Many models of the near‐Earth's space environment (radiation belts, ionosphere, upper atmosphere, etc.) are driven by geomagnetic indices, representing the state of disturbance of the Earth's magnetosphere. Over the past decade, machine learning‐based methods for forecasting geomagnetic indices from near‐Earth solar wind parameters have become popular in the space weather community. These methods often prove to be very accurate and skilled. However, these approaches have the notable drawback of being effective in an operational context only for limited forecasting horizons (often up to a couple of hours ahead at best). In order to increase this prediction horizon, we introduce SERENADE, a novel deep learning‐based proof‐of‐concept model using images delivered by the Atmospheric Imaging Assembly instrument onboard the Solar Dynamics Observatory spacecraft to directly provide probabilistic forecasts of the daily maximum of the geomagnetic index Kp up to a few days ahead. We show in particular that SERENADE is able to capture information on the geomagnetic dynamics from solar imaging alone. In addition, despite it being a prototypical model, our model is more accurate in most situations than three empirical baseline models. However, the model still shows some strong limitations inherent to its structure and the used data set, which could be the focus of future works. This opens the way to a better mid‐to‐long term data‐driven magnetospheric modeling within space weather and geophysical pipelines. Plain Language Summary The Sun is an active star that constantly emits particles in all directions, including toward the Earth. This flow of charged particles (called solar wind) interacts with and disturbs the Earth's magnetic field, resulting in so‐called geomagnetic storms. Geomagnetic storms, and generally speaking Sun‐Earth interactions, can have dramatic consequences on spacecrafts, aircrafts (and their passengers), and electrical power grids. That is why it is essential to be able to accurately forecast the state of disturbance of the Earth's magnetosphere. Most current models rely on in‐situ near‐Earth measurements of the solar wind to forecast the geomagnetic activity up to a few hours in advance. In order to extend the forecasting horizon, we investigate the direct use of solar imaging to drive an artificial intelligence‐based model designed to forecast the geomagnetic activity up to a few days in advance. To do so, we design SERENADE, a prototype model able to partially capture the geomagnetic dynamics at least 2 days ahead, which shows that our approach is very promising. Our model is one of the first of its kind and, although it is not yet ready to be used in an operational context, it opens the way to future developments. Key Points SERENADE is a neural network‐based prototype model designed to forecast the daily maximum of the geomagnetic index Kp 2‐to‐7 days ahead The model's inputs are composed uniquely of sequences of images of the Sun provided by the Solar Dynamics Observatory/Atmospheric Imaging Assembly instrument in the 19.3 nm wavelength The model is able to reproduce some of the Stream Interaction Region‐driven dynamics of Kp and outperforms three empirical baseline models