Reimagining Gen AI

Led the design for a set of Generative AI Vision features, all within tight deadlines and complex technical constraints. Attracted significant customer base for early trials. Featured in Cloud Next ‘23 Keynote by Executives.

Background

Studio Vision empowers developers with generative vision AI capabilities. I led the design for a range of advanced Generative AI Vision features encompassing fine-tuning, style transfer, digital watermarking, prompt expansion, image captioning, image understanding, and video generation.

Goals

• Unified platform: An integrated hub for exploring, envisioning, and experimenting with diverse vision generation capabilities.
• Seamless Editing: A seamless experience of generating and editing media with prompts.
• Better Prompting: Help users build better prompts with hands-on “learning by doing”.

Final Design

From Words to Pixels: Unleash Your Creativity with Image Generation

Embark on an artistic journey with image generation, where mere words ignite a symphony of pixels. Seamlessly refine your creations by steering them towards specific styles or subjects with a single click, unlocking endless creative possibilities.

Unlock Video Insights: Single-Click Access to Concise Video Descriptions

Effortlessly grasp the essence of a video with a concise description that encapsulates its key points, accessible within a single click.

Crafting Expressive Video Narratives with Scene-Based Generation

Empower users with granular control over video creation through scene-based generation, enabling the crafting of personalized and nuanced video narratives.

Design Details

Unlocking Visual Inspiration with the Prompt Gallery

• Problem: Users struggled to craft effective prompts, leading to frustration when image generation didn't match their vision.
• Solution: Introduce Inspiration Gallery, showcasing stunning visuals and corresponding prompts, empowering users to achieve their desired results easily.

Beyond Text Prompts: Detailed Image Customization

• Problem: Users lacked precise control over image generation, leading to unpredictable and sometimes undesirable results.
• Solution: Empower users with granular controls over style, color, subjects, and other key elements. This surpasses simple text prompts for greater customization.

Effortless Visual Exploration with Co-Creative Prompts

• Problem: Prompt generation was cumbersome. Users relied on external tools and time-consuming trial and error to discover desirable image styles.
• Solution: The 'Co-Create' feature offers diverse prompt suggestions from a single input. Infinite scrolling provides continuous inspiration, and AI adapts to user preferences for more personalized results.

Visioning

Generative AI is a new and exciting field, and the best ways to use it are still being discovered. I took the lead in imagining what these powerful tools will be capable of in just two years.

Mastering the Flow: Intuitive Workspaces for Divergent Exploration

Current tools force users to switch between pages, which disrupts their creative process and reduces productivity.

Switching between pages in current tools breaks the creative flow and makes work less efficient.

My design consolidates the creation process within a single workspace. Prompting, inspiration management, and image viewing are easily accessible, encouraging a smoother and more intuitive experience.

Effortless Execution with a Unified Editing Toolkit

 Too many separate tools in products like Adobe Firefly create clutter and disrupt the creative process.

Adobe Firefly's many tools cause clutter and break up the creative process.

I designed a unified editing view where users have all their tools at their fingertips. This allows them to focus on executing their vision seamlessly.

My design supports the entire creative journey – from idea generation to final execution – within a single, streamlined interface.

Highlighted as top tier announcement at I/O and Cloud Next opening keynotes by Executives, showcasing Google's leadership in Generative AI.