I'm new to AI video
I want a clear workflow for creating my first serious AI video.
Good video.
Thoughtful tools.
Your next skill.
Learn to plan, make and refine AI video with a working builder. Practical production skills, useful automation, and fewer expensive mistakes.
One hour · Practical demonstrations · Live Q&A
Bring an idea.
We'll work through the making.
A place to start. Room to go deeper.
Select one of 3 hours workshops fitting your needs
I already work with AI and code
I'm comfortable with Codex, coding and AI development workflows, but AI video production is new to me.
I already make AI videos
I already generate AI video, but I struggle with consistency, references, camera control, physics, failed generations or excessive rerolls.
1 / 3
AI Video Starter
From Idea to Finished AI Video in 3 Hours
The goal:
By the end of the session, you should have created your own short AI video and understand how to repeat the process for your next project.
AI video tools are powerful, but for beginners the hardest part is usually not pressing Generate.
It’s knowing:
- where to start
- which tool to use
- how to turn an idea into something a video model can actually execute
- when you need reference frames
- how to fix bad generations
- how to turn separate clips into one coherent result
- and how to ensure it will not eat whole subscription (or several) for one shot
This is a 3-hour live hands-on workshop designed for people who want to stop experimenting randomly and learn a practical AI-video production workflow they can reuse.
You’ll work through the process step by step:
- Idea
- Shot Plan
- Reference Frames
- Video Generation
- Fix & Iterate
- Assemble
Who is this for?
This workshop is a good fit if:
- you are new to AI video
- you have tried one or two video-generation tools but don’t yet have a clear workflow
- you use AI casually but have never built a complete AI video
- you are a creator, marketer, educator, designer, filmmaker, founder, or simply curious about practical AI video production
- you want to understand the workflow instead of jumping between random tools and prompts
No coding experience is required.
This is not a coding workshop.
What you’ll learn
Turn an idea into a workable video plan
Start with a simple concept and break it into realistic shots instead of asking one model to create everything at once.
Create useful reference frames
Learn when to use:
- first frame
- last frame
- intermediate references
- image-to-video
- text-to-video
Choose the right generation approach
Understand how to decide which tool/model is appropriate for a particular shot instead of choosing only by popularity or price.
Generate your shots
Build several short video segments using your references and prompts.
Fix failed generations
Learn how to identify whether the problem is:
- the prompt
- the reference frame
- the amount of action in the shot
- camera movement
- the chosen model
Assemble the final video
Bring your generated clips together into one coherent short video and understand the basic finishing workflow.
What participants should bring
- a laptop
- one simple idea for a 10-30 second video
- willingness to experiment
You do not need to prepare prompts or reference images in advance.
NoteAI generation is probabilistic, so not every generation will work on the first attempt. Part of the workshop is learning how to diagnose and improve failed results rather than expecting every prompt to succeed immediately.
What participants leave with
You’ll leave with:
- new hands-on skills
- your own short AI-video project
- a repeatable production workflow
- example prompts and templates
- a tool/model reference list
- access to the workshop resource page
2 / 3
AI Video Builder
From Idea to Repeatable AI Video Production Workflow in 3 Hours
The goal:
By the end of the session, you should have built your own short AI video and a master practical AI code-assisted workflow you can reuse for future projects.
You’ll work through the process step by step:
- Idea
- Shot Plan
- References
- Generation Workflow
- Generate
- Diagnose
- Iterate
- Assemble
AI video production introduces a different set of problems than normal software or AI development.
It’s not only about calling a model.
It’s knowing:
- how to turn an idea into a structured set of shots
- how to create and manage reference frames
- how to choose the right generation model for each shot
- when to use UI tools and when code is more efficient
- how to organize prompts, assets, settings and outputs
- how to automate repetitive generation steps
- how to tune based on failed generations to reduce # of iterations
This is a 3-hour live hands-on workshop designed for developers and experienced AI users who are new to AI video production and want to build a more systematic, repeatable workflow.
Who is this for?
This workshop is a good fit if:
- you are comfortable with Claude, Codex, or other AI development tools
- you already build software or AI workflows but are new to AI video
- you want to be able build qualitative video without spending days to try different services
- you want to reduce cost of video generations
- you are interested in APIs, automation and repeatable production workflows
Vide coding experience is recommended.
This is not a beginner coding workshop. The focus is practical AI video production using Codex or Claude as part of the workflow.
What you’ll learn
Design an AI video as a production workflow
Turn an idea into clear shots, references and generation tasks instead of treating the whole video as one prompt.
Build and manage reference assets
Structure first/last frames, prompts, settings and outputs so they can be reused and iterated efficiently.
Choose between UI, API and code
Learn when a visual tool is faster and when code gives you better control, lower cost and repeatability.
Build generation workflows with Codex or Claude
Use AI coding tools to prepare generation requests, call APIs, organize assets and reduce repetitive manual work.
Diagnose failed generations
Identify whether the problem comes from the prompt, reference, model, shot complexity, motion or generation settings - and change the right thing.
Automate repetitive production steps
Create a more efficient workflow for repeated generations, asset organization and iteration.
Assemble the final video
Bring generated shots together into one coherent short video and understand where automation can help with finishing.
What participants should bring
- a laptop
- access to Codex, Claude or your preferred AI enabled coding environment
- one simple idea for a 10-30 second video
- willingness to experiment with different models and workflows
You do not need to prepare scripts, prompts or reference images in advance.
NoteAI video generation is probabilistic. Even a well-designed workflow will sometimes produce failed generations. Part of the workshop is learning how to diagnose the problem, change the right variable, and make the iteration process faster and more systematic.
What participants leave with
You’ll leave with:
- new hands-on AI video production skills
- your own short AI-video project
- a repeatable Codex/Claude-assisted production workflow
- example scripts and workflow patterns
- reusable prompt and reference structures
- a practical model/tool selection framework
- a more organized way to manage assets and outputs
- access to the workshop resource page
3 / 3
AI Video Production Lab
Stop rerolling. Start diagnosing. Learn how to get more predictable AI-video results with fewer failed generations.
The goal:
By the end of the session, you should have improved a real AI-video project or problematic shot and built a practical debugging workflow you can reuse to get better results with fewer failed generations.
You’ll work through the process step by step:
- Problem
- Diagnose
- References
- Model Choice
- Generate
- Compare
- Tune
- Finalize
AI video production often becomes frustrating once you move beyond simple generations.
The problem is no longer just creating a video. It’s creating the video you actually intended.
It’s knowing:
- why the camera moves differently from what you requested
- why characters, objects or environments change between frames
- why physics or motion break
- when a reference image is helping - and when it is hurting
- whether the problem is the prompt, the model, the shot design or the generation settings
- when to stop rerolling and change approach
- how to reduce the number and cost of failed iterations
This is a 3-hour live hands-on workshop designed for people who already have experience generating AI video but want more consistent, controllable and cost-efficient results.
Who is this for?
This workshop is a good fit if:
- you already generate AI videos
- you regularly need several attempts to get an acceptable result
- you struggle with character, object or environment consistency
- camera movement or motion often differs from what you intended
- complex shots frequently break
- you spend too much time and money trying different prompts or models
- you want a systematic way to diagnose problems instead of blindly rerolling
This is not an introductory AI-video workshop.
You should already be familiar with at least one AI video-generation tool and understand basic prompting or reference-image workflows.
Coding experience is not required.
What you’ll learn
Diagnose why a generation failed
Learn to identify whether the problem comes from the prompt, reference, model, shot design, motion request or generation settings.
Improve reference consistency
Use first frames, last frames and additional references more effectively to preserve characters, environments and important visual details.
Control camera and motion
Understand why models ignore or distort camera instructions and how to simplify or restructure difficult movement.
Break down complex shots
Recognize when you’re asking too much from one generation and split difficult scenes into more manageable shots.
Choose when to change the model
Learn when another prompt iteration makes sense - and when switching the model or generation method will save more time and money.
Iterate systematically
Use a simple process:
- Problem
- Hypothesis
- Change One Variable
- Generate
- Compare
instead of changing multiple things at once.
Turn improved shots into a final sequence
Bring the corrected generations together into a coherent short video and apply the same debugging approach across the full project.
What participants should bring
- a laptop
- access to the AI video tools you normally use
- ideally one problematic generation or short project you want to improve
- the original prompt and reference images, if available
- willingness to experiment with alternative models and approaches
If you don’t have a problematic project yet, an example will be provided during the workshop.
NoteAI video generation is probabilistic, and no workflow can guarantee a perfect result every time. The purpose of this workshop is to make the process less random: understand why something failed, decide what to change, and reduce unnecessary iterations.
What participants leave with
You’ll leave with:
- stronger hands-on AI video production skills
- an improved version of your own problematic shot or project
- a repeatable AI-video debugging workflow
- a checklist for diagnosing failed generations
- better reference-frame strategies
- a framework for choosing between prompt changes, model changes and shot redesign
- techniques for reducing unnecessary rerolls and generation cost
- example failure/fix cases
- access to the workshop resource page
Free practical 1-hour webinar
How to Create Quality AI Video Without Burning Budget
AI video can become expensive very quickly.
Multiple subscriptions. Credits disappearing after failed generations. Different models for different tasks. And no clear answer to a simple question:
What do I actually need to create quality AI video?
In this free practical webinar, I'll compare popular AI video tools and their real generation costs, explain a practical end-to-end production workflow, and demonstrate how strong results can be achieved without paying for every platform on the market.
- Free registration
- Live online
- Practical demonstrations
- 1 hour including Q&A
- falSeedance 2.5$4.73
- HiggsfieldSeedance 2.5$3.19
- falSeedance 2.0$3.02
- WaveSpeedSeedance 2.0$2.40
- HiggsfieldSeedance 2.0 Fast$1.50
- Atlas CloudSeedance 2.5$1.34
- Comfy CloudSeedance 2.0 Fast$0.62
- MidjourneyV1 video HD$0.47
- Will be revealed during the webinarQuality similar to Seedance 2.0$0.075
One 10-second 720p generation, priced on each vendor’s own published rate.
What we'll cover
Which AI video tools are actually worth paying for?
Compare platforms, models and different ways of accessing them.
What does a 10-second AI video really cost?
See the same type of generation compared across multiple services.
A practical AI-video production workflow
- Idea
- Shot Plan
- Reference Frames
- Video Generation
- Iterate
- Assemble
How AI can help before you generate anything
Turn an initial idea into a structured video plan, references and effective generation instructions.
A real low-budget production example
See a practical workflow that avoids maintaining an expensive collection of subscriptions.
How to stop wasting credits
Learn when to change the prompt, reference, model or the shot itself.
Live Q&A
Common workshop outcomes
Every session works the same way on a shot that is not behaving: look at what came back, work out which control is responsible, change that one thing.
AI builder, software engineering leader and hands-on AI video experimenter.
20+ years building software products, from first prototype through to systems that stay alive in production. 3+ years building with generative AI, and most recently a deep dive into AI video production.
That dive produced one useful finding: high-quality AI video does not require a high budget. It requires knowing which model to reach for, what to change when a generation fails, and which steps to automate so you stop paying for the same mistake twice.
- 20+ years building and shipping software products
- 3+ years building with generative AI, in production and not in demos
- Original science reels reached 166K and 185K views
- One reel reached 115K unique viewers, founder-reported
- Model costs measured against invoices, not marketing pages
Questions
Do I need to know how to code?
Not for AI Video Starter or AI Video Production Lab. AI Video Builder assumes you are already comfortable with code and Codex.
What do I need to bring?
A laptop and a working internet connection. You build during the session, so a machine you can install and sign in on matters more than its specification.
Will I have to pay for AI tools during the workshop?
Budget for a small amount of generation credit. The whole point of the session is keeping that number low, and the free tiers cover a lot of it.
Is the webinar a sales pitch for the workshops?
It is a working session with real numbers and live demonstrations. The workshops exist for people who want to build rather than watch, and the webinar stands on its own if that is not you.
How do registration and payment work?
Everything runs through Luma. You register there and pay there, and Luma sends the joining details.
Are sessions recorded?
Yes. The recording is shared with registered participants.
Individual support
Need help with your specific AI video project?
Not every problem fits a group workshop.
If you have a specific video idea, production challenge, workflow, automation problem or AI-video project you'd like to work through individually, you can request:
- 1-to-1 training
- AI video production consultancy
- Creating Ads for your product or helping you to create one
- Codex/Claude workflow setup or enhancement
- Project or failed-generation review
- Tool/model selection and cost optimization
- Custom AI-video production workflows
Tell me briefly what you're trying to build or what problem you're facing, and we can decide whether an individual training session or consultancy would be the best fit.