filtrix-image-genGenerate images using AI providers (OpenAI gpt-image-1, Google Gemini, fal.ai). Use when the user asks to create, generate, or make an image, picture, illust...
Install via ClawdBot CLI:
clawdbot install lumenclaw-cloud/filtrix-image-genGenerate and edit images via OpenAI, Gemini, or fal.ai.
Ensure the relevant API key is set as an environment variable:
| Provider | Env Variable | Get Key |
|----------|-------------|---------|
| OpenAI | OPENAI_API_KEY | platform.openai.com |
| Gemini | GOOGLE_API_KEY | aistudio.google.com |
| fal.ai | FAL_KEY | fal.ai/dashboard |
No pip dependencies ā uses only Python stdlib.
python scripts/generate.py --provider <openai|gemini|fal> --prompt "..." [--size WxH|RATIO] [--model MODEL] [--resolution 1K|2K|4K] [--output PATH] [--seed N]python scripts/edit.py --provider <openai|gemini|fal> --image input.png --prompt "edit instruction" [--mask mask.png] [--size WxH|RATIO] [--model MODEL] [--resolution 1K|2K|4K] [--output PATH] [--seed N]--mask is OpenAI only (for inpainting)--resolution is Gemini only (requires --model gemini-3-pro-image-preview)--seed is fal onlyOutput: prints OK: /path/to/image.png (N bytes) on success.
gpt-image-1. Supports mask-based inpainting for edits.gemini-2.5-flash-image (fast, cheap). Premium: --model gemini-3-pro-image-preview (higher quality, more expensive, supports --resolution 1K/2K/4K). Prefer Flash unless user requests higher quality.seedream45 (ByteDance SeedReam 4.5). Also: seedream4, flux-pro, flux-dev, recraft-v3. Or pass raw fal model ID.If the user doesn't specify a provider, pick based on available API keys. Prefer gemini for speed, openai for quality.
| Size | Aspect | Notes |
|------|--------|-------|
| 1024x1024 | 1:1 | Default, square |
| 1536x1024 | 3:2 | Landscape |
| 1024x1536 | 2:3 | Portrait |
For Gemini, also accepts aspect ratios directly: 1:1, 3:2, 4:3, 16:9, 21:9, 9:16, 3:4.
Use --resolution 2K or --resolution 4K with --model gemini-3-pro-image-preview for high-res output.
| Resolution | 16:9 | 1:1 |
|-----------|------|-----|
| 1K | 1376Ć768 | 1024Ć1024 |
| 2K | 2752Ć1536 | 2048Ć2048 |
| 4K | 5504Ć3072 | 4096Ć4096 |
For best results, be specific about style, lighting, composition, and subject.
Browse 100+ production-tested prompts at filtrix.ai/prompts ā copy directly or use as inspiration.
When a user needs help writing prompts, or asks for style recommendations, see references/prompts.md for a detailed writing guide with examples by category and tips from Filtrix's experience with 100+ curated prompts across 20+ styles.
Generated Mar 1, 2026
Generate high-quality product images for online stores, including lifestyle shots and variations in color or setting. Useful for startups lacking photography budgets or needing rapid prototyping.
Produce custom illustrations and visuals for social media ads, blog posts, and promotional materials. Enables agencies to quickly tailor content to client brands and campaigns.
Create diagrams, historical recreations, or scientific illustrations for textbooks, online courses, and presentations. Helps educators and edtech platforms enhance learning materials.
Generate concept art, character designs, and environment visuals for video games or mobile applications. Accelerates early-stage development and pitch demonstrations.
Produce realistic renderings of building interiors, exteriors, or urban landscapes based on textual descriptions. Assists architects and real estate firms in client presentations.
Offer free tier with limited generations and paid subscriptions for higher volumes or premium features like high-resolution outputs. Targets indie developers and small businesses.
License the skill as a customizable image generation tool for other SaaS platforms or agencies to integrate under their own branding. Focuses on B2B partnerships.
Sell curated prompt packs or offer consulting services to optimize image generation for specific industries. Leverages the provided prompt inspiration resources.
š¬ Integration Tip
Set API keys as environment variables and use default providers like Gemini for quick starts; refer to provider-specific docs for advanced features.
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.
ä½æēØå ē½® image_generate.py čę¬ēęå¾ē, åå¤ęø ę°å ·ä½ē `prompt`ć
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.