CrayEye now supports local/FOSS models – multimodal vision multitool

I (or more accurately A.I.) made the FOSS mobile app <a href="https:&#x2F;&#x2F;www.crayeye.com" rel="nofollow">https:&#x2F;&#x2F;www.crayeye.com</a> to make it easier to experiment with multimodal vision prompts augmented by device data (e.g. location, date&#x2F;time).<p>While this tool still uses GPT-4v &#x2F; GPT-4o as its default, it now supports configuring custom engines (via OpenAPI spec) which can point to any API&#x2F;model - this has been tested using Llava (and Bakllava) running locally via Ollama.