AI Mastery

Video
generation.

From a single idea to a finished scene.

With Mr. Grateful

Grateful you're here.

The arc with me

This is AI Mastery.

01
Image generation
02
Video generation

Last class we made the picture. Today we make the picture move.

Today

Three things.

01
See the opportunity
02
Learn the framework
03
Build one live
What we'll use

One home base.
One thinking partner.

Higgsfield
Where we generate. Every major model lives inside it.
Claude
Where we shape the prompt before we generate.
Seedance 2.0
The model doing most of the heavy lifting today.
The model we'll work with

Seedance 2.0.

Consistency through chaos
Holds a character steady even through wild motion.
Up to 9 references
Characters, places, and props in a single generation.
Native audio
Motion, sound, and speech generated together with lip sync.
Multi-shot
Several beats in one clip while the world stays coherent.
Physics-aware
Weight, momentum, and contact that feel real.
Ad-ready
The engine behind Higgsfield Marketing Studio.
The problem we'll solve

You have the ideas.
Video felt out of reach.

What you'll walk out with

By the end you will generate video three different ways. And you will understand the principles well enough to do it a hundred more times on your own.

Before we dive in
  • Strange results may show up. That is fine.
  • We may get a false restriction on something safe.
  • The goal is creative confidence and problem solving.

We build live together. Feel free to make mistakes. That is the whole point.

01

The opportunity.

And the responsibility that comes with it.

Gallagher / MEDVi visual
Case in point · Matthew Gallagher of MEDVi

Real founders are
building real businesses
with this.

The power is real. So is the responsibility. Realistic AI humans demand consent, disclosure, and intention behind every video.

My own use case

The Sacred Act.
Three different ways.

Type one

UGC.

Made in Higgsfield Marketing Studio. An AI character talks to camera about the product. Fast, social, and surprisingly convincing.

Sacred Act UGC clip
Creative content clip
Type two

Creative content.

Image to video, then edited in Premiere Pro. This is where a still becomes motion and a human hand shapes the final feel.

Type three

Long-form
commercial.

Multi-edit, built from characters, scenes, and post production. Many shots, many cuts, one story. The deep end of what we'll point at today.

Long-form commercial clip
Just for fun

Templates, Seedance, and a few wild prompts.

Template output
Skill-prompted output
Image-reference output
Friends' AI video work
Creators I know

Different people.
Different intentions.

Creator example one
Creator example

One.

All the same principles.

It comes down to two things.

Your use case. And your intention.

02

The framework.

Three ways to generate. Four levels to climb.

Three ways in

Every video starts
one of three ways.

Text to video
Words in. Video out. The most freedom, the least control.
Image to video
Animate a still. Far more control over the look.
Video to video
Existing footage in. Transformed footage out.
What you feed each one

The variables.

Text
A call-out shot prompt
Image
Character sheet, environment sheet, storyboard
Video
Recorded or generated footage to swap and edit
You already know this

S A S

Subject + Action + Setting. The same prompt that built your images builds your video.

Let's start one generating.

Level one · text to video

The basic template.

Template
SAS: [Subject] + [Action] + [Setting]
Example
A golden retriever puppy chases a red ball across a sunlit backyard.

You learned this from image generation. Watch how cleanly it carries over.

Level two · favorite activity

Add what video gave us.

Template
SACSS: [Subject] + [Action] + [Camera] + [Setting] + [Sound]
Example
A golden retriever puppy chases a red ball, slow dolly tracking alongside it, across a sunlit backyard, with soft grass crunch and a distant lawnmower hum.

Video moves and video speaks. So we add camera motion and sound to the same backbone.

Camera vocabulary

The words that move the camera.

Dolly in / outCamera physically moves toward or away from the subject.
Truck left / rightCamera slides sideways, parallel to the subject.
PanCamera rotates left or right on a fixed point.
TiltCamera rotates up or down on a fixed point.
ZoomLens changes focal length. Feels different from a dolly.
Push in / pull outIndustry shorthand for dolly in and dolly out.
OrbitCamera circles around the subject.
TrackingCamera follows the subject as it moves.
CraneCamera rises or drops vertically through space.
HandheldSlight natural shake. Raw and human.
StaticLocked off. No camera movement at all.
FPV / POVFirst-person view, as if through the subject's eyes.
Close-upTight on the face or a single detail.
MediumWaist up. The conversational distance.
Wide / establishingFull scene. Sets the place and scale.
Over-the-shoulderFrom behind one subject, looking at another.
Bonus · cinematic prompt language

Grow your camera vocabulary.

  1. Eye Candy, clips organized by cinematic keyword, at eyecannndy.com
  2. ChatGPT, turn an image you love into a prompt as JSON
  3. The seedance-director skill, your shortcut
The gift

Let it write the
cinematic prompt.

Talk to the skill about your idea. Copy the prompt. Then use your own eyes before you hit generate.

Download the skill file
Control the timing

Direct it beat by beat.

Template
[0–4s]: [Subject] + [Action] + [Setting] + [Camera] + [Sound]
[4–6s]: [Subject] + [Action] + [Setting] + [Camera] + [Sound]
[6–8s]: [Subject] + [Action] + [Setting] + [Camera] + [Sound]
Example
[0–4s]: Puppy sits still in the grass, static close-up, birds chirping.
[4–6s]: Puppy spots the ball and bolts, camera whip-pans to follow, paws thudding.
[6–8s]: Puppy catches the ball and shakes it, slow-motion, triumphant little bark.

The skill adds these for you. This is how you control the timing of what happens, and when.

The real workflow

How the pieces fit.

Story
Write it first.
Images
Characters, places, props.
Scenes
Generate one by one.
Stitch
Edit in post.
A human skill worth keeping

Editing is where the
spirit lives.

We go deep on that in an advanced class. Today, just know it matters.

Editing, defined

Cutting, ordering, pacing,
sound design, color.

Automatic
A template or beats in your prompt handle it for you. Fast, no manual control.
Manual · beginner
On mobile, hands on the timeline, low friction. CapCut or Instagram Edits.
Manual · advanced
On desktop, full control over every frame. Premiere Pro or DaVinci Resolve.
Today builds on last time

Everything from here needs images. Characters, environments, products. Let's settle any image-generation questions before we lean on it.

Three reference assets

The images that steer a scene.

Character sheet
Character sheet
Environment sheet
Environment sheet
Prop or object
Prop or object
Put them together

Combine them
into a storyboard.

Take your character, your environment, and your prop. Feed them in as references and ask the image model to lay them out as a storyboard. Now you can see the whole scene before you ever animate it.

Using the reference images, create a [number]-panel storyboard of [character] in [environment] using [prop]. Show the sequence: [beat 1], [beat 2], [beat 3]. Keep the same character, lighting, and style across every panel.
Storyboard layout
Stay organized

The Elements tab.

In the upload box, open Elements. Load your images sorted by character, location, and prop. Consistency and easy reuse, in one place.

Elements tab screen
Level three · image to video

Add ingredients.

  1. 01
    One ingredient.
    Add a prompt and upload one reference image.
  2. 02
    Three ingredients.
    Story, character, environment, storyboard, call-out prompt.
  3. 03
    Swap for control.
    Trade storyboard and call-out prompt to shape the shots.
Know the ceiling
  • Too many characters at once.
  • Environment plus storyboard plus long text.
  • Everything crammed into one generation.

Overload the model and it loses the plot. Give it room to stay coherent.

Three pro tips
  1. Skin too glossy? Add "no 3d, no cartoon, no vfx" to force photorealism.
  2. What you do not specify gets decided for you. Sometimes that is a gift.
  3. The 180 degree rule. Avoid back-to-back shots flipped a full 180.
Example output
Level four · frames to video

Two frames.
The model fills the gap.

Generate a first frame and a last frame. The model invents all the motion in between. This is called interpolation, and it is the highest control you have over a single clip.

First frame
Last frame
Video to video

Google Omni is the best at this.

Edit real footage with natural language. Swap a character, a place, an object. Kling was the king here, and is still strong, but Omni just took the lead.

One honest catch. The mouth on talking footage is rough. Use it for everything except dialogue. See deepmind.google/models/gemini-omni

Format one

Transformations.

Normal, then chaos, then back to normal. A calm scene breaks into something wild, then resolves. The structure carries the surprise.

Format two

First-person POV.

A single continuous point of view. Be explicit about what the camera is not doing. No cuts, no zooms, just natural head movement.

Now the easiest thing of all.

The climax · Marketing Studio

Paste a link. Get an ad.

Paste product link
01
Drop your link.
Your product page is all it needs.
Pick a character
02
Pick a character.
An AI creator to front the ad.
Generate UGC
03
Generate.
Real-feeling UGC about your product.

That's it.
That simple.

If you remember one thing

Same principles.
Your intention.

03

Your assignment.

Make one video about your company, your product, your service, or your offer. Bring it next time.

The picture moves now.

Go make something.

16 / 50