[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openclaw-openclaw-skills-openai-image-gen":3},{"error":4,"detail":5,"metadata":36,"markdownContent":38,"rawMarkdown":33},false,{"repo_full_name":6,"owner":7,"repo_name":7,"repo_forks":8,"skill_path":9,"repo_stars":10,"name":11,"category_id":12,"description":13,"file_tree":14,"skill_md_content":33,"skill_id":34,"skill_key":35},"openclaw/openclaw","openclaw",62448,"skills/openai-image-gen",323859,"openai-image-gen",1,"Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.",[15,20],{"name":16,"path":17,"size":18,"type":19},"SKILL.md","skills/openai-image-gen/SKILL.md",3352,"file",{"name":21,"path":22,"type":23,"children":24},"scripts","skills/openai-image-gen/scripts","folder",[25,29],{"name":26,"path":27,"size":28,"type":19},"gen.py","skills/openai-image-gen/scripts/gen.py",10980,{"name":30,"path":31,"size":32,"type":19},"test_gen.py","skills/openai-image-gen/scripts/test_gen.py",4999,"---\nname: openai-image-gen\ndescription: Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.\nhomepage: https://platform.openai.com/docs/api-reference/images\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"🎨\",\n        \"requires\": { \"bins\": [\"python3\"], \"env\": [\"OPENAI_API_KEY\"] },\n        \"primaryEnv\": \"OPENAI_API_KEY\",\n        \"install\":\n          [\n            {\n              \"id\": \"python-brew\",\n              \"kind\": \"brew\",\n              \"formula\": \"python\",\n              \"bins\": [\"python3\"],\n              \"label\": \"Install Python (brew)\",\n            },\n          ],\n      },\n  }\n---\n\n# OpenAI Image Gen\n\nGenerate a handful of “random but structured” prompts and render them via the OpenAI Images API.\n\n## Run\n\nNote: Image generation can take longer than common exec timeouts (for example 30 seconds).\nWhen invoking this skill via OpenClaw’s exec tool, set a higher timeout to avoid premature termination/retries (e.g., exec timeout=300).\n\n```bash\npython3 {baseDir}/scripts/gen.py\nopen ~/Projects/tmp/openai-image-gen-*/index.html  # if ~/Projects/tmp exists; else ./tmp/...\n```\n\nUseful flags:\n\n```bash\n# GPT image models with various options\npython3 {baseDir}/scripts/gen.py --count 16 --model gpt-image-1\npython3 {baseDir}/scripts/gen.py --prompt \"ultra-detailed studio photo of a lobster astronaut\" --count 4\npython3 {baseDir}/scripts/gen.py --size 1536x1024 --quality high --out-dir ./out/images\npython3 {baseDir}/scripts/gen.py --model gpt-image-1.5 --background transparent --output-format webp\n\n# DALL-E 3 (note: count is automatically limited to 1)\npython3 {baseDir}/scripts/gen.py --model dall-e-3 --quality hd --size 1792x1024 --style vivid\npython3 {baseDir}/scripts/gen.py --model dall-e-3 --style natural --prompt \"serene mountain landscape\"\n\n# DALL-E 2\npython3 {baseDir}/scripts/gen.py --model dall-e-2 --size 512x512 --count 4\n```\n\n## Model-Specific Parameters\n\nDifferent models support different parameter values. The script automatically selects appropriate defaults based on the model.\n\n### Size\n\n- **GPT image models** (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`): `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto`\n  - Default: `1024x1024`\n- **dall-e-3**: `1024x1024`, `1792x1024`, or `1024x1792`\n  - Default: `1024x1024`\n- **dall-e-2**: `256x256`, `512x512`, or `1024x1024`\n  - Default: `1024x1024`\n\n### Quality\n\n- **GPT image models**: `auto`, `high`, `medium`, or `low`\n  - Default: `high`\n- **dall-e-3**: `hd` or `standard`\n  - Default: `standard`\n- **dall-e-2**: `standard` only\n  - Default: `standard`\n\n### Other Notable Differences\n\n- **dall-e-3** only supports generating 1 image at a time (`n=1`). The script automatically limits count to 1 when using this model.\n- **GPT image models** support additional parameters:\n  - `--background`: `transparent`, `opaque`, or `auto` (default)\n  - `--output-format`: `png` (default), `jpeg`, or `webp`\n  - Note: `stream` and `moderation` are available via API but not yet implemented in this script\n- **dall-e-3** has a `--style` parameter: `vivid` (hyper-real, dramatic) or `natural` (more natural looking)\n\n## Output\n\n- `*.png`, `*.jpeg`, or `*.webp` images (output format depends on model + `--output-format`)\n- `prompts.json` (prompt → file mapping)\n- `index.html` (thumbnail gallery)\n","2279e238-7e7d-5483-84a8-44907f3c6940","openclaw-openclaw-skills-openai-image-gen",{"name":11,"description":13,"homepage":37},"https://platform.openai.com/docs/api-reference/images","\u003Ch1>OpenAI Image Gen\u003C/h1>\n\u003Cp>Generate a handful of “random but structured” prompts and render them via the OpenAI Images API.\u003C/p>\n\u003Ch2>Run\u003C/h2>\n\u003Cp>Note: Image generation can take longer than common exec timeouts (for example 30 seconds).\nWhen invoking this skill via OpenClaw’s exec tool, set a higher timeout to avoid premature termination/retries (e.g., exec timeout=300).\u003C/p>\n\u003Cdiv class=\"md-code-block\">\u003Cdiv class=\"md-code-lang\">bash\u003C/div>\u003Cpre>\u003Ccode class=\"hljs language-bash\">python3 {baseDir}/scripts/gen.py\nopen ~/Projects/tmp/openai-image-gen-*/index.html  \u003Cspan class=\"hljs-comment\"># if ~/Projects/tmp exists; else ./tmp/...\u003C/span>\u003C/code>\u003C/pre>\u003C/div>\u003Cp>Useful flags:\u003C/p>\n\u003Cdiv class=\"md-code-block\">\u003Cdiv class=\"md-code-lang\">bash\u003C/div>\u003Cpre>\u003Ccode class=\"hljs language-bash\">\u003Cspan class=\"hljs-comment\"># GPT image models with various options\u003C/span>\npython3 {baseDir}/scripts/gen.py --count 16 --model gpt-image-1\npython3 {baseDir}/scripts/gen.py --prompt \u003Cspan class=\"hljs-string\">"ultra-detailed studio photo of a lobster astronaut"\u003C/span> --count 4\npython3 {baseDir}/scripts/gen.py --size 1536x1024 --quality high --out-dir ./out/images\npython3 {baseDir}/scripts/gen.py --model gpt-image-1.5 --background transparent --output-format webp\n\n\u003Cspan class=\"hljs-comment\"># DALL-E 3 (note: count is automatically limited to 1)\u003C/span>\npython3 {baseDir}/scripts/gen.py --model dall-e-3 --quality hd --size 1792x1024 --style vivid\npython3 {baseDir}/scripts/gen.py --model dall-e-3 --style natural --prompt \u003Cspan class=\"hljs-string\">"serene mountain landscape"\u003C/span>\n\n\u003Cspan class=\"hljs-comment\"># DALL-E 2\u003C/span>\npython3 {baseDir}/scripts/gen.py --model dall-e-2 --size 512x512 --count 4\u003C/code>\u003C/pre>\u003C/div>\u003Ch2>Model-Specific Parameters\u003C/h2>\n\u003Cp>Different models support different parameter values. The script automatically selects appropriate defaults based on the model.\u003C/p>\n\u003Ch3>Size\u003C/h3>\n\u003Cul>\n\u003Cli>\u003Cstrong>GPT image models\u003C/strong> (\u003Ccode>gpt-image-1\u003C/code>, \u003Ccode>gpt-image-1-mini\u003C/code>, \u003Ccode>gpt-image-1.5\u003C/code>): \u003Ccode>1024x1024\u003C/code>, \u003Ccode>1536x1024\u003C/code> (landscape), \u003Ccode>1024x1536\u003C/code> (portrait), or \u003Ccode>auto\u003C/code>\u003Cul>\n\u003Cli>Default: \u003Ccode>1024x1024\u003C/code>\u003C/li>\n\u003C/ul>\n\u003C/li>\n\u003Cli>\u003Cstrong>dall-e-3\u003C/strong>: \u003Ccode>1024x1024\u003C/code>, \u003Ccode>1792x1024\u003C/code>, or \u003Ccode>1024x1792\u003C/code>\u003Cul>\n\u003Cli>Default: \u003Ccode>1024x1024\u003C/code>\u003C/li>\n\u003C/ul>\n\u003C/li>\n\u003Cli>\u003Cstrong>dall-e-2\u003C/strong>: \u003Ccode>256x256\u003C/code>, \u003Ccode>512x512\u003C/code>, or \u003Ccode>1024x1024\u003C/code>\u003Cul>\n\u003Cli>Default: \u003Ccode>1024x1024\u003C/code>\u003C/li>\n\u003C/ul>\n\u003C/li>\n\u003C/ul>\n\u003Ch3>Quality\u003C/h3>\n\u003Cul>\n\u003Cli>\u003Cstrong>GPT image models\u003C/strong>: \u003Ccode>auto\u003C/code>, \u003Ccode>high\u003C/code>, \u003Ccode>medium\u003C/code>, or \u003Ccode>low\u003C/code>\u003Cul>\n\u003Cli>Default: \u003Ccode>high\u003C/code>\u003C/li>\n\u003C/ul>\n\u003C/li>\n\u003Cli>\u003Cstrong>dall-e-3\u003C/strong>: \u003Ccode>hd\u003C/code> or \u003Ccode>standard\u003C/code>\u003Cul>\n\u003Cli>Default: \u003Ccode>standard\u003C/code>\u003C/li>\n\u003C/ul>\n\u003C/li>\n\u003Cli>\u003Cstrong>dall-e-2\u003C/strong>: \u003Ccode>standard\u003C/code> only\u003Cul>\n\u003Cli>Default: \u003Ccode>standard\u003C/code>\u003C/li>\n\u003C/ul>\n\u003C/li>\n\u003C/ul>\n\u003Ch3>Other Notable Differences\u003C/h3>\n\u003Cul>\n\u003Cli>\u003Cstrong>dall-e-3\u003C/strong> only supports generating 1 image at a time (\u003Ccode>n=1\u003C/code>). The script automatically limits count to 1 when using this model.\u003C/li>\n\u003Cli>\u003Cstrong>GPT image models\u003C/strong> support additional parameters:\u003Cul>\n\u003Cli>\u003Ccode>--background\u003C/code>: \u003Ccode>transparent\u003C/code>, \u003Ccode>opaque\u003C/code>, or \u003Ccode>auto\u003C/code> (default)\u003C/li>\n\u003Cli>\u003Ccode>--output-format\u003C/code>: \u003Ccode>png\u003C/code> (default), \u003Ccode>jpeg\u003C/code>, or \u003Ccode>webp\u003C/code>\u003C/li>\n\u003Cli>Note: \u003Ccode>stream\u003C/code> and \u003Ccode>moderation\u003C/code> are available via API but not yet implemented in this script\u003C/li>\n\u003C/ul>\n\u003C/li>\n\u003Cli>\u003Cstrong>dall-e-3\u003C/strong> has a \u003Ccode>--style\u003C/code> parameter: \u003Ccode>vivid\u003C/code> (hyper-real, dramatic) or \u003Ccode>natural\u003C/code> (more natural looking)\u003C/li>\n\u003C/ul>\n\u003Ch2>Output\u003C/h2>\n\u003Cul>\n\u003Cli>\u003Ccode>*.png\u003C/code>, \u003Ccode>*.jpeg\u003C/code>, or \u003Ccode>*.webp\u003C/code> images (output format depends on model + \u003Ccode>--output-format\u003C/code>)\u003C/li>\n\u003Cli>\u003Ccode>prompts.json\u003C/code> (prompt → file mapping)\u003C/li>\n\u003Cli>\u003Ccode>index.html\u003C/code> (thumbnail gallery)\u003C/li>\n\u003C/ul>\n"]