Mood-Based Music Generator

Mood-Based Music Generator

Selection of music is hard because it happens sometimes when we cannot decide what to listen. So given such condition our model can serve the need to generate unique music by capturing their face thus detecting facial expression, background details. It can give best music based on when user is busy in activities like cooking, cleaning, driving etc. Existing models are biased on users' previous songs history (working on recommendation system) and cannot give Realtime and unique music. But our model is generating real-time music and the whole process is automated. Also, user is flexible to edit the text prompt any time. Initially, text prompt is generated from image captured through webcam which is then used for feature extraction like age, gender, emotions and background color. Later, these features are getting converted into text prompt in real-time for music generation.