OpenAI Image Gen
Generate a handful of “random but structured” prompts and render them via the OpenAI Images API.
Run
Note: Image generation can take longer than common host tool timeouts
(for example 30 seconds). When invoking this skill via OpenClaw's
exec_command, set a higher timeout_sec to avoid premature
termination or retries (for example timeout_sec=300).
python3 {baseDir}/scripts/gen.py
open ~/Projects/tmp/openai-image-gen-*/index.html # if ~/Projects/tmp exists; else ./tmp/...
Useful flags:
# GPT image models with various options
python3 {baseDir}/scripts/gen.py --count 16 --model gpt-image-1
python3 {baseDir}/scripts/gen.py --prompt "ultra-detailed studio photo of a lobster astronaut" --count 4
python3 {baseDir}/scripts/gen.py --size 1536x1024 --quality high --out-dir ./out/images
python3 {baseDir}/scripts/gen.py --model gpt-image-1.5 --background transparent --output-format webp
# DALL-E 3 (note: count is automatically limited to 1)
python3 {baseDir}/scripts/gen.py --model dall-e-3 --quality hd --size 1792x1024 --style vivid
python3 {baseDir}/scripts/gen.py --model dall-e-3 --style natural --prompt "serene mountain landscape"
# DALL-E 2
python3 {baseDir}/scripts/gen.py --model dall-e-2 --size 512x512 --count 4
Model-Specific Parameters
Different models support different parameter values. The script automatically selects appropriate defaults based on the model.
Size
- GPT image models (
gpt-image-1, gpt-image-1-mini, gpt-image-1.5): 1024x1024, 1536x1024 (landscape), 1024x1536 (portrait), or auto
- dall-e-3:
1024x1024, 1792x1024, or 1024x1792
- dall-e-2:
256x256, 512x512, or 1024x1024
Quality
- GPT image models:
auto, high, medium, or low
- dall-e-3:
hd or standard
- dall-e-2:
standard only
Other Notable Differences
- dall-e-3 only supports generating 1 image at a time (
n=1). The script automatically limits count to 1 when using this model.
- GPT image models support additional parameters:
--background: transparent, opaque, or auto (default)--output-format: png (default), jpeg, or webp- Note:
stream and moderation are available via API but not yet implemented in this script
- dall-e-3 has a
--style parameter: vivid (hyper-real, dramatic) or natural (more natural looking)
Output
*.png, *.jpeg, or *.webp images (output format depends on model + --output-format)prompts.json (prompt → file mapping)index.html (thumbnail gallery)
1---2name: openai-image-gen3description: Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.4homepage: https://platform.openai.com/docs/api-reference/images5metadata:6 {7 "openclaw":8 {9 "emoji": "🖼️",10 "requires": { "bins": ["python3"], "env": ["OPENAI_API_KEY"] },11 "primaryEnv": "OPENAI_API_KEY",12 "install":13 [14 {15 "id": "python-brew",16 "kind": "brew",17 "formula": "python",18 "bins": ["python3"],19 "label": "Install Python (brew)",20 },21 ],22 },23 }24---2526# OpenAI Image Gen2728Generate a handful of “random but structured” prompts and render them via the OpenAI Images API.2930## Run3132Note: Image generation can take longer than common host tool timeouts33(for example 30 seconds). When invoking this skill via OpenClaw's34`exec_command`, set a higher `timeout_sec` to avoid premature35termination or retries (for example `timeout_sec=300`).3637```bash38python3 {baseDir}/scripts/gen.py39open ~/Projects/tmp/openai-image-gen-*/index.html # if ~/Projects/tmp exists; else ./tmp/...40```4142Useful flags:4344```bash45# GPT image models with various options46python3 {baseDir}/scripts/gen.py --count 16 --model gpt-image-147python3 {baseDir}/scripts/gen.py --prompt "ultra-detailed studio photo of a lobster astronaut" --count 448python3 {baseDir}/scripts/gen.py --size 1536x1024 --quality high --out-dir ./out/images49python3 {baseDir}/scripts/gen.py --model gpt-image-1.5 --background transparent --output-format webp5051# DALL-E 3 (note: count is automatically limited to 1)52python3 {baseDir}/scripts/gen.py --model dall-e-3 --quality hd --size 1792x1024 --style vivid53python3 {baseDir}/scripts/gen.py --model dall-e-3 --style natural --prompt "serene mountain landscape"5455# DALL-E 256python3 {baseDir}/scripts/gen.py --model dall-e-2 --size 512x512 --count 457```5859## Model-Specific Parameters6061Different models support different parameter values. The script automatically selects appropriate defaults based on the model.6263### Size6465- **GPT image models** (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`): `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto`66 - Default: `1024x1024`67- **dall-e-3**: `1024x1024`, `1792x1024`, or `1024x1792`68 - Default: `1024x1024`69- **dall-e-2**: `256x256`, `512x512`, or `1024x1024`70 - Default: `1024x1024`7172### Quality7374- **GPT image models**: `auto`, `high`, `medium`, or `low`75 - Default: `high`76- **dall-e-3**: `hd` or `standard`77 - Default: `standard`78- **dall-e-2**: `standard` only79 - Default: `standard`8081### Other Notable Differences8283- **dall-e-3** only supports generating 1 image at a time (`n=1`). The script automatically limits count to 1 when using this model.84- **GPT image models** support additional parameters:85 - `--background`: `transparent`, `opaque`, or `auto` (default)86 - `--output-format`: `png` (default), `jpeg`, or `webp`87 - Note: `stream` and `moderation` are available via API but not yet implemented in this script88- **dall-e-3** has a `--style` parameter: `vivid` (hyper-real, dramatic) or `natural` (more natural looking)8990## Output9192- `*.png`, `*.jpeg`, or `*.webp` images (output format depends on model + `--output-format`)93- `prompts.json` (prompt → file mapping)94- `index.html` (thumbnail gallery)
trpc-group 