my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

my-project-public — gitlawb

#1	---
#2	name: openai-image-gen
#3	description: Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
#4	homepage: https://platform.openai.com/docs/api-reference/images
#5	metadata: {"clawdbot":{"emoji":"🖼️","requires":{"bins":["python3"],"env":["OPENAI_API_KEY"]},"primaryEnv":"OPENAI_API_KEY","install":[{"id":"python-brew","kind":"brew","formula":"python","bins":["python3"],"label":"Install Python (brew)"}]}}
#6	---
#7
#8	# OpenAI Image Gen
#9
#10	Generate a handful of “random but structured” prompts and render them via the OpenAI Images API.
#11
#12	## Run
#13
#14	```bash
#15	python3 {baseDir}/scripts/gen.py
#16	open ~/Projects/tmp/openai-image-gen-*/index.html # if ~/Projects/tmp exists; else ./tmp/...
#17	```
#18
#19	Useful flags:
#20
#21	```bash
#22	# GPT image models with various options
#23	python3 {baseDir}/scripts/gen.py --count 16 --model gpt-image-1
#24	python3 {baseDir}/scripts/gen.py --prompt "ultra-detailed studio photo of a lobster astronaut" --count 4
#25	python3 {baseDir}/scripts/gen.py --size 1536x1024 --quality high --out-dir ./out/images
#26	python3 {baseDir}/scripts/gen.py --model gpt-image-1.5 --background transparent --output-format webp
#27
#28	# DALL-E 3 (note: count is automatically limited to 1)
#29	python3 {baseDir}/scripts/gen.py --model dall-e-3 --quality hd --size 1792x1024 --style vivid
#30	python3 {baseDir}/scripts/gen.py --model dall-e-3 --style natural --prompt "serene mountain landscape"
#31
#32	# DALL-E 2
#33	python3 {baseDir}/scripts/gen.py --model dall-e-2 --size 512x512 --count 4
#34	```
#35
#36	## Model-Specific Parameters
#37
#38	Different models support different parameter values. The script automatically selects appropriate defaults based on the model.
#39
#40	### Size
#41
#42	- GPT image models (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`): `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto`
#43	- Default: `1024x1024`
#44	- dall-e-3: `1024x1024`, `1792x1024`, or `1024x1792`
#45	- Default: `1024x1024`
#46	- dall-e-2: `256x256`, `512x512`, or `1024x1024`
#47	- Default: `1024x1024`
#48
#49	### Quality
#50
#51	- GPT image models: `auto`, `high`, `medium`, or `low`
#52	- Default: `high`
#53	- dall-e-3: `hd` or `standard`
#54	- Default: `standard`
#55	- dall-e-2: `standard` only
#56	- Default: `standard`
#57
#58	### Other Notable Differences
#59
#60	- dall-e-3 only supports generating 1 image at a time (`n=1`). The script automatically limits count to 1 when using this model.
#61	- GPT image models support additional parameters:
#62	- `--background`: `transparent`, `opaque`, or `auto` (default)
#63	- `--output-format`: `png` (default), `jpeg`, or `webp`
#64	- Note: `stream` and `moderation` are available via API but not yet implemented in this script
#65	- dall-e-3 has a `--style` parameter: `vivid` (hyper-real, dramatic) or `natural` (more natural looking)
#66
#67	## Output
#68
#69	- `.png`, `.jpeg`, or `*.webp` images (output format depends on model + `--output-format`)
#70	- `prompts.json` (prompt → file mapping)
#71	- `index.html` (thumbnail gallery)
#72

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public