I've been chasing this for ages,
Expand a frame from my favourite aesthetic models while keeping the exact visual language, colour palette, composition style, mood, and worldbuilding is much harder.
I think I'm finally getting somewhere with GPT Image 2
prompt in next post
THE BLACK KNIGHT - Trailer 1080p [1m21s]
Time-travelling Black Comedy with a twist! (or 3)
All made in @LumaLabsAI Luma Agents using Uni-1, GPT-2, Seedance2, Elevenlabs. Soundtrack SunoV5.5
#LumaCPP
Impossible not to love Reve this simple yet genius feature. It transforms any image into a Lego-like canvas, giving you the freedom to edit, move, or delete every detail. 😱
https://t.co/iKkBhozx8V
Today, we’re launching Reve 2.0, the best 4K image model in the world.
We invented a new way to generate and edit any image using precise layouts. For the first time, it’s possible to create images you can touch.
@missalsimpson I like this editing technique. Though the subtle freezing cut that kept the camera moving continuously in Drones of Suburbia had a certain grace.
Callista was a good worker. She did well handling The Black at the Blubber Mill, but after the accident she was never quite the same. Now she lives to do anything she needs to survive while giving carriage patrons a lesson in poetry. #TheUnderworks
Work done with @Kling_ai 4k and @runwayml Aleph 2.0 to change character details last minute.
JUNKYARD KING ⚔️ EP1 - "Training Day"
Here’s what I learned making the latest episode of my 80s-inspired action-adventure fantasy buddy comedy about a kid, a glowing sword, and a mechanical crow.
A thread 👇
@Trickettaro Yeah, it’s pretty funny how GenAI developers figured out they could sell the tool and the training for it too. Like buying a video camera without a manual and just figuring it out from friends’ tips, since we’re on the subject of cameras. 😄