It took me only 5 hours to make this animation. Turn on sound, take a breath and relax.

Anyone can do it thanks to AI and other tools.

Tools used: Adobe Firefly, After Effects, Generative Fill, Adobe Express

Here're 5 steps you need to take to make an animation like this: Step 1:
Generate an image with Adobe Firefly:

How to write a script for After Effects with GPT-4

I'm learning animation with Adobe After Effects and AI helps me learn it faster. I haven't written a script before and I asked GPT-4 to help me write a particle system one.

Here're the steps how I did it: https://t.co/gMzSvJrWwLtwitter.com/i/web/status/1…
Step 1:
Create a file in a text editor (ex. Notepad or Wordpad) and save ending with .jsx (for example, particles.jsx).

Start with a prompt: "Can we write a script making a beautiful particle system with After Effects?

copy-paste your script to the file and press "Save"

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 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)

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

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)

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

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 2/ 7

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.

Another big company added AI in a creative way. Spotify added DJ AI and I can’t get enough of it! DJ is fun, calls me by my name and talks and knows my music tastes. It was trained on a voice of Xavier “X” Jernigan and sounds so real.

Here how it works:
🧵

*not sponsored* Make sure your Spotify app is up to date: The AI DJ feature is only available on the latest version of the Spotify app, so check if you have any pending app updates and install them. 2. Check if the feature is enabled on your account: Make sure that the AI DJ feature is enabled

Practical use of A.I.
(part I) - Custom gifts for kids.

A lot of you are asking me about the practical use of A.I. and what skills someone may need and what they'll do to earn money doing A.I.
I made a number of custom children custom gifts.

Here's how to do it:
🧵👇 twitter.com/i/web/status/1… Parents often asked me to train a model on photographs of their child so we could include the kid in A.I. generated story. Here's a tutorial I made on how to train a model on your photos:

https://twitter.com/icreatelife/status/1656781077380202501?s=20

What are your plans for the weekend?

I'm taking another Machine Learning specialization. And here're 5 more AI courses I took in the past that helped me a lot both as a learner and a teacher.
🧵👇 Course 1: After talking to several people I thought I'll invest more time in learning. A lot of people perceive adulthood as the end of learning and only working, but that's where there'll be the first shift. Continuous learning to keep up.
coursera.org/specialization…

When I visit museums I always wonder what those broken sculptures looked like. Thanks to Generative Fill I restored some. The last one is my favorite.

Would absolutely love to see your restoration efforts: broken sculptures, ancient temples, anything goes! Fragmentary colossal head of a youth, 2nd century B.C. Greek. Marble (restored with Generative Fill / Photoshop)

When you visit me in New York we can see it together in the MET

Why Adobe is winning at Generative AI:

1) commercial safety
2) transparency
3) great UI
4) inpainting and outpainting built into their most popular product, Photoshop
5) offering a separate free product (Firefly)
6) combining efforts with Google and NVIDIA

Read more
🧵👇 1) Adobe trained their model on images they had license for and it's important as governments started questioning how AI models were trained. There'll be regulations, which means having a commercially safe model is a priority. Quality can be improved by licensing more assets.

New Twitter algorithm and how to take advantage of it
😃🧵👇 The New Twitter algorithm favors threads!

If you have GPT-4 browsing you can send this code to be analyzed by it

https://twitter.com/TwitterEng/status/1659678764333428736?s=20

INSPIRATION #1: Things you can do with Generative Fill in Photoshop Beta or in AdobeFirefly (for free)

Every week I'll be sharing with you things that inspired my creativity most.

🧵👇
Extending works of art by @leebrimelow

1/6 twitter.com/i/web/status/1… @adampickard used Dall-E and Generative Fill side by side (using outpainting) to put together these animations
2/6

We're all dreamers and storytellers. This is my first AI-assisted comic book and creating it made me fall in love with AI. Thanks to it you are in my life.

"Zarya of the Dawn", August 2022, New York Pages 2-3

Today was released a ChatGPT PLUG-IN was to generate Midjourney prompts!

Here's a short tutorial on how to use it 🧵👇 twitter.com/i/web/status/1… Step 1
Find the plug-in in the store (it's free) and install it

Step 1 - Settings

A.I. for brands
Since I started freelancing as an AI consultant couple of months ago, brands and agencies were my main clients. I was sharing with you my experiences and today I'd like to put together the "A.I. for brands" posts I made. twitter.com/i/web/status/1… A.I. FOR BRANDS Part 1 - Designing Retail Stores

A lot of people ask me how I find brands/agencies to work with. So far every brand reached out because they saw my work on social media (mostly LinkedIn and Twitter)

https://twitter.com/icreatelife/status/1641112964148129792?s=20

Last year five of my close people passed away within several months (and two of them on the same day). This A.I.-assisted comic book was my way to keep going. A.I. was in its infancy, creativity took me into a state of flow and helped me.
August 2022, Zarya of the Dawn Zarya of the Dawn
pages 2-3