{"skill":{"slug":"krea","displayName":"krea","summary":"Generate images, videos, upscale/enhance images, and train LoRA styles using the Krea.ai API. Supports 20+ image models (Flux, Imagen, GPT Image, Ideogram, S...","tags":{"latest":"1.0.1"},"stats":{"comments":0,"downloads":123,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":2},"createdAt":1774832091594,"updatedAt":1775691408596},"latestVersion":{"version":"1.0.1","createdAt":1775691172424,"changelog":"- Dynamic model/parameter resolution: All scripts now fetch available models, CU costs, and parameters live from the Krea API's OpenAPI spec. No more hardcoded model tables.\n- New: Added LoRA style training script (`train_style.py`) for custom style creation.\n- Expanded local file support for `--image-url`, `--start-image`, and related arguments (URLs and local paths accepted).\n- Parameter defaults and model aliases updated to match current Krea API (e.g. `nano-banana-2`, `veo-3.1-fast`).\n- Documentation fully revised for dynamic usage, improved workflow guidance, and current script options.\n- Enhanced error guidance and model selection mapping based on live API data.","license":"MIT-0"},"metadata":null,"owner":{"handle":"albertsalgueda","userId":"s174n617n7w44nc1chez882by583rxdc","displayName":"Albert Salgueda","image":"https://avatars.githubusercontent.com/u/73529639?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.2.0","updatedAt":1775691408596}}