lesson 004: diverge your own work using the plnty styler
Lesson four is about diverging your own work: taking something you already finished and pulling new directions out of it, rather than generating from scratch. Owen starts with a Cinema 4D and Redshift render of a moody landscape, built around a custom SpeedTree tree, and transfers the style of three references onto it with the plnty styler. What makes it work is what survives: the crooked branches and leaf detail from the 3D stay intact through every restyle. From the favorite frame it runs close-ups, a Topaz upscale to 4K, and a five second Seedance 2.0 move, all in about ten minutes.
What's inside:
Intro
0:00
a cinema 4d and redshift render, three references, and where it's headed
Loading the board
0:29
the render plus three references: two photographs and a 2d illustration made in plnty
styler
0:59
subject and style canvases, the style transfer and object mixer nodes, and @image prompting
Settings + lock
1:40
quality high, aspect ratio auto, 1k, and the lock that auto-builds a frame
First transfer
2:14
the grass and the tree color move across, and the speedtree detail holds
Second transfer
2:54
swapping the style image: new mountain ranges and a cooler tone
Third transfer: halftone
3:28
the generated image as subject, the 2d illustration as style
close-ups
4:22
four macro shots out of one image, with a prompt to keep the tree in frame
Upscaling with Topaz
5:46
redefine over recovery and reimagine, creativity and texture kept low, 1k to 4k
Motion with Seedance 2.0
7:08
a plain prompt, the star to refine it for the model, then five seconds at 720p
Wrap-up
8:19
render to styles to close-up to upscale to motion, in about ten minutes
all
gen-ai
lessons
2the ai skill nobody teaches you: intuition
Lesson three is about intuition with AI: knowing when to push a model, when to let go, and which one to reach for in each moment. To make that concrete I carry a single idea from a sketch all the way to a finished product film, an imaginary handheld for running Claude Code away from the desk, built end to end inside plnty. It runs through image generation with Uni 1.1 and GPT Image 2, variations and styler for the design, a 3D model and a Cinema 4D hero shot, a video restyle shootout across Kling, Ray 2, Aleph 2 and Seedance, then an upscale, a Figma mock-up and the final presentation.
Welcome to plnty
Plnty is open for Early Access. Co-founder Yambo walks through what we've been building: a three-dimensional workspace that holds image, 3D, and animation in one infinite, collaborative canvas. It's built for the part of the work where you don't know yet, where you've got nine half-ideas open and you're trying to see which one wants to grow.