\n## OpenAI-Compatible Gateway Dialects\n\n`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_api_dialect` in EXTEND.md, `OPENAI_IMAGE_API_DIALECT`, or `--imageApiDialect`:\n\n- `openai-native`: pixel `size` (`1536x1024`) and native OpenAI quality fields\n- `ratio-metadata`: aspect-ratio `size` (`16:9`) plus `metadata.resolution` (`1K|2K|4K`) and `metadata.orientation`\n\nUse `openai-native` for the OpenAI native API or strict clones; try `ratio-metadata` for compatibility gateways in front of Gemini or similar models. Current limitation: `ratio-metadata` applies only to text-to-image; reference-image edits still need `openai-native` or a provider with first-class edit support.\n\n## Provider-Specific Guides\n\nEach provider has its own quirks (model families, size rules, ref support, limits). Read these when the user picks that provider or asks for non-default behavior:\n\n| Provider | Reference |\n|----------|-----------|\n| DashScope (Qwen-Image families, custom sizes) | `references/providers/dashscope.md` |\n| Z.AI (GLM-Image, cogview-4) | `references/providers/zai.md` |\n| MiniMax (image-01, subject-reference) | `references/providers/minimax.md` |\n| OpenRouter (multimodal models, `/chat/completions` flow) | `references/providers/openrouter.md` |\n| Replicate (nano-banana, Seedream, Wan) | `references/providers/replicate.md` |\n\n## Provider Selection\n\n1. `--ref` provided + no `--provider` → auto-select Google → OpenAI → Azure → OpenRouter → Replicate → Seedream → MiniMax (MiniMax's subject reference is more specialized toward character/portrait consistency)\n2. `--provider` specified → use it (if `--ref`, must be google/openai/azure/openrouter/replicate/seedream/minimax)\n3. Only one API key present → use that provider\n4. Multiple keys → default priority: Google → OpenAI → Azure → OpenRouter → DashScope → Z.AI → MiniMax → Replicate → Jimeng → Seedream\n\n## Quality Presets\n\n| Preset | Google imageSize | OpenAI size | OpenRouter size | Replicate resolution | Use case |\n|--------|------------------|-------------|-----------------|----------------------|----------|\n| `normal` | 1K | 1024px target | 1K | 1K | Quick previews |\n| `2k` (default) | 2K | 2048px target | 2K | 2K | Covers, illustrations, infographics |\n\nGoogle/OpenRouter `imageSize` can be overridden with `--imageSize 1K|2K|4K`.\n\nFor OpenAI native `gpt-image-2`, `normal` maps to `quality=medium` and a low-latency valid size near the requested aspect ratio; `2k` maps to `quality=high` and 2048px-class sizes such as `2048x2048`, `2048x1152`, or `1152x2048`. Use explicit `--size` for valid custom or 4K outputs, e.g. `3840x2160`.\n\n## Aspect Ratios\n\nSupported: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `2.35:1`.\n\n- Google multimodal: `imageConfig.aspectRatio`\n- OpenAI: `gpt-image-2` uses the closest valid custom size for the requested ratio; older GPT Image and DALL·E models use their closest supported fixed size\n- OpenRouter: `imageGenerationOptions.aspect_ratio`; if only `--size <WxH>` is given, the ratio is inferred\n- Replicate: behavior is model-specific — `google/nano-banana*` uses `aspect_ratio`, `bytedance/seedream-*` uses documented Replicate ratios, Wan 2.7 maps `--ar` to a concrete `size`\n- MiniMax: official `aspect_ratio` values; if `--size <WxH>` is given without `--ar`, sends `width`/`height` for `image-01`\n\n## Generation Mode\n\n**Default**: sequential. **Batch parallel**: enabled automatically when `--batchfile` contains 2+ pending tasks.\n\n| Situation | Prefer | Why |\n|-----------|--------|-----|\n| One image, or 1-2 simple images | Sequential | Lower coordination overhead, easier debugging |\n| Multiple images with saved prompt files | Batch (`--batchfile`) | Reuses finalized prompts, applies shared throttling/retries, predictable throughput |\n| Each image still needs its own reasoning / prompt writing / style exploration | Subagents | Work is still exploratory, each needs independent analysis |\n| Input is `outline.md` + `prompts/` (e.g. from `baoyu-article-illustrator`) | Batch — use `scripts/build-batch.ts` to assemble the payload | The outline + prompt files already contain everything needed |\n\nRule of thumb: once prompt files are saved and the task is \"generate all of these\", prefer batch over subagents. Use subagents only when generation is coupled with per-image thinking or divergent creative exploration.\n\n**Parallel behavior**:\n\n- Default worker count is automatic, capped by config, built-in default 10\n- Provider-specific throttling applies only in batch mode; defaults are tuned for throughput while avoiding RPM bursts\n- Override with `--jobs <count>`\n- Each image retries up to 3 attempts\n- Final output includes success count, failure count, and per-image failure reasons\n\n## Error Handling\n\n- Missing API key → error with setup instructions\n- Generation failure → auto-retry up to 3 attempts per image\n- Invalid aspect ratio → warning, proceed with default\n- Reference images with unsupported provider/model → error with fix hint\n\n## References\n\n| File | Content |\n|------|---------|\n| `references/usage-examples.md` | Extended CLI examples across providers and batch mode |\n| `references/providers/dashscope.md` | DashScope families, sizes, limits |\n| `references/providers/zai.md` | Z.AI GLM-image / cogview-4 |\n| `references/providers/minimax.md` | MiniMax image-01 + subject reference |\n| `references/providers/openrouter.md` | OpenRouter multimodal flow |\n| `references/providers/replicate.md` | Replicate supported families + guardrails |\n| `references/config/preferences-schema.md` | EXTEND.md schema |\n| `references/config/first-time-setup.md` | First-time setup flow |\n\n## Extension Support\n\nCustom configurations via EXTEND.md. See Step 0 for paths and schema.","tags":["baoyu","imagine","skills","jimliu","agent-skills","claude-skills","codex-skills","openclaw-skills"],"capabilities":["skill","source-jimliu","skill-baoyu-imagine","topic-agent-skills","topic-claude-skills","topic-codex-skills","topic-openclaw-skills"],"categories":["baoyu-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/JimLiu/baoyu-skills/baoyu-imagine","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add JimLiu/baoyu-skills","source_repo":"https://github.com/JimLiu/baoyu-skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 16958 github stars · SKILL.md body (13,634 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-03T00:52:27.409Z","embedding":null,"createdAt":"2026-04-18T21:53:31.916Z","updatedAt":"2026-05-03T00:52:27.409Z","lastSeenAt":"2026-05-03T00:52:27.409Z","tsv":"'-01':856,1273,1541,1788 '-04':855 '-2':1563 '-3':1049 '-3.1':1063 '-4':1269,1784 '/.baoyu-skills/.env':927,928 '/4.5/4.0':676 '/baoyu-image-gen/extend.md':312 '/baoyu-imagine/extend.md':254 '/baoyu-skills/baoyu-imagine/extend.md':260 '/bun/bun':221 '/chat/completions':1281 '/scripts/main.ts':204,392,407,424,436,449,470,488 '0':223,1817 '1':96,575,576,603,703,866,938,976,1293,1447,1448,1458,1562 '1.5':972 '10':540,1683 '1024px':1367 '1024x1024':583 '1152x2048':1432 '1536x1024':1144 '16':414,573,594,1157,1449,1452 '1k':612,1161,1366,1369,1370,1390 '2':11,61,122,466,482,588,942,968,1032,1318,1399,1466,1553 '2.0':461 '2.35':1457 '2.7':1518 '2025':854 '2048px':1376,1424 '2048px-class':1423 '2048x1152':1430 '2048x2048':1429 '2k':417,606,610,613,1162,1373,1375,1378,1379,1391,1417 '3':149,578,602,947,1328,1454,1455,1710,1741 '3.0':685,687 '3840px':597 '3840x2160':1443 '4':492,577,952,1337,1453,1456 '4k':614,1163,1392,1440 '5.0':675 '9':415,574,1158,1450,1451 'access':771,776 'across':1768 'agent':109 'ai':4,49 'alia':751,831,1017 'allow':568 'alon':335 'alreadi':1629 'analysi':1607 'api':26,53,355,717,720,724,728,731,734,737,740,743,746,749,753,756,759,762,765,768,783,789,847,851,869,1113,1129,1135,1174,1331,1728 'api-bas':52 'appli':268,934,1197,1583,1688 'applic':161 'ar':413,570,1520,1535 'arg':923 'ark':782,788 'articl':1616 'ask':117,137,172,275,1248 'askuserquest':112,182,287 'aspect':34,348,399,571,643,1154,1415,1444,1510,1527,1746 'aspect-ratio':642,1153 'assembl':1622 'attempt':1711,1742 'attribut':884 'auth':1098 'auto':532,556,1299,1737 'auto-detect':555 'auto-retri':1736 'auto-select':1298 'automat':1549,1675 'avoid':1699 'azur':12,62,544,659,722,726,828,832,836,846,849,990,995,998,1006,1020,1303,1344 'backward':1015 'backward-compat':1014 'banana':1287 'baoyu':2,252,310,326,885,894,903,908,1615 'baoyu-article-illustr':1614 'baoyu-imagin':1,325 'baoyu-skil':251,309 'base':54,839 'basedir':196,203,391,406,423,435,448,469,487 'bash':387 'basic':388 'batch':37,150,359,365,385,483,518,529,891,1546,1578,1618,1650,1691,1771 'batch.json':490 'batchfil':489,516,1551,1579 'behavior':1253,1503,1670 'bigmodel':752,810 'block':226,237 'blue':439 'brew':216 'built':99,537,954,961,1680 'built-in':98,536,953,960,1679 'bun':206,209,213,389,404,421,433,446,467,485 'burst':1701 'bytedance/seedream-':1512 'call':158,166 'cap':361,893,1676 'case':1364 'cat':395,452,473 'cat.png':397 'character/portrait':1316 'check':241 'chosen':144 'clarifi':116 'class':1219,1425 'cli':922,939,1766 'clone':1177 'closest':1469,1486 'cn':864 'cn-north':863 'cogview':1268,1783 'collect':289 'combin':159 'compat':307,631,1016,1091,1105,1183 'complet':230,305 'concaten':505 'concret':181,1523 'concurr':897,901,907 'config':257,535,1678 'configur':1812 'consist':1317 'contain':1552,1630 'content':1763 'content.md':427 'continu':298 'coordin':1568 'count':527,1673,1716,1718 'coupl':1659 'cover':1380 'creativ':1667 'credenti':781 'current':108,1192 'custom':1037,1261,1438,1471,1811 'dall':1481 'dashscop':16,66,456,546,677,690,742,745,804,1256,1346,1774 'debug':1571 'default':45,270,343,345,347,350,357,531,539,554,566,609,619,837,853,862,944,956,963,1083,1127,1252,1340,1374,1544,1671,1682,1693,1751 'default_model.azure':992 'default_model.google':1047 'deploy':830,838,996,1000,1021,1038 'descript':495,715 'detect':557 'dialect':356,633,870,1093,1130,1136 'differ':1123 'directori':195,200 'display':1070 'diverg':1666 'document':1514 'doesn':318 'e':1482 'e.g':111,582,902,1442,1612 'easier':1570 'edg':596 'edit':658,661,1207,1220 'els':210,214 'emit':129 'enabl':1548 'endpoint':632,844 'entrypoint':1101 'env':925,948,1004,1042,1056,1086 'environ':712 'equival':121,190 'error':1725,1730,1757 'everi':936 'everyth':1631 'exact':1036 'exampl':186,372,1767 'exist':128,240,313,330 'expect':641,1121 'explicit':580,1434 'explor':1598,1668 'exploratori':1603 'expos':105 'extend':1765 'extend.md':239,296,341,924,943,1040,1045,1068,1082,1132,1801,1814 'extens':1809 'failur':1717,1723,1735 'fallback':123 'famili':669,695,1233,1260,1775,1798 'field':1149 'file':42,420,504,519,1577,1628,1638,1762 'final':1581,1712 'first':246,282,1218,1805 'first-class':1217 'first-tim':281,1804 'fix':1488,1759 'flag':940 'flash':1065 'flash-image-preview':1064 'flow':1282,1794,1808 'follow':88 'forc':552 'format':1125 'found':265,279 'front':1186 'full':377 'gap':919 'gateway':639,1092,1120,1184 'gemini':1048,1062,1188 'gen':887,896,905,910 'generat':6,38,48,56,234,235,301,524,1075,1542,1645,1657,1734 'given':1497,1533 'glm':19,70,1266,1781 'glm-imag':18,69,1265,1780 'googl':14,64,542,653,736,739,801,1059,1301,1342,1355,1459 'google/nano-banana':1508 'google/openai/azure/openrouter/replicate/seedream/minimax':1327 'google/openrouter':618,1383 'gpt':9,59,464,480,586,656,966,970,974,978,1030,1397,1464,1478 'gpt-imag':479,585,965,969,973,1029,1396,1463 'guarante':1109 'guardrail':1799 'guid':1225 'handl':1726 'height':1538 'high':402,1421 'highest':932 'hint':1760 'hit':247 'home':258,264 'home/.baoyu-skills/baoyu-imagine/extend.md':262 'home/.config':259 'http':878 'id':561,773 'illustr':1381,1617 'imag':5,10,20,31,33,47,55,60,71,233,302,351,354,396,411,428,432,440,453,460,465,474,481,506,508,514,523,587,615,650,657,699,791,799,802,805,808,811,814,817,820,823,826,834,850,868,886,895,904,909,950,967,971,975,979,987,1008,1031,1052,1060,1066,1087,1112,1128,1134,1203,1206,1259,1267,1272,1398,1465,1479,1540,1560,1565,1573,1589,1663,1706,1722,1744,1753,1782,1787 'imageapidialect':622,1138 'imageconfig.aspectratio':1461 'imagegenerationoptions.aspect':1491 'images':611,1356,1384,1389 'imagin':3,327 'includ':379,1714 'independ':1606 'infer':1501 'info':1072 'infograph':1382 'input':80,103,115,1608 'instal':217 'instruct':1733 'interv':912 'invalid':1745 'invoc':383 'jimeng':22,73,549,683,770,774,778,822,858,860,1350 'job':491,525,1704 'json':517,709,710 'kept':1011 'key':342,718,721,725,729,732,735,738,741,744,747,750,754,757,760,763,772,777,784,790,1332,1339,1729 'landscap':410 'latenc':1409 'leav':333 'legaci':306 'limit':366,1193,1238,1777 'load':224,266,920 'local':189 'locat':294 'low':1408 'low-lat':1407 'lower':1567 'lowest':933 'm':559 'main':201 'make':438 'map':1401,1418,1519 'max':533,595,888 'mean':1096 'medium':1404 'messag':135 'metadata':628,637,876,1152,1181,1196 'metadata.orientation':1165 'metadata.resolution':647,1160 'minimax':21,72,548,670,758,761,813,1271,1307,1308,1348,1525,1786 'minimum':370 'miss':1727 'mode':386,484,515,530,1543,1692,1772 'model':271,276,291,358,457,478,558,560,666,691,792,796,800,803,806,809,812,815,818,821,824,827,835,929,941,945,951,984,988,991,1009,1027,1061,1071,1078,1080,1081,1084,1088,1191,1232,1280,1483,1506 'model-specif':1505 'ms':913 'multi':522 'multi-imag':521 'multimod':654,665,1279,1460,1793 'multipl':155,592,1338,1572 'must':229,590,1325 'n':696,702 'name':997,1023,1039 'nano':1286 'nano-banana':1285 'nativ':625,873,1116,1141,1146,1169,1173,1212,1395 'near':1412 'need':1209,1591,1605,1632 'new':316,339 'non':1251 'non-default':1250 'normal':605,1365,1400 'north':865 'npx':211 'null':274 'number':131,697 'number/answer':145 'offici':51,1526 'older':1477 'one':174,1330,1559 'openai':8,13,58,63,353,463,477,543,624,630,655,660,716,719,723,727,798,829,833,867,872,958,986,999,1007,1090,1095,1104,1115,1133,1140,1147,1168,1172,1211,1302,1343,1357,1394,1462 'openai-compat':629,1089,1103 'openai-n':623,871,1139,1167,1210 'openrout':15,65,545,664,730,733,816,877,880,883,1278,1304,1345,1359,1490,1792 'option':493,494,882 'order':95,180,245 'otherwis':1033 'out.png':412,429,441,454,475 'outlin':1626 'outline.md':1610 'output':507,706,711,1441,1713 'outsid':692 'oven':219 'oven-sh':218 'overhead':1569 'overrid':797,845,890,1041,1702 'overridden':1387 'p':497 'parallel':1547,1669 'pars':267 'path':243,249,317,340,509,1819 'payload':1624 'pend':1554 'per':157,381,794,842,899,915,1662,1721,1743 'per-imag':1661,1720 'per-provid':380,793,841,898,914 'pick':1244 'pixel':1142 'plain':133 'plain-text':132 'plus':646,1159 'png/jpg':662 'predict':1586 'prefer':97,208,225,1003,1557,1649 'present':1333 'preset':608,1353,1354 'preview':857,1053,1067,1372 'prioriti':94,179,921,931,1341 'pro':462,1051 'pro-image-preview':1050 'proceed':1749 'project':255 'prompt':41,85,393,408,418,437,450,471,496,498,502,1576,1582,1595,1611,1627,1637 'promptfil':425,500 'provid':272,290,344,363,382,445,455,476,541,553,563,795,843,900,916,937,946,1077,1085,1094,1215,1223,1227,1246,1254,1291,1295,1297,1319,1336,1685,1769 'provider-specif':362,1222,1684 'provider/model':1756 'qualiti':292,346,403,416,604,607,621,1148,1352,1403,1420 'question':148,156,162,171 'quick':1371 'quirk':1231 'qwen':459,1258 'qwen-imag':458,1257 'ratio':35,349,400,572,598,627,636,644,875,1151,1155,1180,1195,1416,1445,1476,1492,1499,1511,1516,1528,1747 'ratio-metadata':626,635,874,1150,1179,1194 'read':501,1239 'reason':1594,1724 'ref':442,648,1236,1294,1324 'refer':32,183,431,564,649,673,879,1205,1255,1276,1311,1752,1761,1790 'reference-imag':1204 'references/config/first-time-setup.md':285,1803 'references/config/preferences-schema.md':368,1800 'references/providers/dashscope.md':1263,1773 'references/providers/minimax.md':1277,1785 'references/providers/openrouter.md':1283,1791 'references/providers/replicate.md':1290,1795 'references/providers/zai.md':1270,1778 'references/usage-examples.md':374,1764 'region':859,861 'remain':981 'renam':322 'repli':141 'replic':25,78,551,667,700,764,767,819,906,1284,1305,1349,1361,1502,1515,1796 'request':113,1414,1475 'requir':510,701 'resolut':930,1362 'resolv':205 'retri':1707,1738 'reus':1580 'rout':1100 'rpm':1700 'rule':93,1235,1633 'run':280 'runtim':110,193,321,332 'save':40,293,295,707,1575,1640 'schema':367,1802,1821 'scope':250 'script':194,202 'scripts/build-batch.ts':1620 'sdk':50 'secret':775 'see':373,562,1815 'seededit':686 'seedream':23,75,550,674,684,785,825,1288,1306,1351 'select':92,982,1292,1300 'semant':708,1117 'send':1536 'sequenti':43,1545,1566 'set':378,1046,1058,1126 'setup':284,1732,1807 'sh':220 'share':1584 'similar':1190 'simpl':1564 'singl':165,170,513,705 'single-imag':512 'single-output':704 'single-quest':169 'situat':1556 'size':352,579,581,616,645,1143,1156,1234,1262,1358,1360,1411,1426,1435,1472,1489,1495,1524,1531,1776 'skill':84,253,311 'skill-baoyu-imagine' 'skill.md':198 'snapshot':980 'source-jimliu' 'source.png':443 'special':1314 'specif':364,444,1224,1507,1686 'specifi':1320 'start':911,918 'start-gap':917 'step':222,228,1816 'still':1208,1590,1602 'strict':1176 'style':1597 'subag':1599,1652,1654 'subject':672,1275,1310,1789 'subject-refer':671,1274 'substitut':187 'success':1715 'suggest':215 'support':27,57,154,651,668,681,1221,1237,1446,1487,1797,1810 'switch':1079 'system.md':426 'target':1368,1377 'task':1555,1643 'text':29,134,499,1201 'text-to-imag':28,1200 'think':1664 'throttl':1687 'throttling/retries':1585 'throughput':1587,1697 'thumb':1635 'time':177,283,1806 'titl':881 'token':766,769 'tool':81,91,104,127,153 'tool-select':90 'topic-agent-skills' 'topic-claude-skills' 'topic-codex-skills' 'topic-openclaw-skills' 'toward':1315 'tri':1178 'tune':1695 'under':1026 'unsupport':1755 'upstream':1111 'url':840 'us':46 'usag':369 'use':286,337,634,1028,1034,1076,1114,1166,1321,1334,1363,1433,1467,1484,1509,1513,1619,1653 'user':79,87,102,114,118,139,263,1243 'user-input':101 'valid':1410,1437,1470 'valu':569,1529 'var':926,949,1005,1043,1057 'variabl':713,714 'version':848,852 'via':1813 'volcengin':780,787 'wan':1289,1517 'wan2.7-image':679,694 'wan2.7-image-pro':678 'warn':1748 'wider':600 'width':1537 'width/height':589 'win':248,1069 'wire':1124 'without':1534 'work':371,1600 'worker':360,526,889,892,1672 'write':1596 'x':207,390,405,422,434,447,468,486 'xdg':256,261 'y':212 'z.ai':17,68,755,1264,1347,1779 'zai':547,748,807 '即梦':74,779 '豆包':76,786 '阿里通义万象':67","prices":[{"id":"ae644095-6e89-4518-8b30-fe9e30b1d5fd","listingId":"ea4edbca-3c1b-4ff3-9d86-6f5bf2d03643","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"JimLiu","category":"baoyu-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T21:53:31.916Z"}],"sources":[{"listingId":"ea4edbca-3c1b-4ff3-9d86-6f5bf2d03643","source":"github","sourceId":"JimLiu/baoyu-skills/baoyu-imagine","sourceUrl":"https://github.com/JimLiu/baoyu-skills/tree/main/skills/baoyu-imagine","isPrimary":false,"firstSeenAt":"2026-04-18T21:53:31.916Z","lastSeenAt":"2026-05-03T00:52:27.409Z"}],"details":{"listingId":"ea4edbca-3c1b-4ff3-9d86-6f5bf2d03643","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"JimLiu","slug":"baoyu-imagine","github":{"repo":"JimLiu/baoyu-skills","stars":16958,"topics":["agent-skills","claude-skills","codex-skills","openclaw-skills"],"license":null,"html_url":"https://github.com/JimLiu/baoyu-skills","pushed_at":"2026-04-25T20:03:31Z","description":null,"skill_md_sha":"9b5ef2fbcfb0ae40e01b9964fdad4daa35502a54","skill_md_path":"skills/baoyu-imagine/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/JimLiu/baoyu-skills/tree/main/skills/baoyu-imagine"},"layout":"multi","source":"github","category":"baoyu-skills","frontmatter":{"name":"baoyu-imagine","description":"AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images."},"skills_sh_url":"https://skills.sh/JimLiu/baoyu-skills/baoyu-imagine"},"updatedAt":"2026-05-03T00:52:27.409Z"}}