Testing
Prototyping
We used RunwayML to test a range of Machine Learning models like SPADE-COCO (Sketch-to-Image), PhotoSketch (Image-to-Sketch), and Img2Txt (Image-to-Text). We used the chaining feature to link the output of one model with the input of the other to create a desirable sandboxed experience.
To prototype the conversational experience, we built a model using AWS - Lex and a sandboxed experience inside of RunwayML using Apple's dictation. Through our research, we were able to reverse engineer the runwayML models and the AWS Lex chatbot experience to formulate our proof of concept.
To prototype the conversational experience, we built a model using AWS - Lex and a sandboxed experience inside of RunwayML using Apple's dictation. Through our research, we were able to reverse engineer the runwayML models and the AWS Lex chatbot experience to formulate our proof of concept.