Fabian Mentzer
@mentzer_f
Followers
2K
Following
2K
Statuses
367
Senior Research Scientist at Google DeepMind during the day, modular synth guy at night: https://t.co/Ea84aix9Pm
Zürich, Schweiz
Joined April 2018
📢📢 Hyped to share what I've been working on this year -- here is a quick demo of some truely native image outputs in Gemini 2.0 🦋 Here the model generates images in-between the text it outputs, and responds to some follow up editing requests 🚀🚀
2
6
52
RT @lmarena_ai: Breaking news from Text-to-Image Arena! 🖼️✨ @GoogleDeepMind’s Imagen 3 debuts at #1, surpassing Recraft-v3 with a remarkab…
0
135
0
RT @JeffDean: Introducing Gemini 2.0 Flash Thinking, an experimental model that explicitly shows its thoughts. Built on 2.0 Flash’s speed…
0
494
0
RT @NoamShazeer: We’ve been *thinking* about how to improve model reasoning and explainability Introducing Gemini 2.0 Flash Thinking, an e…
0
307
0
RT @bindureddy: Gotta say Gemini 2.0 is a way bigger launch that whatever OpenAI has announced so far Also love that Google made the API…
0
70
0
RT @robertriachi: A simple yet powerful example of the new Gemini 2.0 Flash's native multimodal input + output. Precise conversational edit…
0
47
0
This is soooo cool ✨✨ We observed it a few times when building the model, where the understanding capabilities of Gemini 2.0 lead it to self correct in generation. #agi
0
1
7
Shout out to the demo chad, @alexanderchen :) Really great to see how this emerged
"Open the box ..." This was a really fun demo to make. My cat makes a cameo. 🐱 My favorite prompt was asking the model to open the box at the end, inspired by conversations with @tokumin + @ameliovr
0
0
1
We have been consistently amazed with what we get out of our model 😍😍 nice demo
Gemini 2.0 Flash (native image out) helps me convert a sketch to an image.
1
0
3
Added my lovely coffee setup to our new Gemini 2.0 with native interleaved Image Out :) It made a mess 😅😅 #europiccola
1
1
15
super happy to be part of this :)
Gemini 2.0 Flash has native image outputs! Congrats to the awesome team that built it. I find the example at 1:15 super cool: to change the car's color and add beach gear, the model generates two images step-by-step using visual chain of thought.
1
0
38
RT @OriolVinyalsML: Gemini 2.0 Flash ⚡️ has arrived! 2.0 Flash > 1.5 Pro (again!) 📈 Interacts with a browser 🤖 Native image generation 🖼️…
0
58
0
RT @testingcatalog: BREAKING 🚨: Gemini Flash 2.0 Experimental is rolling out to some users already! Looks like Google is up to something fo…
0
29
0
RT @lmarena_ai: Massive News from Chatbot Arena🔥 @GoogleDeepMind's latest Gemini (Exp 1114), tested with 6K+ community votes over the past…
0
311
0
RT @lmsysorg: Exciting News from Chatbot Arena! @GoogleDeepMind's new Gemini 1.5 Pro (Experimental 0801) has been tested in Arena for the…
0
412
0
RT @lucastheis: What does it mean for an image, video, or text to be 𝑟𝑒𝑎𝑙𝑖𝑠𝑡𝑖𝑐? Despite how far we've come in 𝑔𝑒𝑛𝑒𝑟𝑎𝑡𝑖𝑛𝑔 realistic data, 𝑞…
0
21
0
RT @hu_yifei: I hate to acknowledge this, but Gemini 1.5 Flash is better than llama-3-70b on long context tasks. It's way faster than my lo…
0
30
0
RT @zacharynado: "i try not to think about competitors too much" interesting how all your launches are timed with ours then
0
390
0