@designaimotioni
iAccount based inAustralia
About this account
- Account based in
- Australia
- Connected via
- Web
Account-level information from X, not a live location or the device used for a specific post.
𖤣
Joined November 2024
- Tweets397
- Following586
- Followers106
- Likes984
DesignAIMotion retweeted
GPT-6 Astra + Scenario MCP turned 9 crappy photos into a fully interactive 3D room.
No measurements. No scans.
Just 9 phone photos of our office.
Astra understood the spatial layout and rebuilt the geometry in Blender.
Scenario MCP pulled the real materials straight from the photos, including the carpet, wood and metal surfaces.
An hour later, we were walking through our actual office in 3D.
100 AI Styles in 100 Days.
Day 37/100
🎨 Art Style: Minimalist black and white doodle — hand drawn lines, rough textures, and quirky simplicity.
Shiba is taking his driving test today. 🚗🐕
Everything is going surprisingly well… despite a little chaos at the roundabout. 😂
Created with Seedance 2.5 on @PixVerseCreator @PixVerse #Pixversecpp
🤖 Made with AI
Great Artstyle
DOUBLE FEATURE
Script/Story: @PocketFM_App
Video: Seedance on @higgsfield
Music: @sunomusic
Directed by: @luthe2nd
My first short film following a Father and Son with a Magic TV Remote.
DesignAIMotion retweeted
Space and time reconstructed in 4D
Is this how higher dimensional beings see us - every moment at once?
Starting to understand what Vonnegut meant by humans being “great millipedes” - clearly it applies to our four legged friends too!
Geolocated 2d video → per frame 3d gaussians → each left precisely where & when it happened
DesignAIMotion retweeted
The all-new Dreamina AI web experience is LIVE!
Every imagination deserves cinematic expression.
🎬 Cinema-grade skills and master workflows, right at your fingertips
▪ Filmmaking — Textbook cinematography skills, delivering theater-grade quality frame after frame.
▪ Advertising & marketing — Brand-grade workflows, bringing every concept to blockbuster quality.
▪ Creator content — The production process behind breakout short-form hits, out in the open and ready to learn.
📃 A rebuilt creation flow
▪ Dual entry points: Generate and Canvas—switch whenever the work calls for it.
▪ A smarter AI agent: multi-session management, every step visible start to finish.
▪ One integrated canvas: text, image, video, and audio—full control across the whole process.
Film-grade creation, now within reach.
✨ Try it now: dreamina.capcut.com/ai-tool/…
⏰ Giveaway: Repost + comment on this post within 12 hours—the first 300 get 1,000 credits.
#DreaminaAI #DreaminaAIweb
DesignAIMotion retweeted
🚨 WE’RE LIVE!
It’s MOOZI MONDAY
🎬 Moozi | TECHNOCRACY
✨ WORLD PREMIERE by @MooziMusic
🕗 8PM ET | 5PM PT
Step into the world of TECHNOCRACY and experience it together with us for the first time.
Tune in. 🤖
⚡️ST^TIC Follow us @aimusicvideo Watch live now nitter.cf/i/broadcasts/1mGPaZmrR…
The Skill 99% of AI Filmmakers Are Missing
youtu.be/9oCppy1gZpo?si=OE6h…
DesignAIMotion retweeted
This influencer doesn't exist.
AI Samson built an AI woman that keeps the same face, voice, and body across every clip.
He says the whole setup took under 20 minutes.
He starts by giving Claude a personality: a playful, adventurous travel creator with blonde hair, freckles, and a septum piercing. Those details become the visual rules for everything that follows.
02:31, one portrait becomes a character sheet with front, profile, three-quarter, and full-body views. He reuses it across six different images, and her facial features, piercing, freckles, and proportions survive.
Then the still image starts moving. Seedance 2.0 animates the shot, while a saved voice keeps the audio consistent between generations.
07:54, a driving video lets Kling 3.0 Motion Control transfer his acting to the character. She copies the performance while he keeps his face and gender off camera.
This produces a convincing first batch. Running the character for months creates another problem.
Her face may stay stable while her eyes lose focus, the voice hits the line with the wrong expression, pauses land in strange places, or head movement changes from one campaign to the next.
ArcCourier's article stores those decisions outside the prompt:
> avatar_id anchors the visible identity
> voice_id preserves the selected voice
> character/bible.md records gaze, expression, pacing, pauses, and head movement
> Claude checks every campaign against those rules
> a human approves the JSON before any credit is spent
MakeUGC handles the actor, voice, and render. Claude Code prepares the local files, and a Node.js script connects the two after approval.
Repeated failures go back into the bible as new rules.
Same face forever. The acting is what improves.
This video is larger than Cloudflare's 512 MB cache, so it can't be played through. More donations are needed to cover a larger cache. Donate
DesignAIMotion retweeted
This is an absolutely fascinating way to visualize human movement tbh. Had to run a few more tests. Made with Sentinel.
DesignAIMotion retweeted
Fun prompt for you to play with this weekend - papercraft cube toy! Turn your pet or anything really into it.
I’d love to see your experiments with it
Works best with GPT Image 2.5
I used Firefly Boards for mine
prompt and more examples👇
🤖 Made with AI
AI #DINOSAUR PROMPTS - #eBook 01
Unlock a prehistoric world of endless creative possibility with AI Dinosaurs Prompts: Create Amazing AI Images!
OVER 800 inspiring prompts designed to expand your knowledge and push the boundaries of AI art generation.
ko-fi.com/s/2721d41fd1
youtu.be/vp7xoPeWzEw?si=_evH…
Will be exploring more Age of Beyond in the future on my channel.
I love creating dystopian & utopian worlds on there.
Another way to get the FREE PDF eBook on AI Image prompts
patreon.com/DesignAIMotion/p…