Share this page!

Enter Twitter Thread URL to Unroll

Needs to be the full URL like: https://twitter.com/threadreaderapp/status/1644127596119195649

How to get URL link on 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
Kris Kashtanova Profile picture
@icreatelife
Jun 23 • 5 tweets • 3 min read Twitter logo Read on Twitter
Scrolly
Midjourney v5.1 (left) versus Midjourney v5.2 (right)

(seems like they fixed "wet skin" issue)

prompt: portrait of a young woman, blue eyes, cinematic

Midjourney v5.1 (left) versus Midjourney v5.2 (right)

prompt: a cartoon of a glowing smiling fish, cinematic

Midjourney v5.1 (left) versus Midjourney v5.2 (right)

prompt: New York street cinematic

Midjourney v5.1 (left) versus Midjourney v5.2 (right)

prompt: An astronaut sitting on the moon, friendly town background, stars, beautiful

Midjourney v5.1 (left) versus Midjourney v5.2 (right)

(definitely got better with the number of fingers)

prompt: two hands silhouettes reaching to the sky reaching the clouds

• • •

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

Keep Current with Kris Kashtanova

Kris Kashtanova Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

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

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @icreatelife

Kris Kashtanova Profile picture
Jun 23
Midjourney version 5.2 - New Feature - ZOOM OUT!

How to use it
👇





Step 1: make sure you're in version 5.2 mode
(write /settings in your prompt line, press enter, choose version 5.2)
Generate an image you want like you used to, short prompts work great and press upscale (U1 - U4)
Step 2
When you upscaled an image in the new version you'll see new options of Zoom. You can choose Zoom 1.5 or Zoom 2.0 and Custom. Custom zoom is from 0 to 2. but don't worry, you'll be able to zoom out in next iteration if 2 isn't enough
Read 5 tweets
Kris Kashtanova Profile picture
Jun 22
Stability AI just released SDXL 0.9. The quality of it is insane and it's free/open source.

Comparison between SDXL 0.9 (left) and Midjourney 5.1 (right)

prompt: portrait of a young woman, blue eyes, cinematic
It's available on the Clipdrop, Stability AI API and DreamStudio

Comparison between SDXL 0.9 (left) and Midjourney 5.1 (right)
prompt: a cartoon of a glowing smiling fish with blue eyes, cinematic

Comparison between SDXL 0.9 (left) and Midjourney 5.1 (right)
prompt: Two hands silhouettes reaching to the sky reaching the clouds

Read 7 tweets
Kris Kashtanova Profile picture
Jun 22
My first AI Lofi animation, sharing my process in the thread

Tools:
* Adobe Express: base image
* Photoshop (beta): to add cats with Generative Fill
* After Effects: to animate
* MusicLM: to generate music

Time: 8 hours

Thx @0xFramer for inspiring me
#KrisAIAnimation
Step 1: Generating and extending original image
Original image (extended with Generative Fill)
Step 2:
Adding a lot of cats with Generative Fill
Read 5 tweets
Kris Kashtanova Profile picture
Jun 17
AI news of the week:

• Apple steps up in AI
• Meta releases MusicGen
• Regulators scrutinize AI safety
• AI to identify respiratory conditions
• MIT research AI in aviation
• Disney Research reveals facial landmark detection network
• Instagram chatbot

Read more
🧵👇
Apple has prioritized AI in its upcoming hardware and software. iOS 17 will offer AI features like suggesting recipes from an image and improved autocorrect using AI. Apple Vision Pro, an augmented reality headset, will also utilize AI for features such as FaceTime
Meta releases an AI-powered music generator: The tool, called MusicGen, can generate about 12 seconds of audio from a text description.
Read 9 tweets
Kris Kashtanova Profile picture
Jun 17
I have to admit Nikon's new ad campaign "Don't give up on the real world" is rather genius marketing. Using the fact that generating AI photorealistic images is trending to promote their photography products.

What do you think?

1/ 7 Image
2/ 7 Image
3/ 7 Image
Read 7 tweets
Kris Kashtanova Profile picture
Jun 17
AI EDUCATION ROADMAP
(part 1)
The first time I studied AI was back in 2006. I was doing my Master's degree in Computer Science and it was a one-semester course. At the time it didn't capture my attention. In the past year, everything changed. I love it. My version of a roadmap:
Maths / Python: brilliant.org/home/ - if you want to refresh or learn maths from scratch I found this website easy and intuitive. There're a few maths and statistics courses that would be great for a foundation. There's also a simple Python course that I enjoyed. It's paid.
pll.harvard.edu/course/cs50-in… - CS50 with David J. Malan is an absolute treat. It teaches you how to think algorithmically and introduces different programming languages, including Python. It's a free (in audit) course.
Read 7 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

Send Email!

:(