Yuqing Du
@d_yuqing
Followers
3K
Following
718
Media
30
Statuses
110
@GoogleDeepMind; CS PhD @berkeley_ai
London, UK
Joined June 2020
some things are best explained visually! can't believe it’s only been ~3 months since our OG Nano Banana model.. am very thankful to be a part of such an incredible team🌟
Today we're launching a major upgrade to the image generation capabilities of our Gemini 3 model. Gemini 3 Pro Image can generate an incredible array of realistic imagery, complex visuals, infographics and more. Here are some examples: Show me a chart of the solar system and
0
1
44
One aspect of Nano Banana Pro that's been particularly exciting for me is seeing how it opens a door towards more visual/multimodal human-AI interaction. For certain tasks, having a shared visual canvas can be more useful and practical than a primarily text-based chat interface.
Imo this is along the lines of how talking to an LLM via text is like typing into a DOS Terminal and "GUI hasn't been invented yet" of some of my earlier posts. The GUI is an intelligent canvas.
2
1
58
highly recommend using nb pro to search for yourself and invent a fun video game character profile, inventory and all
1
0
16
Thinking (test-time compute) in pixel space... 🍌 Pro tip: always peek at the thoughts if you use AI Studio. Watching the model think in pictures is really fun!
21
81
699
💖
Gemini 3 Pro is out with large jumps in multimodal understanding and reasoning. Sounds useful for another application we're picturing... 🎨
1
0
24
We’ve been intensely cooking Gemini 3 for a while now, and we’re so excited and proud to share the results with you all. Of course it tops the leaderboards, including @arena, HLE, GPQA etc, but beyond the benchmarks it’s been by far my favourite model to use for its style and
223
512
6K
"Nano Banana" is now a marketing case study 🍌 It was named at 2am by a tired PM who just needed something for the model registry. Here's my chat w/ DeepMind researchers Benigno Uria & Yuqing Du where they reveal the full story.
10
26
219
Thanks @bilawalsidhu for chatting w/ me and @benigno_uria about 🍌! (:
I just interviewed the DeepMind scientists behind Google's most viral AI sensation. Their 2am naming decision created "Nano Banana" - and they didn't expect this reaction. They've turned insanely complex AI workflows into simple text prompts, taking Gemini to #1 on the App
1
0
23
I see tremendous potential for these in robotics, especially in bridging domain gaps in data between simulation and the real world (sim2real and real2sim). Really impressive
Image generation with Gemini just got a bananas upgrade and is the new state-of-the-art image generation and editing model. 🤯 From photorealistic masterpieces to mind-bending fantasy worlds, you can now natively produce, edit and refine visuals with new levels of reasoning,
0
3
36
You know the team has built a good model when ... people go to a website that randomly serves it some of the time 5 million times
🚨🍌Breaking News: Gemini-2.5-Flash-Image-Preview (“nano-banana”) by @GoogleDeepMind now ranks #1 in Image Edit Arena. In just two weeks: 🟡“nano-banana” has driven over 5 million community votes in the Arena 🟡Record-breaking 2.5M+ votes casted for this model alone 🟡It has
9
14
204
🥹🥹 All vague-posting aside, super happy this model is finally out there & proud of everyone for making this happen 💖 let us know what you think!
Introducing Gemini 2.5 Flash Image (aka nano-banana), our SOTA image generation and editing model 🍌 As you might have already seen, this model excels at character consistency, creative edits, and has Gemini's world knowledge!
9
14
263
This shows a glimpse of what is to come in interactive visual communication. Imagine a textbook, and remove all the images. It wouldn't be a very good textbook! Really excited about the potential of this space.
We just shipped Gemini 2.5 Flash Image, aka nano-banana, a SOTA image generation and editing model 🔥 Among its impressive capabilities, you get native world understanding, multi-image merging, character consistency, and more! https://t.co/OHFKOxvIcn
1
4
29
🍌
19
12
275
Something fun we discovered: you can use #Genie3 to step into and explore your favorite paintings. Here's a short visit to Edward Hopper's "Nighthawks".
1K
1K
11K
highly recommend working with @robertarail; this sounds like an amazing opportunity for those excited about open-ended learning!
I’m building a new team at @GoogleDeepMind to work on Open-Ended Discovery! We’re looking for strong Research Scientists and Research Engineers to help us push the frontier of autonomously discovering novel artifacts such as new knowledge, capabilities, or algorithms, in an
2
2
21
We are hiring on the Veo team!📽️ Some people asked me about this at #ICML2025. If that's you, I will have told you to check https://t.co/w9gTOJiCI4 regularly. 👀It's just been updated: Europe (London, Zurich) https://t.co/2My3Fcztup US (Mountain View)
job-boards.greenhouse.io
Want to be part of a team redefining SOTA for generative video models? Excited about building models that can reach billions of users? The Veo team is hiring! We are looking for amazing researchers and engineers, in North America and Europe. Details below:
2
22
146
ahh the sounds of home 😌💚
0
1
10