Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Divam Gupta Profile picture
Divam Gupta
@divamgupta
Creator of one-click ML tool - https://t.co/NE4LuTGBv5 and https://t.co/oNpCKBAjH9 • AI for VR @Meta • Previously: research @Microsoft, robotics @CarnegieMellon
Jan 28, 2023 • 6 tweets • 2 min read
Most AI image generation tools include an invisible watermark in the generated image.

This watermark is invisible to human eyes, but can be identified by the algorithm 🧵. First, the image is broken down into different sub-bands consisting of high-frequency (fine-grained) and low-frequency (course-grained) components.

This is done using discrete wavelet transform.
Nov 1, 2022 • 12 tweets • 4 min read
DreamBooth is becoming popular for creating custom Stable Diffusion models using your images.

Here is a beginner friendly thread on how it works: 🧵 Image First, what does DreamBooth do?

- It takes few images of a particular subject

- Then it teaches the model to generate more images of that subject in different styles.

For eg. you give 20 normal images of yourself and get a funky painting of yourself in return.

(ft. @ylecun ) Image
Oct 21, 2022 • 9 tweets • 3 min read
It’s been 2 months since Stable Diffusion’s release, it has been re-implemented in almost every popular ML framework out there.

Here are some popular implementations: 🧵 : 1) The original PyTorch implementation by Machine Vision and Learning LMU Munich.

github.com/CompVis/stable…