Semantic Kernel image-to-text models

[AngelStubbings]

Regarding this blog post, can you use any image-to-text models such as Salesforce/xgen-mm-phi3-mini-instruct-r-v1 or does it have to be Salesforce/blip-image-captioning-base like in the demo?

[RogerBarreto]

@AngelStubbings , thanks for the question, the example should work with any Image-To-Text model from HuggingFace assuming they are respecting the contract from the Hugging Face APIs, let me know if that works and feel free to reopen this issue if not. Thanks!