Heather Cooper Profile picture
Apr 14, 2023 14 tweets 8 min read Read on X
Welcome to the world of AI-generated Disney Princesses:

🔹 Meet Tiana:

(Prompt idea credit: @sbacani) Image
@sbacani 🔹 Cinderella

Prompt:
"Full Body 3D render Cinderella, Disney Princess, Intricate, Dressed in Streetwear fashion & jewelry designer bag, in the style of Bella Hadid, light blue & gold gradient colors, Ultra Detailed, 8K, Best Quality, Unreal Engine 5 Render --niji 5" Image
@sbacani 🔹 Moana

Prompt:
"Full Body 3D render of Moana, Disney Princess, Intricate, Dressed in Hip Hop Drip fashion and jewelry with a Birken bag, in the style of Megan thee Stallion, jewel-toned colors, Ultra Detailed, 8K, Best Quality, Unreal Engine 5 Render --niji 5" Image
@sbacani 🔹 Mulan

Prompt:
"Full Body 3D render of Mulan, Disney Princess, Intricate, Dressed in Hip Hop Drip fashion and jewelry with a Birken bag, in the style of Cardi B, tones of red and turquoise colors, Ultra Detailed, 8K, Best Quality, Unreal Engine 5 Render --niji 5" Image
@sbacani 🔹 Aurora

Prompt:
" Full Body 3D render of Mulan, Disney Princess, Intricate, Dressed in Hip Hop Drip fashion and jewelry with a Birken bag, in the style of Cardi B, tones of red and turquoise colors, Ultra Detailed, 8K, Best Quality, Unreal Engine 5 Render --niji 5" Image
@sbacani 🔹 Pocahantas

Prompt:
"Full Body 3D render of Pocahontas, Disney Princess, Intricate, Dressed in Hip Hop Drip fashion and jewelry with a Birken bag, in the style of Megan thee Stallion, dark pastel colors, Ultra Detailed, 8K, Best Quality, Unreal Engine 5 Render --niji 5" Image
@sbacani 🔹 Snow White

Prompt:
"Full Body 3D render of Snow White, Disney Princess, Intricate, Dressed in Streetwear fashion & jewelry Birken bag, in the style of Bella Hadid, magenta, blue, & pearly white colors, Ultra Detailed, 8K, Best Quality, Unreal Engine 5 Render --niji 5" Image
@sbacani 🔹 Tiana

Prompt:
"Full Body 3D render of Tiana, Disney Princess, Intricate, Dressed in Hip Hop Drip fashion and jewelry with a Birken bag, in the style of Megan thee Stallion, jewel-toned colors, Ultra Detailed, 8K, Best Quality, Unreal Engine 5 Render --niji 5" Image
@sbacani 🔹 Jasmine

Prompt:
"Full Body 3D render of Jasmine, Disney Princess, Intricate, Dressed in Hip Hop Drip fashion and jewelry with a Birken bag, in the style of Cardi B, jewel-toned colors, Ultra Detailed, 8K, Best Quality, Unreal Engine 5 Render -- niji 5" Image
@sbacani Thank you for this wonderful idea @sbacani!

Please look through her thread to see even more princesses and results from other readers 👇

@sbacani Try different styles, colors, and characters for your reimagined topic.

Reply with your results 👇 Image
@sbacani Thank you for reading.

If you found this information useful, follow @HBCoop_ for more content on visual information design and AI.

Retweet the 1st tweet below to share this thread:
@sbacani Stay informed without drowning in AI information with my free weekly newsletter.

Elevate your content with the latest generative AI-powered content creation tips, tools, & trends.

Subscribe to Visually AI now to take your content to the next level:

heatherbcooper.substack.com
@sbacani Stay informed without drowning in AI information with my free weekly newsletter.

Elevate your content with the latest generative AI-powered content creation tips, tools, & trends.

Subscribe to Visually AI now to take your content to the next level:

heatherbcooper.substack.com

• • •

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

Keep Current with Heather Cooper

Heather Cooper 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 @HBCoop_

Mar 12
The era of lipdub AI is over.

Captions just launched Mirage.

The most advanced AI video model we’ve seen.

Here’s why:
Lipdub AI is obsolete:

Most current models only tweak mouth movements while keeping the base video intact.

The result is robotic, awkward, and easy to spot. Mirage doesn’t just move lips. It generates actual reality.
Full-body & full-expression AI video completely built from scratch:

→ Realistic facial expressions
→ Natural movement & body language
→ Even the background is AI-generated

This isn’t a simple overlay. It’s a complete AI-generated performance.
Read 6 tweets
Nov 29, 2024
How to train a FLUX LoRA on an illustrated character sheet to generate realistic, consistent characters.

Workflow below:
I started with this character sheet I generated with FLUX on @krea_ai.

I used @CleanShot to take screenshots of each pose, and upscaled them: Character reference sheet in a 3x3 grid, with several different poses of A beautiful woman with medium-length red hair in a navy blue  sweater, a Disney Pixar-style cartoon character, on a white background
@krea_ai @CleanShot I labeled each image with the trigger word I planned to use at the beginning of the filename.

Then I uploaded the images to @FAL's new FLUX Portrait training model.
fal.ai/models/fal-ai/…
Read 6 tweets
Nov 28, 2024
🔳 Quick prompt tips: Adding 'telephoto shot' with 'soft focus' creates natural bokeh effects.

Notice how light particles blur naturally in the background while maintaining sharp detail on the subject?

Prompt below:

@Hailuo_AI
@Hailuo_AI "Extreme telephoto shot slowly transitioning from soft focus to sharp detail on the panther's eye. Environmental particles create magical atmosphere as golden hour lighting wraps the creature's face. Dreamlike depth of field transitions, natural wildlife movements"

@Kling_ai
@Hailuo_AI @Kling_ai In this prompt, I used 'low-angle tracking shot' combined with 'environmental particles' to create dimensional space.

The circular motion helps AI understand depth relationships, resulting in better particle distribution

Prompt below:

Kling AI 1.5
Read 5 tweets
Sep 19, 2024
FLUX LoRA Resources | Part 4

Mega thread👇
1. PuLID for FLUX: Tuning-free ID customization with FLUX-dev

2. Latent Navigation with Flux schnell

Read 15 tweets
Sep 5, 2024
🔎Midjourney vs. FLUX

I was surprised at the similarity between these images generated from the same prompt.

But there are noticeable differences in style, color, depth of field, and mood.

I'll show you how I got to this comparison👇 Image
1. I used Midjourney sref 1542881645 with this prompt, for the original image:

"photorealistic, neon body tattoos, in the style of cyberpunk dystopia, a man, cityscape"

It's an old prompt I've been using for about 1 year.

This is the Midjourney result: Image
2. To find a precise prompt to get a similar result in FLUX, I use @gokayfem's FLUX Prompt Generator with Florence-2 Large VLM to generate an image caption.

Then, Llama 3.1 70B generates a prompt from the caption text: Image
Read 8 tweets
Sep 2, 2024
How to train a FLUX LoRA on your own images using @FAL

Full tutorial and video 👇 Image
@FAL 1. Collect 10-20 selfies or photos of yourself in different poses and backgrounds.

2. • Use the same prefix (e.g., "Heather1, Heather2") for easy retrieval.

3. Optional: Put your images in a folder or zip file.
@FAL 4. Click "Train a FLUX LoRA" on the Model Gallery page: 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!

:(