BRANDING + UI/UXDignity Foundation
SDL
Magna Woman


INTERACTIVE Museumsnacht Basel 2024

A.I + MOTIONMismatching Nature

ENVIRONMENTAL DESIGN
 Foundree

RESEARCH + EDITORIALPractice-led Image and Media Research








about
play
Mismatching Nature
Nature as an Orchestra


Mentorship: Ludwig Zeller
Year: 2023
Collaborators: Paulina Ojeda, Larissa Brochella

Deep LearningAnimationSpeculative Design Mis-Matching is a visual AI exploration that focuses on raising awareness of climate change and gives a futuristic perspective by focusing on ecological mismatching. In this phenomenon, species fall out of sync due to changing environmental conditions. We created an AI-driven animation featuring five plants, initially growing in harmony but later misaligning to illustrate this disruption. The visuals, generated with DALL-E and Stable Diffusion, are paired with a soundtrack from AIVA that intensifies as the mismatch occurs. A voiceover, produced with ChatGPT and ElevenLabs, explains the concept, blending scientific insight with emotional appeal.


Tools -  Stable Diffusion, ChatGPT, Kaiber, AIVA, Eleven Labs






Exploration of Aesthetics
To explore the aesthetics, we initially started with DALL-E, experimenting with prompts to understand how they work and to determine the desired appearance of the plants. While we first considered using real plants, we ultimately decided to create fictional plants inspired by real-life flora.
 


Initial Explorations on Dall-E
Figuring out the right prompt










The Growing and Wilting stage





The Full Video

How can we use Deep Learning to raise awarness 
on Ecological Mismatching?



Email  ↗    LinkedIn  ↗    Instagram  ↗
©AkshadaBhat2025