Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (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
TechHalla Profile picture
TechHalla
@techhalla
Consistently offering insights on generative AI. 🎥 RunwayML, Luma, Leonardo, Kling CCP. Freepik Partner. Tripo Ambassador Join me on other socials! 👇👇
10 subscribers
Jul 21 • 11 tweets • 5 min read
tons of people are making insane ads with Veo 3 lately, but how were they made?

7 examples + JSON templates to help you recreate them in LTX Studio 👇

1. Amazon 2. The North Face

Prompt in the image ALT description 👉
{ "scene_description": "A climber reaches a summit, gasping. As they raise their arms, a sudden gust of wind pushes back their hood — revealing the North Face logo on their shoulder. Quick cut to a wide shot of the climber silhouetted against the sky with the logo clear.", "visual_style": "epic outdoor documentary", "camera_movement": "POV pan + wide drone reveal", "main_subject": "North Face jacket worn during a summit achievement", "background_setting": "mountaintop above clouds", "lig...
Jul 20 • 11 tweets • 5 min read
I’ve shared over 2,750 prompts in the past 2 years.

And I’m not stopping anytime soon.

Here are 9 more for Midjourney 👇 1. 90s Japanese cyber fashion

Prompt in the ALT description 👉
a cheerful girl with exaggerated colorful nails, vibrant rings, and pink translucent sunglasses, posing in front of a wall of Japanese magazines | 90s Japanese cyber fashion style | expressive hand pose with toothy smile | harsh fluorescent lighting | analog aesthetic, fashion editorial look --ar 3:2 --raw --stylize 400
Jul 19 • 11 tweets • 5 min read
9 unique prompts compilation for Midjourney

Bookmark now, keep them forever 👇 1. Grim reaper

Prompt in the ALT. Animation auto low
A highly detailed cinematic shot of a grim reaper knight riding a dark warhorse across a windswept desert, leading a massive army of armored soldiers under a golden waning eclipse | the reaper wears tattered, flowing black robes over skeletal armor, holding a curved obsidian scythe | fine particles of sand swirl in the amber dusk light, casting dramatic shadows | dust trails behind the cavalry, horizon blurred | wide-angle composition, shot on 50mm lens with shallow depth of field
Jul 17 • 9 tweets • 5 min read
you can create stylish intros using Midjourney

just follow these steps and you'll start seeing results in minutes.

includes AI prompts and DaVinci tips 🧵👇 Let’s start with the images. I’ve got the perfect prompt for this, all you need to do is swap out the subject or object to get results like these.

The prompts are in the ALTs. A black silhouette of a big bald man with beard, leather jacket and machete | side view composition with 3/4 of the frame as glowing red flat background | highly saturated | moody, artistic style | minimalist svg aesthetic --ar 2:1 --raw
A black silhouette of a stylish woman over a ford mustang | side view composition with 3/4 of the frame as glowing red flat background | highly saturated | moody, artistic style | minimalist svg aesthetic --ar 2:1 --raw
A black silhouette of cat next to a skull | side view composition with 3/4 of the frame as glowing red flat background | highly saturated | moody, artistic style | minimalist svg aesthetic --ar 2:1 --raw
A black silhouette of the face of a gangsta granny smoking | side view composition with 3/4 of the frame as glowing red flat background | highly saturated | moody, artistic style | minimalist svg aesthetic --ar 2:1 --raw
Jul 16 • 10 tweets • 6 min read
nobody is using this Midjourney trick... and it’s wild!

make endless parallax loops with AI + DaVinci Resolve.

Full guide + prompts in this thread 🧵👇 Let’s start with the character.

I created this hipster cyclist in Midjourney, I like the aesthetic, and more importantly, the background contrasts perfectly with the subject. That’ll come in handy later.

Prompt is in the ALT of the image. profile side view of a 2D cartoonish doodle vivid cyclist plain green chroma background --ar 1:1 --raw --stylize 600
Jul 15 • 9 tweets • 5 min read
this woman isn’t real

I created her in minutes using AI!

Just by combining Higgsfield and Veo 3, all for under $19!

all the details in this thread 🧵👇 First, we’re going to create our reference image.

This one was made with @higgsfield_ai Soul using the Amalfi Summer style it’s killer.

I’ve dropped the prompt in the ALT of the image. A candid close-up shot of a woman in her early 30s with short, straight blonde hair, a distinctive beauty mark on her left cheek, expressive brown eyes, and bold red lips. She wears a simple cream-colored linen blouse, casually unbuttoned at the collar, and small gold hoop earrings. The soft warm daylight typical of a late Italian afternoon gently illuminates her face, enhancing natural skin texture including subtle freckles and fine lines around her eyes. The blurred background hints at a rustic Italian courtyard with whitewashed stone walls and dappled sunshine filtering through leafy gre...
Jul 8 • 11 tweets • 3 min read
I asked Veo 3 to take me around the world and here's what happened... 👇

1. It turned me into a flamenco singer in Spain 🇪🇸 2. Then it took me to the most disco version of Italy. Good vibes 🇮🇹
Jul 7 • 7 tweets • 4 min read
Now you can recreate any TV show with AI.

I'll show you how to do it, using Flow and the prompts included 🧵👇

(save this for later) Let’s start by creating some shots to build the story and help us keep character consistency later on. I used Veo 3 Fast for this since it includes sound effects and dialogue.

Here’s one of the prompts so you have a reference.


{ "scene_description": "Two judges watch the forging process from behind a control table; one reacts dramatically with hands on his head, while the other leans forward, surprised by the technique he's seeing.", "visual_style": "real TV footage", "camera_movement": "medium static shot capturing both judges in frame with slight zoom-in on their expressions", "main_subject": "two judges reacting to the contestant’s unusual technique during the tempering process", "background_setting": "interior of th...
Jul 2 • 19 tweets • 6 min read
the 15 most iconic consoles reimagined as car interiors.

prompts and tools in this thread 🧵👇

1. NES 2. Xbox
Jun 23 • 9 tweets • 4 min read
Stop wasting your time in Photoshop.

This AI can place your product into any image, keeping proportions intact, and it only takes seconds!

Examples and prompts included in this thread 🧵👇 Before I get into how @higgsfield_ai Canvas works and share the prompts with you, here are a couple more examples so you can see how it handles any product or character. Image
Jun 22 • 12 tweets • 8 min read
Midjourney Video shook the AI world this week.

20 prompts for images and videos that prove it 🧵👇 1-2. Urban queen in gold chains

Image prompt in the ALT description 👉
Afro-American girl with long straight black hair and blunt bangs, wearing oversized black streetwear with bold white graphics, standing confidently in a narrow, gritty Tokyo alley covered in graffiti and urban clutter | moody atmosphere | gold accessories | urban fashion editorial | cinematic depth of field
Image
Jun 21 • 12 tweets • 4 min read
I'm sure you've seen tons of AI videos of animals at the swimming Olympics...

Here's how you can make them yourself in this thread!

7 example prompts + info🧵👇 I made all these videos using @Hailuo_AI 02 text-to-video and the following prompt (just swap the animal)

1. televised footage of a CAT is doing an acrobatic dive into a swimming pool at the olympics, from a 10m high diving board, flips and spins
Jun 20 • 7 tweets • 4 min read
Total consistency in Veo 3 is now possible.

Tutorial thread on how to keep characters and style consistent in your videos using Freepik 🧵👇

Includes prompts. examples and all the info. Let’s get started: first thing we need to do is lock in our character and style.

You can use your own LoRA like I did, or generate any character. I used Mystic on @freepik.

Set up the scene with your prompt and choose a style so the entire clip has a consistent look. Image
Image
Jun 18 • 16 tweets • 7 min read
I'm sure you've seen tons of epic AI generated selfie videos.

Wanna learn how to make them yourself? I’ll show you how in this thread.

13 example prompts using Veo 3 on LTX 🧵👇 1. Plague cart man on Medieval streets

Prompt in the ALT 👉
{ "scene_description": "real footage selfie of a plague cart-puller walking through a filthy medieval alley, dragging a cart full of wrapped bodies and shouting theatrically.", "visual_style": "real footage", "camera_movement": "handheld selfie with slight bounce from walking and cart movement, occasional tilt to show the cart", "main_subject": "a ragged man in a beaked plague mask and stained tunic, grinning while pulling the cart", "background_setting": "muddy street in a medieval Euro...
Jun 16 • 6 tweets • 3 min read
I went to Yosemite and things got totally out of hand...

All I had was my phone and the prompts + tips below for Motion 2.0 🧵👇 First, we need to record a video of ourselves. In my case, I took advantage of a trip to San Francisco to swing by Yosemite, and it was amazing! The place is absolutely stunning... so I recorded a few clips like this one!

Now we grab the last frame.
Image
Jun 13 • 8 tweets • 3 min read
she’s not real

but she looks like margot robbie + dua lipa + your high school crush

and she talks

people generate these avatars with $20 Higgsfield Speak.

here's how 🧵 👇 Here’s the rundown:

Upload the person’s pic.

Use Flux Kontext to tweak anything you like (I’d do it in stages).

Boom—you’re ready to animate!

Check out this video from @higgsfield_ai official account. I’ll drop a few more for you now.
Jun 11 • 8 tweets • 4 min read
I’ve cloned myself with AI and now I’m a food vlogger!

Not sure if I’ll make a living off it... but still, here’s the tutorial on how to use Flux Kontext in Higgsfield, their latest feature!

Prompts + all the info, below 🧵👇 Let’s get to the point. @higgsfield_ai just added Flux Kontext and you can upload a photo of yourself and tweak it HOWEVER you want.

The prompt’s in the ALT, but basically I asked it to put me in a fast food restaurant holding a burger. the bald man is holding a super sized hamburguer with one hand and the other hand is out of the scene as an UGC content. The background is a fast food restaurant interior.
Image
Jun 1 • 6 tweets • 3 min read
Creating a video with Veo 3 costs around $3.

That’s why coming up with a solid prompt can save you a ton of cash on your video project!

Let me show you how using JSON prompting 🧵👇 If you’ve never heard of JSON before, let me explain, it’s super simple:

It’s a lightweight text format commonly used in JavaScript, but we can totally use it for our prompts too. It helps us organize parameters in a neat and structured way. Image
May 31 • 14 tweets • 5 min read
Veo 3 is out of control right now!

13 wild examples, prompts included 🧵👇

1. A chimpanzee operating a jackhammer on a city sidewalk 2. A gibbon in a fitted apron stands behind the counter of a modern coffee shop, operating a professional espresso machine and carefully pouring steamed milk into a cappuccino with visible latte art technique, while soft indie music plays
May 26 • 9 tweets • 4 min read
I made this whole video using Veo3.

It makes no sense. Took me just 45 minutes and cost $33 total.

The prompts are below 🧵👇 2000s TV show, broadcast booth. A man, Mike, around 35 years old, is sitting and speaking from a broadcast booth. He’s wearing an earpiece and talking to the camera with an energetic voice. With humor, he says:

“This is SmackDash… and these guys are going to have a blast… literally!”
May 24 • 15 tweets • 9 min read
Everyone’s talking about Google Veo3...

But Kling AI did their homework and is coming in hot!

11 + 11 prompts to create images in Midjourney v7 and animate them in 2.1 🧵👇 1. Model walking the runway with a sword

Image prompt and video prompt in the ALTs 👉👉
A confident girl model in chrome-and-latex battlewear walking on a holographic runway, wielding a crystal blade | lit with pinpoint white spotlights and accent backglow | captured at mid-range with 85mm lens for bokeh effect and motion freeze | fashion combat editorial with high clarity --ar 3:4 --raw --stylize 750
The person strides confidently down the runway, raises the sword high with one hand, and gives a sharp look to the camera, which tracks backward smoothly and keeps pace from a low angle.