openai-image-gen-fixedBatch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Install via ClawdBot CLI:
clawdbot install saschaSpoonbill/openai-image-gen-fixedGenerate a handful of “random but structured” prompts and render them via OpenAI Images API.
OPENAI_API_KEYFrom any directory (outputs to ~/Projects/tmp/... when present; else ./tmp/...):
python3 ~/Projects/agent-scripts/skills/openai-image-gen/scripts/gen.py
open ~/Projects/tmp/openai-image-gen-*/index.html
Useful flags:
python3 ~/Projects/agent-scripts/skills/openai-image-gen/scripts/gen.py --count 16 --model gpt-image-1.5
python3 ~/Projects/agent-scripts/skills/openai-image-gen/scripts/gen.py --prompt "ultra-detailed studio photo of a lobster astronaut" --count 4
python3 ~/Projects/agent-scripts/skills/openai-image-gen/scripts/gen.py --size 1536x1024 --quality high --out-dir ./out/images
*.png imagesprompts.json (prompt ↔ file mapping)index.html (thumbnail gallery)Generated Feb 28, 2026
Agencies can use this skill to quickly generate diverse visual content for social media campaigns or advertisements. By leveraging random prompts, it produces unique images that capture attention and align with brand themes, reducing reliance on stock photos.
Design teams can generate multiple visual concepts for new products or packaging designs. The batch generation allows for rapid iteration and comparison of ideas, speeding up the early stages of product development.
Educators and e-learning platforms can create custom illustrations for textbooks, presentations, or online courses. The random prompt feature helps generate varied imagery to explain complex topics visually.
Artists and illustrators can use this skill to overcome creative blocks by generating unexpected image prompts. The gallery output allows easy browsing of results, serving as a starting point for further artistic refinement.
Web developers and designers can produce custom graphics for websites or apps, such as hero images or icons. The ability to specify prompts and output directories streamlines integration into development workflows.
Offer a monthly subscription where users receive a set number of AI-generated images for their marketing or design needs. This provides recurring revenue and caters to businesses needing regular visual content updates.
Provide bespoke image creation services for clients in industries like advertising or publishing. Use the skill to quickly prototype ideas and deliver high-quality, tailored visuals based on specific client prompts.
License this skill as a plugin or API for existing design tools or platforms, such as graphic design software. Charge based on usage or through one-time licensing fees for integration into third-party applications.
💬 Integration Tip
Ensure the OPENAI_API_KEY is securely stored in environment variables and consider automating output directory management for seamless workflow integration.
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Capture frames or clips from RTSP/ONVIF cameras.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation.
使用内置 image_generate.py 脚本生成图片, 准备清晰具体的 `prompt`。
AI image generation powered by CellCog. Create images, edit photos, consistent characters, product photography, reference-based images, sets of images, style transfer. Professional image creation with AI.