/TRAINING

AI training that doesn't suck.

Six sessions on the real stack — not last year's demos. 50% learning, 50% laughing, 100% hands-on. By the end, your team can ship a model, render a video, and — the part nobody teaches — know when not to use AI at all.

Book a scope call → Download the overview
FORMAT
In-person + remote
SESSIONS
6 core + 4 advanced
DURATION
~10 hours core
COHORT
4–12 people
/WHO THIS IS FOR

/ BUILT FOR

Working professionals — directors, designers, editors, producers — who already ship creative work and want to integrate generative AI into a real, deadline-bound pipeline.

You don't need to be technical. You need to be curious, somewhat skeptical, and willing to make the bad first draft.

/ WHAT YOU LEAVE WITH

  • A working AI image pipeline integrated into your existing stack
  • One custom-trained LoRA in your studio's style
  • Practical literacy on video models — Seedance, Veo, Kling, Wan, LTX
  • An honest map of what to use, what to skip, and why
  • A finished piece made with everything above
/CURRICULUM

Six sessions, in order.

Foundations through hands-on production, ending in a shipped piece. Each session builds on the last. Every new concept anchors to something your team already knows — Photoshop, After Effects, Premiere. Full session-by-session breakdown in the PDF.
01 / 06
GROUNDING — The landscape, honestly mapped
Where this technology actually is — and where the marketing departments would like you to think it is. Vocabulary, model families, and the studio-level decisions you'll be making across the next six weeks.
FOUNDATION
02 / 06
TOOLS — Picking the right tool, hardware reality, IP basics
A decision framework for choosing models. What runs locally, what runs in the cloud, what costs what. The IP basics every working creative needs before shipping a single AI-assisted frame.
FOUNDATION
03 / 06
IMAGE — Prompting, editing, consistency that scales
Hands-on with Midjourney, Flux, Nano Banana Pro, Seedream, Qwen-Edit. Translating Photoshop muscle memory into a new vocabulary. Where AI saves hours and where it eats your day.
WORKSHOP
04 / 06
VIDEO PT. 1 — Single shots: i2v, start frames, model personalities
The video model stack — Runway, Sora, Veo, Kling, Hailuo. How to think about i2v vs t2v, model personalities, the craft of the start frame, and the surprising places these models break.
WORKSHOP
05 / 06
VIDEO PT. 2 — Stitching shots: sequences, consistency, editing handoff
Going from one good shot to a finished sequence. Character and style consistency across shots, transitions that don't betray the pipeline, and how to hand the result to an editor without breaking everything.
WORKSHOP
06 / 06
ADVANCED — V2V, camera control, hybrid workflows
The harder moves. Video-to-video transformations, explicit camera control, and hybrid workflows that mix traditional pipelines with AI generation. The end of the core program — and the start of the advanced track if you want it.
WORKSHOP
/OPTIONAL DEPTH

Going deeper.

Four optional sessions for studios going deeper into custom training and self-hosted production. Adds ~8 hours. Recommended if your team will own the pipeline long-term.
07 / 10
COMFYUI FOUNDATIONS — The control layer. Including no-GPU paths.
ComfyUI from scratch — including hosted options like ComfyCloud and Floyo so the team can start without buying hardware. Node graphs, the mental model, and the first useful workflows.
ADVANCED
08 / 10
PRODUCTION COMFYUI — Real pipelines. Batching, real scale
Production-grade ComfyUI workflows. Open-weight video pipelines (Wan, LTX), batching strategies, API integrations, and how to stop hand-crafting every frame.
ADVANCED
09 / 10
MODEL TRAINING — LoRAs for your studio's IP and brand consistency
Custom LoRA training for client IP, brand looks, character consistency. We train one together in your studio's style. You leave with a working, reusable model that's actually yours.
ADVANCED
10 / 10
COMMERCIAL WORK — IP, ethics, and shipping it.
The legal-and-real talk. Practical IP checklists, the ethics conversations clients now expect, and what shipping commercial AI work actually looks like in 2026 — with real scenarios, not hypotheticals.
ADVANCED

The advanced track is its own conversation. Most studios start with the core six and add advanced sessions later — once they know what they actually need.

/PLATFORMS COVERED

The current stack, honestly assessed.

This list updates every quarter — because the landscape does. You'll leave knowing which to use, which to skip, and which to keep an eye on.

Image / generation

Core stack — refreshed each cohort
Midjourney Flux Nano Banana Pro Seedream GPT Image Ideogram

Video / generation

Core stack — refreshed each cohort
Veo Kling Seedance Runway Hailuo LTX

Advanced / self-hosted

Advanced track only
ComfyUI Wan Civitai HuggingFace Custom LoRAs
/NEXT STEPS

Let's see if this fits your team.

Thirty minutes. Tell me about your studio, your timeline, and what you're actually trying to do. I'll tell you whether this program is the right move — and what you'd do instead if it isn't.

Book a scope call → Download the overview
01 / SCOPE CALL

30 minutes

A real conversation. Your goals, your stack, your team. No deck.

02 / PROPOSAL

Within 1 week

A short, specific proposal. Curriculum tailored to your work, fixed price.

03 / KICKOFF

2–4 weeks out

First session locked. Materials sent. Your team starts before week one.