Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

This is wild: DraGAN: Interactive point-based manipulation of images using AI. This gives you controllability of the pose, shape, expression, and layout of the objects in your images.

AI Breakfast

235,831 subscribers

1,101,134 views • 3 years ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

AI Breakfast3 years ago

DraGAN's project page:

AI Breakfast3 years ago

For the endlessly curious minds, we write a weekly newsletter on the latest AI research, tools, and developments. Join 35,000 readers here ↓

Tom Blake3 years ago

@SmokeAwayyy This is gonna be sick!

AI Breakfast3 years ago

@SmokeAwayyy Expecting Adobe to swoop in and acquire

sercanov3 years ago

Welcome to post-truth era

Jeff3 years ago

This is like Photoshop Liquify and Puppet-Warp tools, with content aware fill, and AI image generation all rolled into one. And in six months it will probably be perfected, at the current pace of things.

Michael Kelczewski3 years ago

I cannot wait to see this employed for real estate marketing..

seefer3 years ago

@SmokeAwayyy Ahh so this is how DMT works

Alts Anonymous 🧐 🆙3 years ago

wow....

Toorkhan3 years ago

@SmokeAwayyy This is outstanding.

Related Videos

The new RFK files were released, including autopsy images and diagrams of the shooting. This case is wild.

The new RFK files were released, including autopsy images and diagrams of the shooting. This case is wild.

Wally Rashid

40,153 views • 1 year ago

The GBU-39 – a visual guide to Israel’s “weapon of choice” in Gaza. This is the first in a series of articles using interactive 3D models alongside images from the OSMP archive to help researchers understand and identify widely-used munitions 1/10

The GBU-39 – a visual guide to Israel’s “weapon of choice” in Gaza. This is the first in a series of articles using interactive 3D models alongside images from the OSMP archive to help researchers understand and identify widely-used munitions 1/10

Open Source Munitions Portal

67,508 views • 1 year ago

We talked to Ritvik Singh about how you can train sim-to-real dexterous manipulation policies using NVIDIA Isaac. This robot is grasping objects using pure RGB stereo: take in images from a camera pair and predict what to do, all without training in the real world.

We talked to Ritvik Singh about how you can train sim-to-real dexterous manipulation policies using NVIDIA Isaac. This robot is grasping objects using pure RGB stereo: take in images from a camera pair and predict what to do, all without training in the real world.

Chris Paxton

20,042 views • 9 months ago

This AI agent lets you edit Nano Banana Pro images with high precision. You just need to point to the exact detail you want to change (clothes, text, objects), mark the area, and describe the changes.

This AI agent lets you edit Nano Banana Pro images with high precision. You just need to point to the exact detail you want to change (clothes, text, objects), mark the area, and describe the changes.

Alvaro Cintas

138,007 views • 6 months ago

Introducing SAM 3D, the newest addition to the SAM collection, bringing common sense 3D understanding of everyday images. SAM 3D includes two models: 🛋️ SAM 3D Objects for object and scene reconstruction 🧑‍🤝‍🧑 SAM 3D Body for human pose and shape estimation Both models achieve state-of-the-art performance transforming static 2D images into vivid, accurate reconstructions. 🔗 Learn more:

Introducing SAM 3D, the newest addition to the SAM collection, bringing common sense 3D understanding of everyday images. SAM 3D includes two models: 🛋️ SAM 3D Objects for object and scene reconstruction 🧑‍🤝‍🧑 SAM 3D Body for human pose and shape estimation Both models achieve state-of-the-art performance transforming static 2D images into vivid, accurate reconstructions. 🔗 Learn more:

AI at Meta

857,003 views • 6 months ago

Dream Machine from Luma AI is now available on Poe! Generate videos, animate images, and build your own custom video bots using this state-of-the-art generative video model. (1/2)

Dream Machine from Luma AI is now available on Poe! Generate videos, animate images, and build your own custom video bots using this state-of-the-art generative video model. (1/2)

Poe

24,455 views • 1 year ago

This is wild! 🤯 This AI can create images that can sing, based on audio input. Here's how you can do it too: (I made the 'Robin Delta' song, haha!)👇

This is wild! 🤯 This AI can create images that can sing, based on audio input. Here's how you can do it too: (I made the 'Robin Delta' song, haha!)👇

Robin Delta

22,984 views • 2 years ago

This video of a pulmonologist using AI to read a patient's images is generating a lot of controversy. But I'd rather have AI read my scans than a random human doctor, at this point? AI is never tired or distracted or biased by its last case...

This video of a pulmonologist using AI to read a patient's images is generating a lot of controversy. But I'd rather have AI read my scans than a random human doctor, at this point? AI is never tired or distracted or biased by its last case...

Justine Moore

46,520 views • 1 year ago

This is the third in my series of dancing videos animated using #VEO3. Images made using #Midjourney. I am so impressed with Google VEO3 and the animation outputs. Song made with @SunoMusic #ai #aiart #aivideo #aimusic #suno #aiimages #aiartwork

This is the third in my series of dancing videos animated using #VEO3. Images made using #Midjourney. I am so impressed with Google VEO3 and the animation outputs. Song made with @SunoMusic #ai #aiart #aivideo #aimusic #suno #aiimages #aiartwork

Kelly Boesch🏳️‍🌈

36,068 views • 7 months ago

What happens when you feed an AI images of every building in the United States? The model can take any blurry image and tell you exactly where that image was taken. GeoSpy AI (now Raven) is wild

What happens when you feed an AI images of every building in the United States? The model can take any blurry image and tell you exactly where that image was taken. GeoSpy AI (now Raven) is wild

Daniel Heinen

144,947 views • 25 days ago

Visualization is a powerful motivator. Here a teacher inspires students by using AI-generated images of their future selves based on their ambitions.

Visualization is a powerful motivator. Here a teacher inspires students by using AI-generated images of their future selves based on their ambitions.

Gurwinder

145,531 views • 1 year ago

You can't trust what you see online anymore. This AI avatar is going viral because the images are almost indistinguishable from real photos. The images on the left were generated using a face and style Flux fine-tuning and brought to life with Kling AI

Halim Alrasihi

107,556 views • 1 year ago

This Flux pricing is insane! You can actually save 72% on your AI Image application . If you're using Flux , you can start using Nebius AI Studio now. Flux Dev Replicate: $25/1K images FAL: $25/1K images Nebius AI Studio: $7/1K images Nebius Token Factory giving $25 for free 👇

This Flux pricing is insane! You can actually save 72% on your AI Image application . If you're using Flux , you can start using Nebius AI Studio now. Flux Dev Replicate: $25/1K images FAL: $25/1K images Nebius AI Studio: $7/1K images Nebius Token Factory giving $25 for free 👇

AshutoshShrivastava

16,379 views • 1 year ago

new Krea Edit. this tool ads a new layer of controllability for editing images with AI. change specific regions, render new perspectives, play with lighting, color palettes, and more – try it now!

new Krea Edit. this tool ads a new layer of controllability for editing images with AI. change specific regions, render new perspectives, play with lighting, color palettes, and more – try it now!

Krea

246,083 views • 3 months ago

Using Icons as images instead. You can be creative with this. Go wild.

Using Icons as images instead. You can be creative with this. Go wild.

Atom the UiUx Designer

62,547 views • 3 months ago

You can basically generate your own custom visual stories using Gemini with just a single prompt 'This is a fictional movie set in a fantasy world similar to The Lord of the Rings. Use this as a starting point and imagine the next sequence of scenes. Create a series of separate images, each depicting a distinct moment in the story, presented in a sequential order like a storyboard. Include quotes for each image to narrate the events happening within it. Ensure the flow between images is consistent and logical, with each one styled like a cinematic movie shot that advances the narrative. Maintain the same format and visual style across all images to keep them cohesive'

You can basically generate your own custom visual stories using Gemini with just a single prompt 'This is a fictional movie set in a fantasy world similar to The Lord of the Rings. Use this as a starting point and imagine the next sequence of scenes. Create a series of separate images, each depicting a distinct moment in the story, presented in a sequential order like a storyboard. Include quotes for each image to narrate the events happening within it. Ensure the flow between images is consistent and logical, with each one styled like a cinematic movie shot that advances the narrative. Maintain the same format and visual style across all images to keep them cohesive'

Cristian Peñas ░░░░░░░░

38,500 views • 1 year ago

We are thrilled to announce a new feature on - Image as Pose! 🎉 This allows you to upload an image of a person as an initial image, and generate other images of people in the same pose. Get the same character in multiple poses and angles consistently🔥

We are thrilled to announce a new feature on - Image as Pose! 🎉 This allows you to upload an image of a person as an initial image, and generate other images of people in the same pose. Get the same character in multiple poses and angles consistently🔥

Leonardo.Ai

391,497 views • 3 years ago

Introducing Objects, the last step to your workflow 🔥 Add the same item across multiple images, and combine it with the rest of the tools in Freepik AI Suite Step-by-step tutorial below 🧵👇

Introducing Objects, the last step to your workflow 🔥 Add the same item across multiple images, and combine it with the rest of the tools in Freepik AI Suite Step-by-step tutorial below 🧵👇

Freepik

53,759 views • 1 year ago

So, what the heck is is this "photogrammetry" thing NVIDIA is supercharging with AI? TL;DR photogrammetry is the art & science of measuring stuff in the real world using images and other sensors (e.g. LiDAR). Here's a 60 second primer:

So, what the heck is is this "photogrammetry" thing NVIDIA is supercharging with AI? TL;DR photogrammetry is the art & science of measuring stuff in the real world using images and other sensors (e.g. LiDAR). Here's a 60 second primer:

Bilawal Sidhu

28,466 views • 3 years ago