I have different workflows to take text to an image and then to a video and also text to image or image to video, but I’m looking for a workflow that can take an existing image and provide text to direct the video creation.
Image + text prompt input → video
Are there any that exist? I’ve searched, but maybe I’m not using the correct key words…?
Please also let me know what else I need to make that workflow work, like what models or transformers.
Thank you for any recommendations.