Behind the scenes of Google's state-of-the-art "nano-banana" image model

Behind the scenes of Google's state-of-the-art "nano-banana" image model

Join host Logan Kilpatrick in discussion with some of the minds behind Google's new state-of-the-art image model, Gemini 2.5 Flash. Product and research leads from the Gemini team break down the technology behind its key capabilities, including interleaved generation for complex edits and new approaches to achieving character consistency and pixel-perfect control. With Nicole Brichtova, Kaushik Shivakumar, Mostafa Dehghani and Robert Riachi.

Watch on YouTube:

Chapters:
0:37 - New model introduction
1:21 -Demo - Image Editing
3:44 - Text rendering capabilities
4:44 Beyond human preference evals
6:44 - Text rendering as a proxy for quality
8:38 - Positive transfer between modalities
11:25 - Demo - Multi-turn, context aware image generation
13:54 - Pixel-perfect editing and character consistency
15:51 - Interleaved image generation
17:59 - Specialized vs. native models
19:52 - Understanding nuanced prompts
20:59 - User feedback shaping model development
22:37 - Improvements in character consistency
24:17 - More natural looking images from team collaboration
26:41 - What’s next for image generation models

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(31)

Sameer Samat on Android 17 and the Future of Intelligent Computing

Sameer Samat on Android 17 and the Future of Intelligent Computing

Sameer Samat, President of Android at Google, joins host Logan Kilpatrick to discuss Android 17 and what it means to shift from operating systems to intelligence systems. Their conversation covers why...

30 Jun 40min

Yossi Matias on the golden age of research

Yossi Matias on the golden age of research

Yossi Matias, Vice President at Google and Head of Google Research, joins host Logan Kilpatrick for a wide-ranging conversation about what it means to do research at Google scale. Their conversation e...

22 Jun 1h 11min

Gemini co-leads on project origins and what's next

Gemini co-leads on project origins and what's next

To mark the launch of Gemini 3.5 Flash, Logan Kilpatrick sat down at Gradient Canopy with four of the people who built it: Jeff Dean, Koray Kavukcuoglu, Noam Shazeer, and Oriol Vinyals. They talked ab...

22 Jun 41min

Google I/O 2026 Recap with Logan Kilpatrick, Josh Woodward and Tulsee Doshi

Google I/O 2026 Recap with Logan Kilpatrick, Josh Woodward and Tulsee Doshi

Josh Woodward from Google Labs, Gemini and AI Studio and Tulsee Doshi from Google DeepMind join host Logan Kilpatrick to break down the biggest launches from Google I/O 2026, from Gemini 3.5 Flash and...

22 Jun 32min

Google Maps Leaders Talk About Its Biggest Update in 10 Years

Google Maps Leaders Talk About Its Biggest Update in 10 Years

Miriam Daniel and David Cronin join host Logan Kilpatrick to unveil the biggest update in Google Maps history. This episode explores the launch of Ask Maps, a conversational experience powered by Gemi...

12 Mar 36min

Gemini in Workspace: New Ways to Create Faster

Gemini in Workspace: New Ways to Create Faster

Chapters: 1:15 - Gemini in Docs 3:17 - Which models power Workspace 3:45 - AI Overviews in Drive 5:22 - Rollout and availability 6:33 - Reimagining every Workspace canvas 8:58 - Gemini in Calend...

12 Mar 40min

Gemini in Chrome: Your agentic browsing assistant

Gemini in Chrome: Your agentic browsing assistant

Chapters: 0:00 - Introduction 2:49 - Evolution from web apps to integrated assistants 4:37 - Chrome as a platform for personal context 6:38 - Navigating the context overload problem 7:52 - Transf...

12 Mar 48min

Inside Lyria 3, Google's music generation model

Inside Lyria 3, Google's music generation model

1:00 - Defining music generation models1:40 - Lyria as a new instrument3:05 - Connecting language and creative intent5:08 - Guest backgrounds and musical journeys7:57 - Demo: Instrumental funk jam8:29...

18 Feb 36min

Populært innen Vitenskap

fastlegen
tingenes-tilstand
abels-tarn
romkapsel
jss
liberal-halvtime
vett-og-vitenskap-med-gaute-einevoll
rekommandert
villmarksliv
sinnsyn
dekodet-2
fjellsportpodden
rss-rekommandert
rss-overskuddsliv
tomprat-med-gunnar-tjomlid
rss-inn-til-kjernen-med-sunniva-rose
kvinnehelsepodden
diagnose
hva-er-greia-med
rss-paradigmepodden