The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
You don't get this kind of result from a single prompt.
You get it from building your own workflow. Here's mine ⬇️
For SECOND SKIN, I wanted the piece to feel like a fashion campaign, a product film and an organic body-horror visual system at the same time. Not just “AI video”, but a full visual direction pipeline where every step has a specific role.
The process behind it:
· Editorial character and outfit image creation in ComfyUI using Z-Image, a modified SeedVR2 upscaling setup with SkinDiff, and my own PERSONA custom nodes for character creation.
· GPT Image 2 for archetype exploration and character sheet development.
· Caimera for campaign development, fashion editorial stills, product direction, LLM-assisted concept expansion and video scripting. (get a 50% discount in the first comment link 😉 )
· Dreamina AI AI OCTO with Seedance 2.0 to animate the stills and typographic title sequences.
· Final upscaling with Starlight 2.5 from Topaz Labs Labs. Exquisite! 😍
· Final edit, compositing and polish in DaVinci Resolve.
The important part is not the list of tools.
The important part is knowing what each tool is good at, where it breaks, how to connect it to the next stage, and how to keep the creative direction intact through the whole chain.
That is where AI production starts becoming professional.
Not faster random output.
A controlled system.
A workflow with taste.
A pipeline that can repeat quality.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Challenges
View all
Related posts
What happens when you take a hero frame from an AI-generated video and push it back into an image edit model?
This weekend I took a still from a recent Seedance 2.5 piece I made —depicting a solo mountaineer in a harsh alpine environment — and ran it through Midjourney's new v8.2 edit model to see how far I could iterate on a single frame without regenerating from scratch.
Tested wardrobe swaps, environment shifts, and style transfers.
Video walkthrough of the process coming in a separate post.
This looks cool
Some quick mockups for Relay, an AI infrastructure platform concept built around model routing, observability, and performance.
Exploring what a mobile command center could look like for teams managing multiple AI models, with a focus on clear data, fast decisions, and a developer-first UX.
Product design, mobile UI, AI tools, and a little systems thinking all in one.
the blue dots and orange blocks pop. did you build this in Framer?
My first digital product is here! 🔥
The Unique Characters (Vol. 1) is a collection of 17 original AI characters, each with a unique fashion wardrobe, multi-angle character sheets, and custom-designed voice.
https://contra.com/products/kcbvZ9NN-the-unique-characters-vol-1-17-ai-characters-for-filmfashion
