Adobe Firefly AI Model Development
AI model development | creative strategy | creative direction | dataset development | responsible AI
Led creative strategy for Adobe Firefly's generative AI model training datasets across text-to-image and text-to-video capabilities, collaborating with computer scientists, product leadership, and strategic business development to create diverse, ethically sourced datasets
Directed creative team in developing briefs that guided artists in creating targeted content to train and improve Adobe Firefly's AI models
Developed creative frameworks that moved beyond traditional commercial photography and video, incorporating cinematic styles, lighting elements, realistic motion, and atmospheric visual elements to help models interpret spatial depth and environmental nuance
Enhanced model capabilities to depict bodies and objects in motion across diverse scenarios, contributing to the successful public beta release of Firefly's text-to-video tools, including generative b-roll and clip extension in Adobe Premiere Pro
Prompt: A cinematic, photorealistic portrait of a confident, pensive Asian man in his 30s, standing in the rain against a neon-lit cityscape at night. He wears a futuristic black leather jacket slick with rain, droplets beading on his shoulders and damp hair. His face is turned slightly away from the camera, dramatically lit by a mix of soft neon lights and golden moonlight. The night sky glows navy and purple, with a small golden moon positioned just above and to the right of his head. Neon reflections shimmer on the wet pavement in streaks of pink, violet, and electric blue. The composition features cinematic lighting and film noir-inspired shadows, casting high-contrast highlights across his face and jacket. Captured with a shallow depth of field, the background blurs softly—rain-streaked signs glow abstractly, their symbols obscured by water and motion. The overall mood is atmospheric and futuristic, with a quiet intensity and melancholic tone.