SaaS & AI
Aneya
By transforming GIF creation through the practical redesign of text prompts, our platform seamlessly integrates AI, voice assistants, and an intuitive interface, enabling users to generate dynamic GIFs in real time.
Duration
Collaborators
Tools
15 Weeks | Aug - Dec 2023
Figma, Nvivo, Hotjar, Miro
ML Engineers, AI Researchers, Designers
Project overview
Our platform redefines GIF creation by combining AI, voice assistants, and intuitive design, allowing users to effortlessly generate dynamic, personalized GIFs through text prompts, cursor tracking, and voice recognition. Our vision is to empower creativity while fostering a seamless synergy between human expression and AI innovation.
Metrics
Increase in session interaction
30%
Reduction in customized Gif creation time
25%
Increased creative control
60%
Contributions
01
Conducted research on Large Language Models (LLMs), human-AI interaction and text-prompts to develop Gen AI-driven solutions.
02
Created 80+ responsive designs exploring practical redesign of text prompts with multi-modal inputs and real-time outputs.
03
Performed semi-contextual inquiries, competitive analysis and iterated multiple designs in 3 sprints.
Problem
01
Creative Constraints
Limited Exploration
02
03
Impaired Innovation
Traditional text prompts are rigid and predefined, limiting users' creative freedom and their ability to fully experiment.
Rigid prompts hinder the exploration of new AI-powered possibilities, limiting users’ creative growth and artistic innovation.
Predefined inputs restrict users from exploring new techniques, innovative styles, and dynamic creative possibilities.
Solution
Multi modal inputs - Diversifying creative inputs
Users can get creative using different inputs at the same time, they can type/select ideas suggested by the text prompt, upload sketches or photos, draw on the canvas, or simply speak to Aneya's voice assistant.
These features seamlessly work together, letting users switch between sketching, getting suggestions via text, or using voice commands making creative expression easy and dynamic.
Realtime output - Minimizing creative lag
With our real-time output feature, users can instantly see the impact of their inputs on the GIF in the adjacent output panel.
This seamless integration enhances user-friendliness, allowing quick adjustments based on the generated output. The dynamic and intuitive process ensures a smoother and more engaging creative experience by minimizing the delays between prompts and generated outputs.
Cursor tracking - Enabling natural ways of interaction
Users can simply express their desired animation using voice commands while drawing on the canvas. For example, saying 'from here to here' guides Aneya to track the cursor and understand the animation direction.
This seamless integration of voice and cursor tracking enhances the creative process, making it more user-friendly and accessible for users to bring their animations to life.
In the rapidly evolving world of digital art creation, conventional text prompts have posed significant challenges, limiting users' ability to fully realize their creative potential. We aimed to explore text prompt-based inputs and deliver an intuitive solution that seamlessly integrates artificial intelligence with human ingenuity.
After conducting our contextual inquiries, we gained a deeper understanding of how the problem is currently being addressed. This analysis helped us refine our ideas for potential features and inspired further directions for the project. During our competitive analysis, we focused on key aspects such as intuitiveness, cognitive load, and the balance between manual and conversational text prompts.
By synthesizing the data, we were able to map the issues identified in our secondary research to specific categories, which allowed us to clearly visualize the problem areas and opportunities for improvement.
Here’s how Amy currently navigates the process of creating GIFs, juggling multiple platforms and steps to meet tight deadlines while maintaining quality.
Meet Amy, a Creative Designer at an ad agency. With tight deadlines, she creates short GIFs for campaigns and uses various platforms to quickly produce them, saving time while maintaining quality.
Process
Context
Problem
Understanding gaps in the other platforms
Competitive Analysis
Semi-Contextual inquiries
Research -
We conducted semi-structured contextual inquiries to uncover key themes and identify opportunities based on our research. By observing users in their natural environments and engaging them in open-ended discussions, we focused on 3-4 generative AI sites as examples.
From these inquiries, we identified four recurring themes, supported by direct user quotes. To refine these insights, we applied thematic analysis, coding the data to uncover patterns and relationships between the themes.
By digging deeper into the underlying issues and user needs, we were able to refine and reframe the initial themes into four more focused ones. Through a strategic brainstorming session, we then developed four key solutions to address these themes: introducing a variety of multimodal inputs, bridging the gap between prompt creation and the desired output, offering customizable text prompts, and enabling real-time output
AI Experts and platform users
Interviews -
Through discussions with experts, we gained valuable insights into how users engage with AI-driven systems, including their expectations, preferences, and pain points. By considering expert perspectives on human-AI interaction, we identified key factors for designing intuitive interfaces and seamless user experiences.
Understanding the strengths and limitations of generative AI models allowed us to implement features that not only boost user engagement and satisfaction but also minimize potential sources of frustration or confusion.
Design decisions
Through discussions with experts, we gained valuable insights into how users engage with AI-driven systems, including their expectations, preferences, and pain points. By considering expert perspectives on human-AI interaction, we identified key factors for designing intuitive interfaces and seamless user experiences.
Understanding the strengths and limitations of generative AI models allowed us to implement features that not only boost user engagement and satisfaction but also minimize potential sources of frustration or confusion.
Design process
The input panel offered a range of drawing options and settings, similar to those in standard drawing applications, such as color, line thickness, and opacity adjustments. On the other hand, the output panel focused on settings for audio, video, and keyframe adjustments, providing users with the customization and control they needed to fine-tune their GIF creations.
Conceptualizing two distinct panels
Designing the text-prompt
We explored the idea of eliminating traditional settings options to simplify the user experience. A key feature that emerged was the introduction of a smart AI text prompt, which leveraged users’ history to suggest ideas and streamline the creative process. We also envisioned seamlessly integrating text and voice inputs, giving users multiple ways to interact with the platform and effortlessly generate GIFs.
To further enhance interaction, we introduced cursor tracking, transforming how users engaged with the platform by enabling them to issue commands casually while sketching or adding photos. By combining this with other input methods, our goal was to create a fluid, intuitive experience that allowed users to express their creativity without the constraints of traditional input options.
Making the platform intuitive
Full solution
Developed prototype
Simultaneously while working on Designs our development team explored some really cool things like Controlnet morphing, frame interpolation for large motions, and even played around with Controlnet plus dream booth.
Reflection
This project opened doors to a new realm of UX design, unlike any I've encountered before. Exploring GIF creation introduced me to unique challenges and methodologies, especially in understanding generative AI trends and real-time collaboration tools. It highlighted the importance of intuitive interactions and personalized experiences, reshaping my approach to design and digital experiences. Participating in the creative AI project helped me explore how technology and human creativity intersected. It encouraged me to try new things beyond traditional user research methods.
Way forward I would like to bring additional user's perspective into this and have more user research rounds to make it user centered as well.
