OpenFlamingo

OpenFlamingo models can handle any mixed text and image sequences and produce text as an output. Captioning, visual question answering, and image classification are just some of the activities that can benefit from this and the model’s ability to take samples in context.

https://www.marktechpost.com/2023/07/01/with-five-new-multimodal-models-across-the-3b-4b-and-9b-scales-the-openflamingo-team-releases-openflamingo-v2-which-outperforms-the-previous-model/