Image to Emote

Created by team Image2Emote on December 04, 2022

The system generates emotions from images, primarily intended for game NPCs so that they would react emotionally to the game environment. The sentiment analysis model is an LSTM-based Dense Neural Network that are fed Word2Vec embeddings. The model was trained using generated data from using the prompt: "I felt <emotion> when I saw <img2text>" System Flow: img2txt -> generator -> text2emote -> LSTM+DenseNN The images are passed to a CLIP Interrogator (BLIP + CLIP (ViT-32-B)) to generate text descriptions. Such text descriptions are elaborated by generator to generate emotional responses using the prompts: "When I saw <img2txt output>, I felt emotions such as"

Category tags: