{"id":"95bd323f-fec8-4821-b143-af76a38ff3d3","shortId":"X2hwkf","kind":"skill","title":"baoyu-image-gen","tagline":"[Deprecated: use baoyu-imagine] AI image generation with OpenAI, 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. Seque","description":"# Image Generation (AI SDK)\n\nOfficial API-based image generation. Supports OpenAI, 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 `${BUN_X}`: prefer `bun`; else `npx -y bun`; else suggest `brew install oven-sh/bun/bun`.\n\n## Step 0: Load Preferences ⛔ BLOCKING\n\nThis step MUST complete before any image generation — generation is blocked until EXTEND.md exists.\n\nCheck these paths in order; first hit wins:\n\n| Path | Scope |\n|------|-------|\n| `.baoyu-skills/baoyu-image-gen/EXTEND.md` | Project |\n| `${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-image-gen/EXTEND.md` | XDG |\n| `$HOME/.baoyu-skills/baoyu-image-gen/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\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${BUN_X} {baseDir}/scripts/main.ts --prompt \"A cat\" --image out.png --provider dashscope --model qwen-image-2.0-pro\n\n# Batch mode\n${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`) |\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. Not supported by Jimeng, Seedream 3.0, SeedEdit 3.0 |\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 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.\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 | 1K | 1K | Quick previews |\n| `2k` (default) | 2K | 2048px | 2K | 2K | Covers, illustrations, infographics |\n\nGoogle/OpenRouter `imageSize` can be overridden with `--imageSize 1K|2K|4K`.\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: closest supported 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","image","gen","skills","jimliu","agent-skills","claude-skills","codex-skills","openclaw-skills"],"capabilities":["skill","source-jimliu","skill-baoyu-image-gen","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-image-gen","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 (12,349 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":"2026-05-03T00:52:27.345Z","embedding":null,"createdAt":"2026-04-18T21:53:31.170Z","updatedAt":"2026-05-03T00:52:27.345Z","lastSeenAt":"2026-05-03T00:52:27.345Z","tsv":"'-01':767,1130,1321,1568 '-04':766 '-2':1343 '-3':906 '-3.1':920 '-4':1126,1564 '/.baoyu-skills/.env':838,839 '/4.5/4.0':598 '/baoyu-image-gen/extend.md':251 '/baoyu-skills/baoyu-image-gen/extend.md':257 '/bun/bun':218 '/chat/completions':1138 '/scripts/main.ts':201,354,369,386,398,411,430 '0':220,1597 '1':93,517,518,614,777,849,1150,1251,1252,1262,1342 '10':482,1463 '1024px':1224 '1024x1024':525 '1536x1024':1001 '16':376,515,1014,1253,1256 '1k':534,1018,1223,1225,1226,1245 '2':119,853,1175,1333 '2.0':423 '2.35':1261 '2.7':1298 '2025':765 '2048px':1232 '2k':379,528,532,535,1019,1229,1231,1233,1234,1246 '3':146,520,858,1185,1258,1259,1490,1521 '3.0':604,606 '4':434,519,863,1194,1257,1260 '4k':536,1020,1247 '5.0':597 '9':377,516,1015,1254,1255 'access':682,687 'across':1548 'agent':106 'ai':10,49 'alia':662,742,896 'allow':510 'alreadi':1409 'analysi':1387 'api':29,53,317,628,631,635,639,642,645,648,651,654,657,660,664,667,670,673,676,679,694,700,758,762,780,970,986,992,1031,1188,1508 'api-bas':52 'appli':265,845,1054,1363,1468 'applic':158 'ar':375,512,1300,1315 'arg':834 'ark':693,699 'articl':1396 'ask':114,134,169,272,1105 'askuserquest':109,179,284 'aspect':37,310,361,513,565,1011,1248,1290,1307,1526 'aspect-ratio':564,1010 'assembl':1402 'attempt':1491,1522 'attribut':795 'auth':955 'auto':474,498,1156,1517 'auto-detect':497 'auto-retri':1516 'auto-select':1155 'automat':1329,1455 'avoid':1479 'azur':15,59,486,581,633,637,739,743,747,757,760,869,874,877,885,1160,1201 'backward':894 'backward-compat':893 'banana':1144 'baoyu':2,8,249,796,805,814,819,1395 'baoyu-article-illustr':1394 'baoyu-image-gen':1 'baoyu-imagin':7 'baoyu-skil':248 'base':54,750 'basedir':193,200,353,368,385,397,410,429 'bash':349 'basic':350 'batch':40,147,321,327,347,425,460,471,802,1326,1358,1398,1430,1471,1551 'batch.json':432 'batchfil':431,458,1331,1359 'behavior':1110,1283,1450 'bigmodel':663,721 'block':223,234 'blue':401 'brew':213 'built':96,479,865,1460 'built-in':95,478,864,1459 'bun':203,206,210,351,366,383,395,408,427 'burst':1481 'bytedance/seedream-':1292 'call':155,163 'cap':323,804,1456 'case':1221 'cat':357,414 'cat.png':359 'character/portrait':1173 'check':238 'chosen':141 'clarifi':113 'class':1076 'cli':833,850,1546 'clone':1034 'closest':1267 'cn':775 'cn-north':774 'cogview':1125,1563 'collect':286 'combin':156 'compat':553,895,948,962,1040 'complet':227,302 'concaten':447 'concret':178,1303 'concurr':808,812,818 'config':254,477,1458 'configur':1592 'consist':1174 'contain':1332,1410 'content':1543 'content.md':389 'continu':295 'coordin':1348 'count':469,1453,1496,1498 'coupl':1439 'cover':1235 'creativ':1447 'credenti':692 'current':105,1049 'custom':1118,1591 'dashscop':19,63,418,488,653,656,715,1113,1203,1554 'debug':1351 'default':267,305,307,309,312,319,473,481,496,508,531,541,748,764,773,855,867,940,984,1109,1197,1230,1324,1451,1462,1473,1531 'default_model.azure':871 'default_model.google':904 'deploy':741,749,875,879 'deprec':5 'descript':437,626 'detect':499 'dialect':318,555,781,950,987,993 'differ':980 'directori':192,197 'display':927 'diverg':1446 'document':1294 'e.g':108,524,813,1392 'easier':1350 'edit':580,583,1064,1077 'els':207,211 'emit':126 'enabl':1328 'endpoint':554,755 'entrypoint':958 'env':836,859,883,899,913,943 'environ':623 'equival':118,187 'error':1505,1510,1537 'everi':847 'everyth':1411 'exampl':183,334,1547 'exist':125,237 'expect':563,978 'explicit':522 'explor':1378,1448 'exploratori':1383 'expos':102 'extend':1545 'extend.md':236,293,303,835,854,897,902,925,939,989,1581,1594 'extens':1589 'failur':1497,1503,1515 'fallback':120 'famili':591,1090,1117,1555,1578 'field':1006 'file':45,382,446,461,1357,1408,1418,1542 'final':1361,1492 'first':243,279,1075,1585 'first-class':1074 'first-tim':278,1584 'fix':1539 'flag':851 'flash':922 'flash-image-preview':921 'flow':1139,1574,1588 'follow':85 'forc':494 'format':982 'found':262,276 'front':1043 'full':339 'gap':830 'gateway':561,949,977,1041 'gemini':905,919,1045 'gen':4,798,807,816,821 'generat':12,41,48,56,231,232,298,466,932,1322,1425,1437,1514 'given':1277,1313 'glm':22,67,1123,1561 'glm-imag':21,66,1122,1560 'googl':17,61,484,575,647,650,712,916,1158,1199,1212,1263 'google/nano-banana':1288 'google/openai/azure/openrouter/replicate/seedream/minimax':1184 'google/openrouter':540,1238 'gpt':578 'guarante':966 'guardrail':1579 'guid':1082 'handl':1506 'height':1318 'high':364 'highest':843 'hint':1540 'hit':244 'home':255,261 'home/.baoyu-skills/baoyu-image-gen/extend.md':259 'home/.config':256 'http':789 'id':503,684 'illustr':1236,1397 'imag':3,11,23,34,36,47,55,68,230,299,313,316,358,373,390,394,402,415,422,448,450,456,465,537,572,579,610,702,710,713,716,719,722,725,728,731,734,737,745,761,779,797,806,815,820,861,887,909,917,923,944,969,985,991,1060,1063,1116,1124,1129,1320,1340,1345,1353,1369,1443,1486,1502,1524,1533,1562,1567 'imageapidialect':544,995 'imageconfig.aspectratio':1265 'imagegenerationoptions.aspect':1271 'images':533,1213,1239,1244 'imagin':9 'includ':341,1494 'independ':1386 'infer':1281 'info':929 'infograph':1237 'input':77,100,112,1388 'instal':214 'instruct':1513 'interv':823 'invalid':1525 'invoc':345 'jimeng':25,70,491,602,681,685,689,733,769,771,1207 'job':433,467,1484 'json':459,620,621 'kept':890 'key':304,629,632,636,640,643,646,649,652,655,658,661,665,668,671,674,683,688,695,701,1189,1196,1509 'landscap':372 'limit':328,1050,1095,1557 'load':221,263,831 'local':186 'locat':291 'lower':1347 'lowest':844 'm':501 'main':198 'make':400 'map':1299 'max':475,799 'mean':953 'messag':132 'metadata':550,559,787,1009,1038,1053 'metadata.orientation':1022 'metadata.resolution':569,1017 'minimax':24,69,490,592,669,672,724,1128,1164,1165,1205,1305,1566 'minimum':332 'miss':1507 'mode':348,426,457,472,1323,1472,1552 'model':268,273,288,320,419,500,502,588,703,707,711,714,717,720,723,726,729,732,735,738,746,840,852,856,862,870,888,918,928,935,937,938,941,945,1048,1089,1137,1286 'model-specif':1285 'ms':824 'multi':464 'multi-imag':463 'multimod':576,587,1136,1264,1573 'multipl':152,1195,1352 'must':226,1182 'n':607,613 'name':876 'nano':1143 'nano-banana':1142 'nativ':547,784,973,998,1003,1026,1030,1069 'need':1066,1371,1385,1412 'non':1108 'non-default':1107 'normal':527,1222 'north':776 'npx':208 'null':271 'number':128,608 'number/answer':142 'offici':51,1306 'one':171,1187,1339 'openai':14,16,58,60,315,485,546,552,577,582,627,630,634,638,709,740,744,778,783,878,886,947,952,961,972,990,997,1004,1025,1029,1068,1159,1200,1214,1266 'openai-compat':551,946,960 'openai-n':545,782,996,1024,1067 'openrout':18,62,487,586,641,644,727,788,791,794,1135,1161,1202,1216,1270,1572 'option':435,436,793 'order':92,177,242 'out.png':374,391,403,416 'outlin':1406 'outline.md':1390 'output':449,617,622,1493 'oven':216 'oven-sh':215 'overhead':1349 'overrid':708,756,801,898,1482 'overridden':1242 'p':439 'parallel':1327,1449 'pars':264 'path':240,246,451,1599 'payload':1404 'pend':1334 'per':154,343,705,753,810,826,1442,1501,1523 'per-imag':1441,1500 'per-provid':342,704,752,809,825 'pick':1101 'pixel':999 'plain':130 'plain-text':129 'plus':568,1016 'png/jpg':584 'predict':1366 'prefer':94,205,222,882,1337,1429 'present':1190 'preset':530,1210,1211 'preview':768,910,924,1228 'prioriti':91,176,832,842,1198 'pro':424,908 'pro-image-preview':907 'proceed':1529 'project':252 'prompt':44,82,355,370,380,399,412,438,440,444,1356,1362,1375,1391,1407,1417 'promptfil':387,442 'provid':269,287,306,325,344,407,417,483,495,505,706,754,811,827,848,857,934,942,951,1072,1080,1084,1103,1111,1148,1152,1154,1176,1193,1465,1549 'provider-specif':324,1079,1464 'provider/model':1536 'qualiti':289,308,365,378,526,529,543,1005,1209 'question':145,153,159,168 'quick':1227 'quirk':1088 'qwen':421,1115 'qwen-imag':420,1114 'ratio':38,311,362,514,549,558,566,786,1008,1012,1037,1052,1249,1272,1279,1291,1296,1308,1527 'ratio-metadata':548,557,785,1007,1036,1051 'read':443,1096 'reason':1374,1504 'ref':404,570,1093,1151,1181 'refer':35,180,393,506,571,595,790,1062,1112,1133,1168,1532,1541,1570 'reference-imag':1061 'references/config/first-time-setup.md':282,1583 'references/config/preferences-schema.md':330,1580 'references/providers/dashscope.md':1120,1553 'references/providers/minimax.md':1134,1565 'references/providers/openrouter.md':1140,1571 'references/providers/replicate.md':1147,1575 'references/providers/zai.md':1127,1558 'references/usage-examples.md':336,1544 'region':770,772 'repli':138 'replic':28,75,493,589,611,675,678,730,817,1141,1162,1206,1218,1282,1295,1576 'request':110 'requir':452,612 'resolut':841,1219 'resolv':202 'retri':1487,1518 'reus':1360 'rout':957 'rpm':1480 'rule':90,1092,1413 'run':277 'runtim':107,190 'save':43,290,292,618,1355,1420 'schema':329,1582,1601 'scope':247 'script':191,199 'scripts/build-batch.ts':1400 'sdk':50 'secret':686 'see':335,504,1595 'seededit':605 'seedream':26,72,492,596,603,696,736,1145,1163,1208 'select':89,1149,1157 'semant':619,974 'send':1316 'sequ':46 'sequenti':1325,1346 'set':340,903,915,983 'setup':281,1512,1587 'sh':217 'share':1364 'similar':1047 'simpl':1344 'singl':162,167,455,616 'single-imag':454 'single-output':615 'single-quest':166 'situat':1336 'size':314,521,523,538,567,1000,1013,1091,1119,1215,1217,1269,1275,1304,1311,1556 'skill':81,250 'skill-baoyu-image-gen' 'skill.md':195 'source-jimliu' 'source.png':405 'special':1171 'specif':326,406,1081,1287,1466 'specifi':1177 'start':822,829 'start-gap':828 'step':219,225,1596 'still':1065,1370,1382 'strict':1033 'style':1377 'subag':1379,1432,1434 'subject':594,1132,1167,1569 'subject-refer':593,1131 'substitut':184 'success':1495 'suggest':212 'support':30,57,151,573,590,600,1078,1094,1250,1268,1577,1590 'switch':936 'system.md':388 'task':1335,1423 'text':32,131,441,1058 'text-to-imag':31,1057 'think':1444 'throttl':1467 'throttling/retries':1365 'throughput':1367,1477 'thumb':1415 'time':174,280,1586 'titl':792 'token':677,680 'tool':78,88,101,124,150 'tool-select':87 'topic-agent-skills' 'topic-claude-skills' 'topic-codex-skills' 'topic-openclaw-skills' 'toward':1172 'tri':1035 'tune':1475 'unsupport':1535 'upstream':968 'url':751 'usag':331 'use':6,283,556,933,971,1023,1178,1191,1220,1289,1293,1399,1433 'user':76,84,99,111,115,136,260,1100 'user-input':98 'valu':511,1309 'var':837,860,884,900,914 'variabl':624,625 'version':759,763 'via':1593 'volcengin':691,698 'wan':1146,1297 'warn':1528 'width':1317 'win':245,926 'wire':981 'without':1314 'work':333,1380 'worker':322,468,800,803,1452 'write':1376 'x':204,352,367,384,396,409,428 'xdg':253,258 'y':209 'z.ai':20,65,666,1121,1204,1559 'zai':489,659,718 '即梦':71,690 '豆包':73,697 '阿里通义万象':64","prices":[{"id":"d52356b9-234f-4e47-9c3d-a91d3d573642","listingId":"95bd323f-fec8-4821-b143-af76a38ff3d3","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":"2026-04-18T21:53:31.170Z"}],"sources":[{"listingId":"95bd323f-fec8-4821-b143-af76a38ff3d3","source":"github","sourceId":"JimLiu/baoyu-skills/baoyu-image-gen","sourceUrl":"https://github.com/JimLiu/baoyu-skills/tree/main/skills/baoyu-image-gen","isPrimary":false,"firstSeenAt":"2026-04-18T21:53:31.170Z","lastSeenAt":"2026-05-03T00:52:27.345Z"}],"details":{"listingId":"95bd323f-fec8-4821-b143-af76a38ff3d3","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"JimLiu","slug":"baoyu-image-gen","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":"14026237864a714159b22b8c48d587fc1f6bb345","skill_md_path":"skills/baoyu-image-gen/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/JimLiu/baoyu-skills/tree/main/skills/baoyu-image-gen"},"layout":"multi","source":"github","category":"baoyu-skills","frontmatter":{"name":"baoyu-image-gen","description":"[Deprecated: use baoyu-imagine] AI image generation with OpenAI, 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-image-gen"},"updatedAt":"2026-05-03T00:52:27.345Z"}}