Sensitive content

This media may contain sensitive content.

Loading video...

Video Failed to Load

Go Home

Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold paper page:

_akhaliq's profile picture

AK

395,973 subscribers

3,396,886 views • 3 years ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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.
1:02

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

1,101,148 views • 3 years ago

InstantDrag Improving Interactivity in Drag-based Image Editing discuss: Drag-based image editing has recently gained popularity for its interactivity and precision. However, despite the ability of text-to-image models to generate samples within a second, drag editing still lags behind due to the challenge of accurately reflecting user interaction while maintaining image content. Some existing approaches rely on computationally intensive per-image optimization or intricate guidance-based methods, requiring additional inputs such as masks for movable regions and text prompts, thereby compromising the interactivity of the editing process. We introduce InstantDrag, an optimization-free pipeline that enhances interactivity and speed, requiring only an image and a drag instruction as input. InstantDrag consists of two carefully designed networks: a drag-conditioned optical flow generator (FlowGen) and an optical flow-conditioned diffusion model (FlowDiffusion). InstantDrag learns motion dynamics for drag-based image editing in real-world video datasets by decomposing the task into motion generation and motion-conditioned image generation. We demonstrate InstantDrag's capability to perform fast, photo-realistic edits without masks or text prompts through experiments on facial video datasets and general scenes. These results highlight the efficiency of our approach in handling drag-based image editing, making it a promising solution for interactive, real-time applications.
0:46

InstantDrag Improving Interactivity in Drag-based Image Editing discuss: Drag-based image editing has recently gained popularity for its interactivity and precision. However, despite the ability of text-to-image models to generate samples within a second, drag editing still lags behind due to the challenge of accurately reflecting user interaction while maintaining image content. Some existing approaches rely on computationally intensive per-image optimization or intricate guidance-based methods, requiring additional inputs such as masks for movable regions and text prompts, thereby compromising the interactivity of the editing process. We introduce InstantDrag, an optimization-free pipeline that enhances interactivity and speed, requiring only an image and a drag instruction as input. InstantDrag consists of two carefully designed networks: a drag-conditioned optical flow generator (FlowGen) and an optical flow-conditioned diffusion model (FlowDiffusion). InstantDrag learns motion dynamics for drag-based image editing in real-world video datasets by decomposing the task into motion generation and motion-conditioned image generation. We demonstrate InstantDrag's capability to perform fast, photo-realistic edits without masks or text prompts through experiments on facial video datasets and general scenes. These results highlight the efficiency of our approach in handling drag-based image editing, making it a promising solution for interactive, real-time applications.

AK

71,201 views • 1 year ago

📢📢 "Proteina: Scaling Flow-based Protein Structure Generative Models" #ICLR2025 (Oral Presentation) 🔥 Project page: 📜 Paper: 🛠️ Code and weights: 🧵Details in thread... (1/n)
0:20

📢📢 "Proteina: Scaling Flow-based Protein Structure Generative Models" #ICLR2025 (Oral Presentation) 🔥 Project page: 📜 Paper: 🛠️ Code and weights: 🧵Details in thread... (1/n)

Karsten Kreis

42,365 views • 1 year ago

📢A new learning-based approach to SfM: #ACEZero No img-to-img matching, optimises image-to-scene correspondences directly. Needs no pose priors. Works on unordered image sets. Efficiently handles thousands of images. Paper: Page:
0:20

📢A new learning-based approach to SfM: #ACEZero No img-to-img matching, optimises image-to-scene correspondences directly. Needs no pose priors. Works on unordered image sets. Efficiently handles thousands of images. Paper: Page:

Eric Brachmann

71,101 views • 2 years ago

DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects abs: paper page:
0:27

DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects abs: paper page:

AK

17,532 views • 3 years ago

I'm excited to share our new work, VistaDream, which generates a 3D Gaussian field from a single-view image. The codes have already been released. Project page: (with interactive demos) Code: Paper:
0:27

I'm excited to share our new work, VistaDream, which generates a 3D Gaussian field from a single-view image. The codes have already been released. Project page: (with interactive demos) Code: Paper:

Yuan Liu

79,592 views • 1 year ago

Check out our new paper that turns a (single image) => (interactive dynamic scene)! I’ve had so much fun playing around with this demo. Try it out yourself on the website:
0:22

Check out our new paper that turns a (single image) => (interactive dynamic scene)! I’ve had so much fun playing around with this demo. Try it out yourself on the website:

Aleksander Holynski

301,713 views • 2 years ago

Generative World Renderer paper:
1:27

Generative World Renderer paper:

AK

14,238 views • 2 months ago

Google presents MobileDiffusion Subsecond Text-to-Image Generation on Mobile Devices paper page: MobileDiffusion achieves a remarkable sub-second inference speed for generating a 512 × 512 image on mobile devices, establishing a new state of the art.
0:20

Google presents MobileDiffusion Subsecond Text-to-Image Generation on Mobile Devices paper page: MobileDiffusion achieves a remarkable sub-second inference speed for generating a 512 × 512 image on mobile devices, establishing a new state of the art.

AK

150,538 views • 2 years ago

AR + AI effect We made an AR filter that interacts with your hands. I inpainted the image using Photoshop's new AI feature, and Sergei Galkin turned it into an interactive filter Made for @adobe using Photoshop (beta) Generative Fill #AdobeFirefly #AdobePartner
0:25

AR + AI effect We made an AR filter that interacts with your hands. I inpainted the image using Photoshop's new AI feature, and Sergei Galkin turned it into an interactive filter Made for @adobe using Photoshop (beta) Generative Fill #AdobeFirefly #AdobePartner

Karen X. Cheng

864,165 views • 3 years ago

Introducing Universal Simulator (UniSim), an interactive simulator of the real world. Interactive website: Paper:
1:57

Introducing Universal Simulator (UniSim), an interactive simulator of the real world. Interactive website: Paper:

Sherry Yang

440,007 views • 2 years ago

🏗️ Build #3D scenes from a single input view based on the latest #NVIDIAResearch paper accepted at #ICCV2023. 👀 This 3D-aware #generativeAI model can build diverse and plausible views. research paper: project page:
0:24

🏗️ Build #3D scenes from a single input view based on the latest #NVIDIAResearch paper accepted at #ICCV2023. 👀 This 3D-aware #generativeAI model can build diverse and plausible views. research paper: project page:

NVIDIA AI Developer

113,873 views • 2 years ago

build an agent that speaks your UI. your charts. your forms. your seat maps. multi-turn, streaming, interactive. introducing tambo 1.0, the open-source generative UI toolkit for react.
1:11

build an agent that speaks your UI. your charts. your forms. your seat maps. multi-turn, streaming, interactive. introducing tambo 1.0, the open-source generative UI toolkit for react.

Michael Magán

261,138 views • 4 months ago

Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis
1:07

Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis

AK

28,101 views • 11 months ago

Check out our new paper that turns (text, sparse images, videos) => (dynamic 3D scenes)! I can't get over how cool the interactive demo is. Try it out for yourself on the project page:
0:46

Check out our new paper that turns (text, sparse images, videos) => (dynamic 3D scenes)! I can't get over how cool the interactive demo is. Try it out for yourself on the project page:

Aleksander Holynski

37,142 views • 1 year ago

generative series of interactive, playable artworks Mitchell F Chan on July 17 with OpenSea x Art Blocks
0:20

generative series of interactive, playable artworks Mitchell F Chan on July 17 with OpenSea x Art Blocks

Dr Mimi Nguyen واحد 🥯

10,643 views • 11 months ago

Generative image to scene is getting incredibly good. This is pure 3D without v2v generated from the image in the reply ...
0:23

Generative image to scene is getting incredibly good. This is pure 3D without v2v generated from the image in the reply ...

martin_casado

57,089 views • 9 months ago

iOS 19 TabView concept, live and interactive in SwiftUI! based on the renders from fpt.
0:38

iOS 19 TabView concept, live and interactive in SwiftUI! based on the renders from fpt.

xezrunner

76,512 views • 1 year ago

Introducing the Anemoia Device, a scent-memory machine that uses generative AI to distill photographs into bespoke fragrances. ✺ Register your interest: Guided by language models, a dial-based interface, and a custom olfactory formulation system, each image becomes a singular scent composition — a multisensory memory that evokes anemoia: nostalgia for a moment you never lived. ✤ Read our NeurIPS Paper: ✶ Created at MIT MIT Media Lab:
0:52

Introducing the Anemoia Device, a scent-memory machine that uses generative AI to distill photographs into bespoke fragrances. ✺ Register your interest: Guided by language models, a dial-based interface, and a custom olfactory formulation system, each image becomes a singular scent composition — a multisensory memory that evokes anemoia: nostalgia for a moment you never lived. ✤ Read our NeurIPS Paper: ✶ Created at MIT MIT Media Lab:

Cyrus

18,277 views • 6 months ago