Add vision multimodal into publer#2343

I have an app to get photos taken time, date, weather, location and identify the photo with openai vision api, then,
DRAFT A POST for the photo
https://photo2writing.vercel.app/?lang=en

My another app is to tranform photos into ex. Ghibli fashion via calling openai api
https://imageapi2me.vercel.app/

Publer should be able to do the same. Even more, generate video from photo. Schedule the post. Post.