Allen T. Profile picture
AI Videomaker ✦ AI Educator ✦ Optimist ❥Sharing AI trends, tools, & tutorials
Danz Castilho Profile picture 1 subscribed
Jun 25 5 tweets 2 min read
Toys "R" Us has released the first OpenAI SORA generated brand commercial

The use of generative AI in commercial work is here. Full details:


@visiblemakers @ChristianF369 with the scoop!toysrus.com/pages/studios
Jun 12 16 tweets 5 min read
Luma AI dropped their Sora competitor & it's insane

The best part? They are actually letting people use it

10 awesome examples with prompts: 1) Prompt: Man with a television head walking through new york city times square

Note: I created each generation in this thread with Luma's text2image or image2image feature

#LumaDreamMachine
May 7 7 tweets 3 min read
Aging Morphing 🧒👴

Using the Img2Img feature on @getremixai & frame interpolation on @runwayml we can age characters in less than 5 minutes

I will teach you how in the posts below 👇

#RemixAmbassador 1) Create a character

Using the RealVisXL model I generated a starter image for this process

Prompt: A teenage man, close up shot, macro Image
Mar 17 11 tweets 3 min read
This week @Magnific_AI began beta testing their new "Transfer Style" feature

The early results look amazing!

10 awesome examples:Image 1) @moritzkremb

Feb 17 10 tweets 3 min read
Incase your phone has been broken for the past 48 hours

The OpenAI team has been dropping new Sora videos since the official release

Here are 10 incredible Sora videos posted on X: 2)
Dec 24, 2023 8 tweets 2 min read
AnyDoor is now online and it's incredible!

It can be used for virtual try-on, moving, swapping, or inserting objects into new scenes, and shape editing

This will be huge for e-commerce.

More examples in thread Swapping objects
Dec 13, 2023 5 tweets 2 min read
Virtually try-on any clothing on any person with AI!

The research project "Outfit Anyone" aims to create high-quality virtual try-on for different poses and body shapes.

It's works for everything. From anime to real-life images.

Examples and link below: github.com/HumanAIGC/Outf…
Aug 30, 2023 9 tweets 4 min read
Huge strides have been made for creating consistent characters with Midjourney.

Using an inpainting technique, we can go further.

With this workflow, you can bring a character into new scenes with different expressions.

This is big. Especially for video storytelling. Image 1) First, let's start with the amazing prompt from @chaseleantj and @juliewdesign_

Prompt: [Subject], split into 3 different images, shot from multiple angles --s 50

Important: You want three (3) panels for this workflow.
Aug 24, 2023 12 tweets 3 min read
Midjourney's inpainting was released this week

Users testing the feature have already discovered incredible capabilities. Bookmark for future reference.

Here are 10 amazing discoveries so far: Image @Nerbts - Creating consistent characters with inpainting
Aug 22, 2023 9 tweets 4 min read
Creating character collections 💎

Using Midjourney to create massive collections of characters with unique traits and styles. Bookmark for reference later.

Let's get started Image 1) The Prompt

Prompt: NFT collection, [Adjective] cartoon [Subject] with different colors, clothing, and expressions, close up, grid collection --style raw

NFT collection, rich and fancy cartoon pigs with different colors, clothing, and expressions, close up, grid collection --style raw
NFT collection, cool cartoon llamas with different colors, clothing, and expressions, close up, grid collection --style raw
NFT collection, cool cartoon cats with different colors, clothing, and expressions, close up, grid collection --style raw
Aug 20, 2023 7 tweets 3 min read
How to layer elements in Midjourney

Layering elements in your images is important for creating depth and spatial relationships within a scene.

It makes your images feel complex.

Let's dive in 👇 Image The key to layering elements is using the tokens foreground, middle ground, and background.

The nearest part of a photo is the foreground, the most distant is the background, and the area between is the middle ground; however, not every image requires all 3.

Let’s continue Blonde woman in the foreground, forest in the middle ground, mountains in the background, Kodak portra 800 --ar 16:9
Jul 18, 2023 12 tweets 6 min read
Midjourney Website Designs

I have been using Midjourney to workshop website design ideas lately and the results are quite amazing.

Prompt: [Type] website landing page, [Subject], [Color] color pallet, geometry, wide angle --ar 4:3

10 website examples below 🧵👇 Image #1 Video Game Website

Prompt: Intense video game website landing page, space exploration game, rich and saturated color pallet with blues, oranges, greens, color pallet, geometry, wide angle --ar 4:3
Image
Image
Jun 19, 2023 10 tweets 4 min read
📸 Midjourney Aspect Ratios

The aspect ratio is one of the most powerful parameters when crafting a Midjourney prompt.

It plays a critical role in the composition, shape, and aesthetic of the image

Let's look at some examples and discuss🧵👇 (1/10) Image --ar 1:1

The default aspect ratio (ar) in Midjourney is 1:1 or "--ar 1:1".

An ar of 1:1 is the classic square image. It is ideal for social media profile pics, icons, and logos.
(2/10) Adult fashion model astrona...
May 31, 2023 4 tweets 4 min read
Prompt Share: Isometric Views 🍟👜 🧵

Isometric illustrations are a fun way to generate 3D objects. They are created with equal proportions and unique angles to maintain the size and add depth to digital designs.

When Midjourney V4 came, I was a little bit obsessed with… twitter.com/i/web/status/1… McDonald’s fries, isometric...Nike air max, isometric 3d,...The starry night, isometric...Gucci handbag, isometric 3d... Isometric clothing. Ran ban sunglasses, isometr...Yankee’s hat, isometric 3d,...gucci belt, isometric 3d, s...
May 30, 2023 4 tweets 2 min read
🌸 A Ronin's Infinite Stand🌸

I played around with @ElunaAI @rpnickson infinite zoom feature this morning and it really is a quite impressive feature.

I have added my prompts for the infinite zoom and music generation in the tweets below. 🧵👇 For this generation I used three prompts and only changed the subject of each. I also kept the guidance low because I like the AI to have more creativity while generating (I like a little bit of chaos). Image
May 29, 2023 13 tweets 7 min read
My 10 favorite AI tips, news, and threads from the past week (includes both large and growing accounts): 🧵👇

🔁Retweet and post any of your favorite AI creations from the past week that I missed! Also follow all of these wonderful creators. @rpnickson infinite zoom using @eluna AI

May 8, 2023 7 tweets 3 min read
GPT-4 Mini Game - Ghoul City - Version 1 🎮🤖

Ghoul City is a simple side-scrolling video game that I created entirely with GPT-4 and Midjourney.

To create Ghoul City, I pretended to not have any coding background and instead let AI handle all of the coding and debugging. 🧵👇 The goal of Ghoul City was to see how difficult it would be to create a simple video game for someone with absolutely no coding experience. I got the idea to try this out from @icreatelife fantastic tutorial on creating video games with AI.