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.