Alexander Chen's banner

Alexander Chen

@alexanderchen • 13,353 subscribers

Creative Director at Google Creative Lab. Exploring multimodal AI. Opinions are my own.

Shorts

Gemini Omni 🕶️ prompt in 🧵

Gemini Omni 🕶️ prompt in 🧵

160,718 просмотров

Omnizoom 🍜 diving into a photo with Gemini Omni

Omnizoom 🍜 diving into a photo with Gemini Omni

64,889 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Marble Run 🟢🔊 Made with Veo 3 in Google Gemini.

Marble Run 🟢🔊 Made with Veo 3 in Google Gemini.

150,209 просмотров • 1 год назад

Banana World🍌 Create your own isometric worlds. Made w/ Gemini 2.5 Flash (nano banana) Sound on 🔊 Link in🧵

Banana World🍌 Create your own isometric worlds. Made w/ Gemini 2.5 Flash (nano banana) Sound on 🔊 Link in🧵

113,009 просмотров • 10 месяцев назад

Gemini 2.5 Pro codes a TV. 📺 With just one prompt, it came up with its own ideas for 10 channels and coded each one! Link + details in 🧵

Gemini 2.5 Pro codes a TV. 📺 With just one prompt, it came up with its own ideas for 10 channels and coded each one! Link + details in 🧵

130,916 просмотров • 1 год назад

You as agent: super cool Gemini demo by Filip Havlena👤🍎🖥️ We've been experimenting with agentic interfaces at Creative Lab and this one was so fun: he turned himself into a 3d agent with spatial awareness + reasoning loop + tools (docs/emails with Google Workspace CLI). Made in Three.js. Real-time screencap ▶️

You as agent: super cool Gemini demo by Filip Havlena👤🍎🖥️ We've been experimenting with agentic interfaces at Creative Lab and this one was so fun: he turned himself into a 3d agent with spatial awareness + reasoning loop + tools (docs/emails with Google Workspace CLI). Made in Three.js. Real-time screencap ▶️

39,434 просмотров • 4 месяцев назад

Banana Scan: Capture things in your physical world and visualize them in new ways. Built with Gemini 2.5 / Nano Banana.🍌📷 Code/link + details in 🧵

Banana Scan: Capture things in your physical world and visualize them in new ways. Built with Gemini 2.5 / Nano Banana.🍌📷 Code/link + details in 🧵

70,743 просмотров • 10 месяцев назад

Veo Explainers: Talking Objects🎈🎺👀 Dan Motzenbecker + I are experimenting with Veo 3 to explain concepts. Here are some of our favorite tests so far! Used Gemini to co-think and write prompts. Veo generated all the dialogue. Sound on 🔊 Prompts in 🧵

Veo Explainers: Talking Objects🎈🎺👀 Dan Motzenbecker + I are experimenting with Veo 3 to explain concepts. Here are some of our favorite tests so far! Used Gemini to co-think and write prompts. Veo generated all the dialogue. Sound on 🔊 Prompts in 🧵

69,898 просмотров • 1 год назад

TypeBeat 🔤🥁 Brought my text drum machine to phone with Gemini in Google Antigravity + pretext by Cheng Lou. Sound on 🔊 You can now share your beats:

TypeBeat 🔤🥁 Brought my text drum machine to phone with Gemini in Google Antigravity + pretext by Cheng Lou. Sound on 🔊 You can now share your beats:

22,581 просмотров • 3 месяцев назад

Jello shader 🟦 Gemini 3 in one shot. Prompt + code/link in 🧵

Jello shader 🟦 Gemini 3 in one shot. Prompt + code/link in 🧵

41,546 просмотров • 8 месяцев назад

Conceptual alphabet 🔤🧠 I asked Gemini 3 to think of 26 concepts and code an abstract illustration of each one. It returned this in one shot. Prompt + link in 🧵

Conceptual alphabet 🔤🧠 I asked Gemini 3 to think of 26 concepts and code an abstract illustration of each one. It returned this in one shot. Prompt + link in 🧵

38,495 просмотров • 8 месяцев назад

Having fun playing with new native audio capabilities in Gemini 1.5 Pro! ♊ Here’s a demo using audio from the #GoogleIO keynote with examples you can try: transcription, word-level timecodes, and searching audio by drawing. (🔊Video has sound)

Having fun playing with new native audio capabilities in Gemini 1.5 Pro! ♊ Here’s a demo using audio from the #GoogleIO keynote with examples you can try: transcription, word-level timecodes, and searching audio by drawing. (🔊Video has sound)

77,097 просмотров • 2 лет назад

Beatboxing blobfish. 🔊 Made with Veo 3 in Google Gemini

Beatboxing blobfish. 🔊 Made with Veo 3 in Google Gemini

47,235 просмотров • 1 год назад

Bear + bird 🐻🔊 Made with Veo 3 in Google Gemini App

Bear + bird 🐻🔊 Made with Veo 3 in Google Gemini App

41,425 просмотров • 1 год назад

TypeBeat 🔤🥁 I made a drum machine entirely out of text. Made with pretext by Cheng Lou + Gemini in Google Antigravity. Sound on 🔊

TypeBeat 🔤🥁 I made a drum machine entirely out of text. Made with pretext by Cheng Lou + Gemini in Google Antigravity. Sound on 🔊

15,239 просмотров • 3 месяцев назад

"Can you form a snowman?" A simple canvas for human + AI co-manipulation. 🔴🟢🔵💬 Made using Gemini 2.0 w/ Kyle Phillips. Video has sound 🔊. Prompt + thoughts in 🧵

"Can you form a snowman?" A simple canvas for human + AI co-manipulation. 🔴🟢🔵💬 Made using Gemini 2.0 w/ Kyle Phillips. Video has sound 🔊. Prompt + thoughts in 🧵

42,051 просмотров • 1 год назад

EmojiDrop. 🐱🎵 Just vibe-coded this with Gemini 2.5! It's something I've dreamed of making ever since I first saw the "Pipe Dream" musical physics video when I was a kid. Video has sound 🔊

EmojiDrop. 🐱🎵 Just vibe-coded this with Gemini 2.5! It's something I've dreamed of making ever since I first saw the "Pipe Dream" musical physics video when I was a kid. Video has sound 🔊

27,995 просмотров • 1 год назад

Visualizing Gemini intelligence with things in my life 🔊🧵

Visualizing Gemini intelligence with things in my life 🔊🧵

12,777 просмотров • 5 месяцев назад

Make a few more of these ... Make a LOT more of these ... Gemini 2.0 native image output is enabling a new way to prompt: instructing with image and text together. Subtle shifts in how I draw change how Gemini interprets the same text prompt.

Make a few more of these ... Make a LOT more of these ... Gemini 2.0 native image output is enabling a new way to prompt: instructing with image and text together. Subtle shifts in how I draw change how Gemini interprets the same text prompt.

23,601 просмотров • 1 год назад

Want to build on the new Google Multimodal Live API with Gemini 2.0? My teammates Kyle Phillips + @tinaz0ne + Trudy Painter made open-source starter demos! 🧵 Here's a React.js boilerplate console you can start with. Code here:

Want to build on the new Google Multimodal Live API with Gemini 2.0? My teammates Kyle Phillips + @tinaz0ne + Trudy Painter made open-source starter demos! 🧵 Here's a React.js boilerplate console you can start with. Code here:

25,037 просмотров • 1 год назад