TechHalla Profile picture
Apr 18, 2023 6 tweets 3 min read Read on X
(1/6)🧐Character Consistency for Video Games in #Midjourney

🧍‍♂️Introducing Jimmy Jazz, a potential character for a Lucas Arts-style 2D adventure.

🧵In this thread, I'll show you how to do it so that you can apply it to your own projects.

#AI #AIart #conceptart #videogames /imagine prompt: a comic dr...
(2/6)The tricky part is keeping our character consistent while applying variations.

So let's do just that. Copy the URL of the initial image (ensure to open it on browser first), use /imagine prompt:, and then paste the same prompt as before. But let's add a little modification /imagine prompt: [url_of_up...
(3/6) Now, do the same, maintaining the original image url, but modifying his status. Lets say... bowing! /imagine prompt: [url_of_up...
(4/6) And keep going on! Now Jimmy is prepared to run /imagine prompt: [url_of_up...
(5/6) We can also add accesories, such as sunglasses /imagine prompt: [url_of_up...
(6/6) I know the results can be improved, but certainly this can greatly accelerate the process of designing characters, animations... Give it a try and let me know!😊

• • •

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

Keep Current with TechHalla

TechHalla 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 @techhalla

Dec 1
This is the best combo for total consistency with AI.

Kling O1 + Nano Banana Pro

Here’s everything you need to know to get it on Higgsfield 👇
Just a few hours after its release and @higgsfield_ai has already integrated Kling O1 into its suite, the omnireference model that lets you achieve video consistency like never before.

Let’s get started 👇
First thing we’ll do is generate our character.

I found that this grid prompt for Nano Banana Pro is perfect, you upload a pic of someone and it gives you 4 shots from different angles, which we’ll use right after.

The prompt is super long, so I’ll drop it in a screenshot. Image
Image
Image
Read 10 tweets
Nov 28
these 2 prompts for Nano Banana Pro will save you a ton of time.

just upload an image, generate the cinematic grid, and pull the frames you like!

examples made in Higgsfield AI, and prompts below 👇 Image
Image
Image
Image
First, you need to pick the images you want to pull extra cinematic frames from.

You’ll see it works with both real photos and AI-generated ones, like the one below.

We’re starting in @higgsfield_ai and selecting NB Pro as the model. Let’s keep going! Image
It’s a pretty detailed prompt — so detailed it doesn’t fit in an ALT, so I’m dropping a screenshot instead.

What’s cool is we’re tapping into the model’s ability to really analyze the original image and stick super closely to what we ask for.

The result in 4K is insane! Image
Image
Image
Read 8 tweets
Nov 25
Flux 2 just dropped and it's already the alternative to Nano Banana Pro!

I tested both models across 11 different scenarios using extreme prompts in LTX, which one comes out on top?

Let’s break it down in this thread 🧵
1. How would a 5 year old kid draw a portrait of Steve Buscemi?

Unless that kid’s name is Picasso, I’d say the second option (Flux) is way closer, it did a much better job figuring out the kind of lines it should use!

The prompt’s in the screenshot.

Nano Banana 0 - 1 Flux 2.0 Image
Image
Image
Image
2. What if he were a character being hunted by the Spanish Inquisition?

Once again, the second option takes the win. Nano Banana made him look way too good!

Another point for Flux. Prompt’s in the screenshot.

Nano Banana 0 - 2 Flux 2.0 Image
Image
Image
Read 15 tweets
Nov 14
This workflow for creating infinite lofi chill AI loops is one of my favorites!

Do the work once, then just enjoy creating with Workflows on ImagineArt.

Bookmark this now, save time later.
Having a creative interface that’s optimized and perfectly organized is key for any project.

That’s why @ImagineArt_X launched Workspaces, a tool that lets you set up the perfect pipeline to save you time and money. Let me show you how it works 👇
Every project’s different and might need different nodes, but I’ll cover the key ones here.

Start with an Import node (ref image), a text node (prompt), and an image node.

Set up nano banana, connect the dots like in the screenshot, and the prompt goes in the ALT.

That’s it! Image
use the reference subjet and put her listening to music and writing on a blank notebook on a desk. close up of her face, side viewshot. she's wearing a light brown sweater  lofi chill, polished digital illustration. retro vintage vibes. 2D.  there's a fat white and orange cat with green eyes next to her  living room interior, big sized window showing Los Angeles skyline
Read 9 tweets
Nov 12
How much money are AI music cover channels making?

Is it even legal?

I’m breaking it all down for you, based on my own channel that I started just a month ago 👇 Image
AI covers are blowing up lately, soo I decided to launch my channel a month ago, got it monetized in 10 days, and it’s been getting an amazing response.

Here’s the link, and I’ll walk you through the whole process and share some numbers, just below 👇 youtube.com/@radiomandanga
It all started after I watched the iconic Soul cover of 50cent.

Spain needs to bring its musical classics back, too much trash coming out lately. So I picked an 80s icon: El Fary.

I used Suno v5 to cover La Mandanga, which also gave the channel its name.

The vibe? 60s Motown! Image
Read 16 tweets
Nov 8
check out how many camera angle changes there are in this one scene.

How is that even possible with AI without losing consistency?

Blueprints, Leonardo’s new feature is the key, and you can pull it off in minutes following these steps 👇
The team at @LeonardoAi just dropped an awesome new feature called Blueprints, packed with super useful templates you can use in your projects.

And the best part? For the video you just watched, I only used one of them.

Let’s check it out 👇 Image
To start, I created a still using Lucid Origin, a model that lets you generate high-def images with stunning aesthetics.

I’ve added the prompt in the ALT in case you need it. A still cinematic frame with muted colors, showing a Viking warrior in an aggressive stance from behind, holding a big axe, preparing to attack a towering, mythical oracle shaman creature resembling a bear-crow hybrid, in a Norwegian fjord. Shot in third-person POV, with over-the-shoulder composition, dramatic ambient fog, low-contrast lighting, overcast skies | moody film still | Norse mythology influence
Read 8 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!

:(