Post

How to get URL link on X (Twitter) App

On the Twitter thread, click on or icon on the bottom
Click again on or Share Via icon
Click on Copy Link to Tweet
Paste it above and click "Unroll Thread"!
More info at Twitter Help

Cyril Diagne

Jun 17, 2022 • 5 tweets • 6 min read • Read on X

@clipdropapp

Today we're launching @clipdropapp Image Upscaler on @ProductHunt, the easiest way to upscale your images 2x or 4x with AI.

⚡️ Upscale, denoise and enhance in 1 click
🔍 Sharpen blurry edges
✨ Remove JPEG compression artifacts
🔌 Public API

→ producthunt.com/posts/clipdrop…

@clipdropapp

@clipdropapp @ProductHunt Once again, our team has used a couple of our favorite tricks to push the quality and speed of 2x and 4x image upscaling models.

It's an ongoing effort, but the result is already quite spectacular 🤓

@clipdropapp

@clipdropapp @ProductHunt We've been using it a lot lately to improve the images produced by image diffusion models such as #dalle2 #minidalle #imagen or more recently CogView2 - cc @hardmaru

Here's an example of @shashj amazing Mughal helicopters

@clipdropapp

@clipdropapp @ProductHunt @hardmaru @shashj The community has already built incredible apps with our background removal and inpainting APIs.

So we're also making Image Upscaler available to all developers with an easy-to-use public API: clipdrop.co/apis/docs/supe…

Looking forward to seeing what you can make with it!

@clipdropapp

@clipdropapp @ProductHunt @hardmaru @shashj As usual, your loud support helps our small team build these public tools. In good Web2 fashion, your likes, RTs & upvotes are really appreciated 🙌

producthunt.com/posts/clipdrop…

And we have a lot more coming over the next few weeks 💡

• • •

Missing some Tweet in this thread? You can try to force a refresh

This Thread may be Removed Anytime!

Twitter may remove this content at anytime! Save it as PDF for later use!

More from @cyrildiagne

Cyril Diagne

@cyrildiagne

Jan 14

Stable Diffusion 100% in the browser with running at < 1s per image ⚡️

Thanks to SD Turbo by @AxSauer & al @StabilityAI and diffusers.js on webGPU by @daken_

Demo:

More info in ↓🧵 cyrildiagne.com/lab/sdturbo-we…

It’s currently only compatible Chrome/Edge v120+ (webgpu can be enabled with an experimental flag on Safari TP & Firefox 122+)

You need to activate both experimental WebAssembly flags to run the latest @onnxruntime

You also need a solid internet connection, because it will download a couple of big files:

- unet: 1.73gb
- text encoder: 682mb
- taesd: 9mb

The files downloaded directly from @huggingface: huggingface.co/cyrildiagne/sd…

Read 9 tweets

Cyril Diagne

@cyrildiagne

Dec 19, 2021

This weekend I played with 3 things I ♥: machine learning, #generativeart, and the web.

Here's a small neural network running entirely in a #webgl GLSL shader that hallucinates thousands of new handwritten digits in real-time.

How so? 👇🧵

@hardmaru

I first learned about CPPNs in "Generating Large Images from Latent Vectors" by @hardmaru back in 2016 (!).

At the time, GANs were stuck at 256px and I was amazed to learn about these fast, high resolution, generators.

blog.otoro.net/2016/04/01/gen…

@hardmaru

The fact that they operate on pixel coordinates makes them particularly good candidates for GLSL shaders.

(figure by @hardmaru)

Read 12 tweets

Cyril Diagne

@cyrildiagne

Oct 22, 2020

@jblanchefr

Aaand here it is..!!! 😱

After months of hard work with @jblanchefr, @ClipDropApp beta (AR Copy Paste) is now publicly available on #Android, #iOS, #macOS, and #Windows

🔥 clipdrop.co 🔥

Here's a thread of what you can already do with it ↓ 1/n

#ML #AR #AI

@figmadesign

You can capture directly from your desktop with a screenshot and drag & drop to any other app (my favorite feature 🤩)

It works from/to virtually any application & websites: @figmadesign, @Photoshop, @Canva, @Pitch, @Powerpoint, @GoogleDocs...etc!

#ML #Augmented #DesktopOS

You can extract anything: objects, people, drawings, and text. The quality of the salient object detection, background removal, and text detection is now quite incredible 😳😲🤯

Read 8 tweets

Cyril Diagne

@cyrildiagne

May 17, 2020

@centrepompidou

Proto 6/10: Copy printed text to desktop with AR+ML

Code: github.com/cyrildiagne/ar…
Book: Neurones, les intelligences simulées, Frédéric Migayroux & al (Editions Hyx 2018 @centrepompidou)

#ML #AR #AI #AIUX #ARCore #ARKit #WebXR

Technical Insights: ↓

The magic here is to use ARCore + AugmentedImages rather than SIFT.
Phone gets a new desktop screenshot on touch and adds it to ARCore (< 100ms).
Tracking is crazy fast & precise.

Interesting alternative to touch screen for interactive installations!

@Firebase

The text detection is performed on device with @Firebase #MLKit. Super fast, good accuracy and cross platform.

Read 6 tweets

Cyril Diagne

@cyrildiagne

May 3, 2020

@HOLOmagazine

4/10 - Cut & paste your surroundings to Photoshop

Code: github.com/cyrildiagne/ar…

Book: @HOLOmagazine
Garment: SS17 by @thekarentopacio
Type: Sainte Colombe by @MinetYoann @ProductionType
Technical Insights: ↓

#ML #AR #AI #AIUX #Adobe #Photoshop

The secret sauce here is BASNet (Qin et al, CVPR 2019) for salient object detection and background removal.

The accuracy and range of this model are stunning and there are many nice use cases so I packaged it as a micro-service / docker image: github.com/cyrildiagne/ba…

And again, the OpenCV SIFT trick to find where the phone is pointing at the screen.

I also packaged it as a small python library: github.com/cyrildiagne/sc…

Send a camera image + a screenshot and you get accurate x, y screen coordinates!

Read 6 tweets

Cyril Diagne

@cyrildiagne

Feb 10, 2019

The coarse knob of #StyleGAN really is mesmerizing. Esp. how it adds/replaces some features to match the artistic style (collars, hats..etc)

On random interpolation, the truncated latent space also looks surprisingly continuous & morphologically coherent.

(Last one) with the fine knobs (range 6-16). Looks much more like a traditional style transfer which keeps the face features & pose relatively intact.