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

Nov 1
I've put together this collection of 9 prompts for Mystic v2.5 just for you!

Try them out, play around, and share your results in the comments.

Thread below 🧵👇
1. A striking portrait of a woman with vivid pink hair, wearing a neon green jumpsuit, set against a white minimalist backdrop | natural light | soft color palette with high contrast | edgy, modern fashion editorial style | relaxed and confident poseImage
2. a black panther in the savanna, splashing through puddles | hunting a hidden crocodile | bright, sunny day with clear blue skies, documentary footage | dramatic lighting with motion blurImage
Read 12 tweets
Oct 9
Creating your own LoRA styles in Flux is absolutely mind-blowing!

In this thread, I’ll explain how, including a couple of tricks to make the style completely your own.

Let’s go! 👇
If you're an artist with your own works, you can skip these steps.

If, like me, you’re terrible at drawing, you can create a basic sketch or simply generate an image using your favorite model. Here, I applied Dynavision in Remix (prompt in the ALT). Image
NFT 2.5D bizarre art; a cartoonish lovecraftian humanoid. Ultra big head, tiny body. Wearing white shirt and blue jeans and brown boots. Brown head, pale skin. intrincate details. Cosmic psychedelic background
If you want to try @getremixai , do it now through this link.

They’re adding new LoRAs almost daily! Plus, it's the perfect place to learn from others and perfect your prompting technique!

Read 14 tweets
Sep 26
Less than 24 hours since the release of Mystic v2, and I've compiled 7 prompts for you to try!

Plus, I've animated the images using Runway Gen3 and added some flair with Domo AI stylization.

All the info you need is in this thread 👇
1. An old scientist with gray hair and goggles, wearing a space suit, staring in awe at the stars. Futuristic machinery and soft blue lighting in the background, cinematic, highly detailed, with a subtle glow around the figure. Photorealistic styleImage
2. A single eerie figure with a cracked, pale face and hollow eyes, wearing a weathered red hood. The figure stares into the distance with an unsettling, otherworldly gaze. Lovecraftian horror, standing in a foggy, desolate landscape. Photorealistic, dark, and ominous atmosphereImage
Read 13 tweets
Sep 25
Generative AI is about to change how brands create their merch and marketing.

And now, you can do it too—in under an hour!

From designing your own product to generating stock images for your e-commerce and promotional videos!

Here’s your step-by-step guide 🧵👇
First, we need images of our products. This can be a real product, of course, or you can design it from scratch using AI. I used Ideogram 2.0 on @getremixai to create these snapback hats. The prompts are in the ALTs.


A red and black snapback cap of Viking-themed brand with the text"Tech Halla" in bold, modern, uneven typography on it | ecommerce product photography | completely white background | high-detail, clean, professional look | side view, full lighting
A acid green and light purple snapback cap of Viking-themed brand with the text"Tech Halla" in bold, modern, uneven typography on it | ecommerce product photography | completely white background | high-detail, clean, professional look | side view, full lighting
A acid green and purple snapback cap of Viking-themed brand with the text"Tech Halla" in bold, modern, uneven typography on it | ecommerce product photography | completely white background | high-detail, clean, professional look | side view, full lighting
A cyan and gold snapback cap of Viking-themed brand with the text"Tech Halla" in bold, modern, uneven typography on it | ecommerce product photography | completely white background | high-detail, clean, professional look | side view, full lighting
Now, it’s as easy as heading to @TheSimplicityAI and training your own models.

Here’s the step-by-step guide! I’m also sharing the prompts I used and how to animate the images to create the final clips!

Read 7 tweets
Sep 18
Tripo v2.0 is finally out!

Now you can create stunning 3D assets for your projects in 3 minutes from scratch! 🤯

Want to know how? All the info below, prompts, and links included! 🧵👇

(Bookmark this for later)
Let's start with the base images. For this, I opted for Flux Pro on @getremixai and used this prompt:

Kawaii Isometric 3D model | [style] mmorpg [asset] | [element] | [style] architecture | [material] | empty white background | simple shapes

Prompts in ALTs. Access link next.Kawaii Isometric 3D model | fantasy mmorpg building | a hut | traditional architecture | wood and stone | empty white background | simple shapes
Kawaii Isometric 3D model | fantasy mmorpg asset | a cat | traditional design | black | empty white background | simple shapes
Kawaii Isometric 3D model | fantasy mmorpg asset | a fountain | traditional design | stone | empty white background | simple shapes
Kawaii Isometric 3D model | classic mmorpg asset | a red van | modern design | empty white background | simple shapes
You can try Remix without needing to register through this very link! But if you like it, I recommend signing up to unlock all its capabilities!

Read 7 tweets
Sep 11
Is it posible to get AI character consistency in Flux with just one picture?

Yes, with Rendernet it’s a piece of cake! 😎

I’ll show you how with 7 sample prompts 👇🏻

(Bookmark this for later)
Before we get started, we need a picture of the character’s face that we want to replicate. I took a selfie, but it works with any character! Image
Now, in @rendernet_ai , we create our AI character, upload a photo, frame it, and set the parameters to our liking.

At the end of the thread, I'll drop the access link.


Image
Image
Image
Image
Read 13 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!

:(