There are a lot of new multimodal models coming out, do you plan to support them?
1 Like
Hi @azamat !
Thanks for the question! Yes, we’re working on OCR support in the short term, so you’ll be able to recognise and extract text from images. Image generation is on our longer-term roadmap. We’ll prioritise it if we see more interest from the community.
Could you elaborate on your specific use case? That would help us understand how to best support your needs.