Subvolts take Learn how Google's Nano Banana achieved character consistency and what it means for visual AI. Nov 11, 2025 - Developers
- Learn about achieving character consistency in image generation and the role of data quality in AI realism.
- Business
- Understand how user creativity drives AI utility and how models like Nano Banana impact personal storytelling and professional design.
- Everyday users
- Discover how AI image models are evolving to let you see yourself in new worlds and create compelling personal content.
This episode provides a solid interview with the leads behind a significant Google AI image model, discussing its development and impact.
How Google’s Nano Banana Achieved Breakthrough Character Consistency
Audio streams from Sequoia Capital. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Sequoia Capital's Training Data podcast features Google's Nicole Brichtova and Hansa Srinivasan discussing their Nano Banana image model. They explain how they achieved character consistency, the importance of human evaluation for AI that feels right, and the role of user creativity in driving visual AI's future. The conversation also touches on Gemini's multimodal design and data quality's impact on realism.
Google's "Nano Banana" is an AI that creates images, and its creators explain how they made characters look consistent. They discuss why human feedback is key to making AI feel right and how people use it for fun and work.
This episode offers insight into Google's approach to visual AI, specifically character consistency in image generation with Nano Banana. It's for product managers, engineers, and AI enthusiasts interested in the practical challenges and successes of building user-facing AI. The discussion on human evaluation and data quality directly relates to ongoing efforts by frontier labs like Google Gemini, Anthropic, and Meta AI to improve model realism and user experience.
- HostSequoia Capital
- GuestNicole Brichtovaproduct lead, Google
- GuestHansa Srinivasanengineering lead, Google
- Episode Title: How Google’s Nano Banana Achieved Breakthrough Character Consistency
- Show: Training Data (an official AI show)
- Hosts: Sequoia Capital
- Length: 44 minutes
- Model: Nano Banana
- Company: Google
When Google launched Nano Banana, it instantly became a global phenomenon, introducing an image model that finally made it possible for people to see themselves in AI-generated worlds. In this episode, Nicole Brichtova and Hansa Srinivasan, the product and engineering leads behind Nano Banana, share the story behind the model’s creation and what it means for the future of visual AI.
Nicole and Hansa discuss how they achieved breakthrough character consistency, why human evaluation remains critical for models that aim to feel right, and how “fun” became a gateway to utility. They explain the craft behind Gemini’s multimodal design, the obsession with data quality that powered Nano Banana’s realism, and how user creativity continues to push the technology in unexpected directions—from personal storytelling to education and professional design. The conversation explores what comes next in visual AI, why accessibility and imagination must evolve together, and how the tools we build can help people capture not just reality but possibility.
Hosted by: Stephanie Zhan and Pat Grady, Sequoia Capital
- character consistency
- Nicole Brichtova and Hansa Srinivasan
- making sure a person or object looks the same across different AI-generated images.
- multimodal design
- AI that can understand and work with different types of information, like text, images, and sound, all at once.
1 h 08David Silver and Lasse Espeholt of Ineffable Intelligence: A Superlearner for the Age of Experience
WithDavid Silver, Lasse Espeholt
1 h 041 h 0552 minMaking Cities Awesome: Peregrine’s Nick Noone & Ben Rudolph
WithNick Noone, Ben Rudolph
Same guests, other shows
41 minEp 75: Nano Banana’s Oliver Wang and Nicole Brichtova - Behind the Breakthrough as Gemini Tops the Charts
WithNicole Brichtova, Oliver Wang
31 minBehind the scenes of Google's state-of-the-art "nano-banana" image model
WithNicole Brichtova, Kaushik Shivakumar, Mostafa Dehghani, Robert Riachi
59 minThe CEO Behind the Fastest-Growing AI Inference Company | Tuhin Srivastava
WithTuhin Srivastava
57 min
Questions people ask
- What is Nano Banana?
- Nano Banana is an image model developed by Google that enables users to see themselves in AI-generated worlds, achieving breakthrough character consistency.
- Why is human evaluation important for AI models?
- Human evaluation remains critical for models aiming to 'feel right,' ensuring they meet user expectations for realism and usability beyond automated metrics.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Sequoia Capital.