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
Apr 26, 2023 • 11 tweets • 6 min read • Read on X
Scrolly
1/🎨✨Ready to dive deeper into AI image generation with #Midjourney?

🧵In this thread, we'll focus on creating unique prompts that feature diverse characters, photographic styles, and illustration techniques!

Like and share will be welcomed!❤️🔁
#AIArtcommunity Image
2/🧩 Category Prompting: Break down your idea into specific categories like mood, scene, actors, and location. This helps the AI understand your vision in detail. Example in the ALT of the image #CategoryPrompting /imagine prompt: IMAGE: Por...
3/➕ Additive Prompting: This style focuses on adding specific elements to your prompt, one by one. Example in the ALT of the image #AdditivePrompting /imagine prompt: Serene Mou...
4/📚 Narrative Prompting: Tell a story or describe a scene in a detailed manner. This style helps the AI generate images based on the narrative you provide. Example in the ALT of the image #NarrativePrompting /imagine prompt: In a dream...
5/❓ Interrogative Prompting: Frame your idea as a question. This encourages the AI to come up with an image that answers the question. Example in the ALT of the image #InterrogativePrompting /imagine prompt: What would...
6/🌟 Lighting & Mood: Create a unique atmosphere in your prompts by playing with lighting and mood, such as dramatic contrasts or soft, diffused light. Example in the ALT of the image #LightingAndMood /imagine prompt: Low key po...
7/🔑 Remember: Don't use commas within the prompts! Use semicolons or other punctuation instead. Commas should only be used to separate prompt styles. Keep this in mind when crafting your prompts! Example in the ALT of the image /imagine prompt: IMAGE: Ill...
8/💡 Start by experimenting with different prompting styles and see which one works best for your needs. You can even combine styles to create a more refined and detailed prompt. The possibilities are endless! 🚀 /imagine prompt: Candid sho...
9/🎉 Now you're ready to create amazing AI-generated images with Midjourney! Share your creations with the world and inspire others. Happy prompting! #AI #ImageGeneration /imagine prompt: Futuristic...
10/10 🥳 That's it, folks! We hope this thread has inspired you to explore the world of AI image generation with Midjourney. Have fun, and don't forget to share your unique and captivating creations with your friends and followers! #AIArt #AIartcommunity #Midjourney Silhouette | Sunset | A cou...
Don't forget to visit my Gumroad store to download my free guides

techhalla.gumroad.com

• • •

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

TechHalla Profile picture
Sep 17
In the past week, Hailuo just dropped 7 Days Unlimited Start/End Frames.
I made this piece to show you its potential.

The smoothest, sharpest, most creative control on the market.

And here you've got everything you need to know to make videos like this yourself in minutes ↓
Other AI video tools? Clunky. Rigid. Break the illusion every time.

Hailuo fixes it:

Pick your start/end frames, and Hailuo fills the gap flawlessly.

Try Hailuo now through my partner link:
New users → Membership bonus
Existing users → Top-up bonuseshailuoai.video/create/image-t…
Before you start animating with @Hailuo_AI, it’s important to have all the stills you need to build the final sequence.

I used nano banana to create the full storyboard, starting from a single image and iterating from there. If you need a prompt, just ask.

Let’s animate! ↓ Image
Read 9 tweets
TechHalla Profile picture
Sep 16
quick tutorial on how to create ink smoke style transitions with AI.

It’s so easy, it’s kinda ridiculous 🧵👇
Let’s start by creating the stills.

I went with Midjourney version 6.1 (not the current version 7) because it works best for the look I’m going for.

The prompts are in the ALTs, all you gotta do is pick a character. Batman drawn in smoke is shown, in the style of abstract ink art, flowing silhouette, polished metamorphosis, dark and intricate, contemporary. black and white --ar 16:9 --stylize 200 --v 6.1
Jimi Hendrix drawn in smoke is shown, in the style of abstract ink art, flowing silhouette, polished metamorphosis, dark and intricate, contemporary. black and white --ar 16:9 --stylize 200 --v 6.1
Luffy drawn in smoke is shown, in the style of abstract ink art, flowing silhouette, polished metamorphosis, dark and intricate, contemporary. black and white --ar 16:9 --stylize 200 --v 6.1
Geralt of Rivia drawn in smoke is shown, in the style of abstract ink art, flowing silhouette, polished metamorphosis, dark and intricate, contemporary. black and white --ar 16:9 --stylize 200 --v 6.1
Now take the starting frame and the final frame over to @Kling_ai 2.1 and use the prompt you see in the screenshot.

Same prompt every time, no matter which characters you’re using, it always works for this style!
Image
Read 6 tweets
TechHalla Profile picture
Sep 14
you don’t need a master’s degree in AI to make these videos.

just spend 5 minutes reading this thread and trying out the tips and prompts below 🧵👇
Start by recording yourself on video.

BBQ season is (sadly) coming to an end in my area, so I had to go out with a bang with a good old chorizo feast!

Grab the last frame of the video.
Image
Now we’re gonna use Seedream 4 to create the rest of the images for the final video.

I’ve got unlimited access through @freepik, and you can get it too using the link I’ll drop at the end of the thread.

It’s super easy: you upload a reference image and use prompts to edit it. Image
Image
Image
Image
Read 8 tweets
TechHalla Profile picture
Sep 11
I asked nano banana to handle my next marketing campaign and here’s what happened...

in just 5 minutes: branding, merch, and even an ad!

I’ll show you how to do it yourself in leonardo in this thread 🧵👇
First, I asked nano banana on @LeonardoAi_ to create a brochure with all the elements for my product.

From scratch. Here is the prompt:

Create a professional single logo, branding, packaging and merch brochure for a coffee brand called 'Viking beam'

I’m still blown away. Image
Image
Next, I took a photo of myself and the freshly generated brochure, and this time I asked nano banana to create a version of me enjoying the coffee.

Perfect! Prompt examples in the ALTs. the man on the photo is now at a top of a fjord bar terrace, wearing the merch of the brand. the product is over a wooden table next to a coffee maker. professional photography
the man on the photo is now at a bar, wearing the merch of the brand. the product is over a wooden table next to a coffee maker. professional photography
the man on the photo is now at his home, wearing the merch of the brand. the product is over a wooden table next to a coffee maker. professional photography
Read 6 tweets
TechHalla Profile picture
Sep 10
use nano banana to create controlled hyperlapse effects

everything you need to know to do it yourself with AI, in this thread 🧵👇
Let’s start with the initial image.

I don’t have a house to restore, so I just created one using Seedream 4.

You’ll find the prompt in the ALT. A wide shot of an abandoned house in the middle of a barren desert, sun-bleached wood siding peeling off, broken windows, and a collapsed roof | realistic desolation and decay | dry cracked earth, scattered debris, and distant dunes under a hazy sky | mid-afternoon sun casting harsh shadows | taken with a full-frame DSLR, slightly underexposed to enhance textures and shadows
From this image, we’re going to generate the rest of the stills.

You can go into as much detail as you want and make sure the final result is consistent instead of letting the AI make stuff up.

Prompts in the ALTs, using the previous image as a reference in nano banana. Only the foundation and the ruins of the house are left.
I want the house in @img2 to be halfway built based on the state of @img2 . You can see the structure of the house without the final finish and without any walls.
Restore the house so it looks brand new.
Read 6 tweets
TechHalla Profile picture
Sep 9
save 100s of hours of image editing with Higgsfield's Banana Placement

all you need is one product shot!

full guide on how to create videos like this on higgs in minutes, in this thread 🧵👇
The team at @higgsfield_ai just dropped Banana Placement, a new feature in their Canvas that makes life much easier...

But first, let’s create our model.

initial image on the left, still pulled using nano banana on the right.

I’ve added the prompts in the ALTs. A candid low-angle iPhone shot of a stylish young woman sitting casually on a worn bench in an urban street setting, wearing oversized urban clothing and clearly visible Air Jordan sneakers. The dusk ambient lighting softly illuminates her natural skin texture, the fabric grain of her clothing, and casts gentle shadows, while street lights begin to glow in the background. In the foreground, a puddle on the asphalt reflects the scene with subtle distortions, reinforcing the gritty street style mood with cool tones and strong contrast. The spontaneous framing and slightly tilted angle capture...
macro close up of the sneaker. the person is standing
And now comes the magic.

We hit Edit, Banana Placement, upload the image we want to tweak into the Canvas, and paint a stroke over whatever we want to change.

Reflections included.

Upload the product (in this case, the new sneaker) and boom, you're done! Image
Image
Image
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!

Send Email!

:(