Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

1/ Introducing high precision masked editing. No bleeding. Highly targeted AI based image editing to give you more control. Here's an end-to-end workflow in 30 seconds:

358,788 Aufrufe • vor 3 Jahren •via X (Twitter)

11 Kommentare

Profilbild von Suhail
Suhailvor 3 Jahren

2/ Make entirely new scenes by layering your edits on top of each other: "Make it snowy", "Change the door to brown", "Golden hour", "Add a bit of snow to the roof", "Add a cute bunny in the foreground"

Profilbild von Suhail
Suhailvor 3 Jahren

3/ Modify memes: "Add a bathrobe"

Profilbild von Suhail
Suhailvor 3 Jahren

4/ Bigger edits that only target the hair: "make her hair curly with natural color"

Profilbild von Suhail
Suhailvor 3 Jahren

5/ You don't have to be exact in your masked edits: "make it red lava, black rocks"

Profilbild von Suhail
Suhailvor 3 Jahren

6/ Use it at

Profilbild von Suhail
Suhailvor 3 Jahren

7/ One shot AI avatar using masks:

Profilbild von GrepMed
GrepMedvor 3 Jahren

"Create a badly receding hairline" 🤣

Profilbild von Suhail
Suhailvor 3 Jahren

Oh my lord

Profilbild von Tim O'Shea
Tim O'Sheavor 3 Jahren

I see why you burnt the boat Congrats, playground is fantastic

Profilbild von Adham
Adhamvor 3 Jahren

seems like instruct-pix-2-pix with masked attention control (from google's prompt-to-prompt) or inpainting task finetuning like runwayml with instruction training. Very cool @Suhail

Profilbild von Suhail
Suhailvor 3 Jahren

def instructpix2pix :)

Ähnliche Videos

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

71,228 Aufrufe • vor 1 Jahr