Fabian Mentzer (@mentzer_f) profile picture

Fabian Mentzer

@mentzer_f

DeepMind during the day, modular synth guy at night: https://nitter.gq/t.co/Ea84aix9Pm

 Zürich, Schweiz
fmentzer.github.io
Joined April 2018
  • Tweets434
  • Following224
  • Followers2.7K
72Media
Photo by Fabian Mentzer (@mentzer_f)Photo by Fabian Mentzer (@mentzer_f)Photo by Fabian Mentzer (@mentzer_f)Photo by Fabian Mentzer (@mentzer_f)Photo by Fabian Mentzer (@mentzer_f)Photo by Fabian Mentzer (@mentzer_f)Photo by Fabian Mentzer (@mentzer_f)Photo by Fabian Mentzer (@mentzer_f)Photo by Fabian Mentzer (@mentzer_f)Photo by Fabian Mentzer (@mentzer_f)
Glad we launched => aistudio.google.com
Image from Fabian Mentzer (@mentzer_f)
75
276
41
4,526
459,683
Image from Fabian Mentzer (@mentzer_f)
Nano Banana 2.1 (@NanoBanana) profile pictureNano Banana 2.1
@NanoBanana2 Dec 2025
It seems like a lovely day in London. Use the prompt below on Nano Banana Pro to make cute images of a location with live weather conditions. Make sure you have search grounding enabled to get the current weather.
Image from Nano Banana 2.1 (@NanoBanana)
1
12
697
🤯🤯
sid (@immasiddx) profile picturesid
@immasiddx21 Nov 2025
Google’s Nano Banana Pro is by far the best image generation AI out there. I gave it a picture of a question and it solved it correctly in my actual handwriting. Students are going to love this. 😂
Image from sid (@immasiddx)
3
745
Prompt: "Make this into professional digital art. zoom out a bit and show more. Make it look engaging"
1
86
not sure what happened here lol
Image from Fabian Mentzer (@mentzer_f)
Image from Fabian Mentzer (@mentzer_f)
76
Fabian Mentzer retweeted
cg (@InjarapuC) profile picture
cg@InjarapuC20 Nov 2025
Replying to @mentzer_f
@mentzer_f
Image from cg (@InjarapuC)
1
2
243
Check out these amazing examples from the 🐐 AS himself ⬇️⬇️
Abhishek Sinha (@a7b2_3) profile pictureAbhishek Sinha@a7b2_320 Nov 2025
We are excited to release Nano Banana Pro today! We have been working hard for the past few months trying to improve the model and now can’t wait for everyone to play with it! The model should feel smarter for both t2i and editing and also comes with new capabilities.. (1/n)
Image from Abhishek Sinha (@a7b2_3)
Image from Abhishek Sinha (@a7b2_3)
1
4
567
None of these cool things would be happening without @phillip_lippe What Phillip pulled off, especially on thinking and image generation, is beyond impressive 🫡
Phillip Lippe (@phillip_lippe) profile picturePhillip Lippe@phillip_lippe20 Nov 2025
Since I joined GDM in January, we've been working on making our image generation models smarter. From 2.0 Flash, Imagen 4, Nano Banana, and now Nano Banana Pro, it's been quite a ride with immense progress. And there's no sign of slowing down 🚀🍌
3
1
109
18,175
Very proud to have contributed to this amazing model!!! 🍌🍌 →→ check it out → →deepmind.google/models/gemin…
Image from Fabian Mentzer (@mentzer_f)
Oriol Vinyals (@OriolVinyalsML) profile pictureOriol Vinyals
@OriolVinyalsML20 Nov 2025
Replying to @ErikaCoaches
Confirmed
Image from Oriol Vinyals (@OriolVinyalsML)
4
1
32
3,212
Replying to @ErikaCoaches
Confirmed
Image from Oriol Vinyals (@OriolVinyalsML)
5
5
4
219
28,229
Fabian Mentzer retweeted
Angel 🌼 (@Angaisb_) profile picture
Angel 🌼
@Angaisb_20 Nov 2025
Nano Banana Pro NAILED my burguer test It's the first model to do this perfectly
Image from Angel 🌼 (@Angaisb_)
79
34
12
2,063
189,613
Fabian Mentzer retweeted
Pietro Schirano (@skirano) profile picture
Pietro Schirano
@skirano20 Nov 2025
Nano Banana Pro is wild. Here’s my favorite use case so far: take papers or really long articles and turn them into a detailed whiteboard photo. It’s basically the greatest compression algorithm in human history.
141
594
105
6,691
1,340,748
🍌🍌 👀
Robert Riachi (@robertriachi) profile pictureRobert Riachi
@robertriachi19 Nov 2025
Currently in Japan 🍌 🍌
Image from Robert Riachi (@robertriachi)
6
678
🍌🍌
2
2
1
16
1,776
🤯🤯🤯
Matt McGill (@MattMcGill_) profile pictureMatt McGill@MattMcGill_5 Aug 2025
One nice thing you can do with an interactive world model, look down and see your footwear ... and if the model understands what puddles are. Genie 3 creation.
2
437
Fabian Mentzer retweeted
Jakob Bauer (@jkbr_ai) profile picture
Jakob Bauer@jkbr_ai6 Aug 2025
Yesterday we announced Genie 3. One feature of the model that's especially fun to play with is starting worlds from existing videos. Here's a drone shot generated by Veo 3, with me taking control mid-flight.
Google DeepMind (@GoogleDeepMind) profile pictureGoogle DeepMind
@GoogleDeepMind5 Aug 2025
What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵
92
213
107
2,457
703,727
Incredible evolution of "Neural Video Games": from GQN (2018) to Genie3 (2025). The future is exciting! deepmind.google/discover/blo…
54
318
37
2,946
260,471
Dope image gen models ⬇️
Aäron van den Oord (@avdnoord) profile pictureAäron van den Oord
@avdnoord25 Jul 2025
We updated our Imagen 4 models and Ultra is tied for #1 on the lmarena leaderboard! The models are available in Google AI Studio and the Gemini API - try them out and let us know what you think.
3
327
Fabian Mentzer retweeted
Lisan al Gaib (@scaling01) profile picture
Lisan al Gaib
@scaling0120 May 2025
Google's new video generator Veo 3 looks insane
Lisan al Gaib (@scaling01) profile pictureLisan al Gaib
@scaling0120 May 2025
Veo 3
Image from Lisan al Gaib (@scaling01)
16
103
29
1,654
144,907
Fabian Mentzer retweeted
testtm (@test_tm7873) profile picture
testtm
@test_tm78736 May 2025
Gemini-2.5-Pro-preview-05-06 isn't only the best model for coding. its the best model for everything! across all tasks!
Image from testtm (@test_tm7873)
35
111
33
1,403
224,106
Fabian Mentzer retweeted
JB Alayrac (@jalayrac) profile picture
JB Alayrac@jalayrac6 May 2025
Gemini 2.5 Pro latest update is amazing at code! What I find even more amazing is combining this coding skill with Gemini's state-of-the-art MM video understanding capability 🎞️, here transcribing a YouTube video ✈️ into a p5.js animation. PS: guess which video is this :)
Arena.ai (@arena) profile pictureArena.ai
@arena6 May 2025
🚨Breaking: @GoogleDeepMind’s latest Gemini-2.5-Pro is now ranked #1 across all LMArena leaderboards 🏆 Highlights: - #1 in all text arenas (Coding, Style Control, Creative Writing, etc) - #1 on the Vision leaderboard with a ~70 pts lead! - #1 on WebDev Arena, surpassing Claude for the first time This is the first-ever sweep across text, vision, and WebDev by any model!🥇 Huge congrats to @GoogleDeepMind on this incredible breakthrough!
Image from Arena.ai (@arena)
2
21
1
132
16,240
Load more