Hybrid filmmaking: traditional craft and applied AI
Learn the craft that makes a shot mean something, extend it with controllable AI video, and finish a short film that works as a story rather than as a technology demonstration.
Free
12 modules
8 weeks
22 to 28 hours
What you will learn
- Plan and shoot an editable scene using story, composition, lenses, lighting, blocking, sound and continuity.
- Design a coherent AI visual world and compare Higgsfield, Kling and alternatives on a production rubric.
- Integrate generated and live-action shots through matching, compositing, sound, colour and motivated editing.
- Document consent, licensing, synthetic-media provenance and the production decisions behind each shot.
- Finish and present a short film that works as a story on its own terms.
- Deliver a master, a vertical derivative and captions against a platform specification.
Your instructors
Patrick Kriwanek
View profile, Patrick Kriwanek on LinkedIn
Course content
Method step 1, Profile
Dramatic intention, shot purpose and the difference between a beautiful image and a useful one.
- What a shot is for
- Reverse-engineer a scene and write the treatment
- The treatment and beat sheet
Method step 2, Build
Exposure, lens, light and composition, learned as meaning rather than as settings.
- Exposure, lens and light as meaning
- Shoot a nine-image study of one subject
- The contact sheet and camera report
Method step 2, Build
Shoot coverage that cuts together, with motion and light doing narrative work.
- Coverage that cuts together
- Light and shoot a two-beat scene twice
- The shot list and lighting diagram
Method step 2, Build
Get a usable performance and clean dialogue, with consent and continuity documented.
- Directing people and recording sound
- Rehearse and record one performance scene
- Release forms and the continuity log
Method step 2, Build
Cut the footage twice, and learn what rhythm alone can change.
- Selects, assemblies and cut logic
- Edit the scene twice, with two different rhythms
- The delivery specification
Method step 2, Build
Decide shot by shot what to shoot, generate, composite or previsualize, and what each choice costs.
- Shoot, generate, composite or previsualize
- Convert the treatment into a hybrid shot plan
- The hybrid source matrix
Method step 2, Build
Build a world that holds together across shots the model generates separately.
- Art direction beats isolated prompts
- Build the continuity bible and six keyframes
- The continuity bible
Method step 4, Measure
Compare models on accepted shots and cost rather than on novelty.
- What actually controls a generated shot
- Generate the same three-shot sequence in three models
- The model comparison rubric
Method step 2, Build
Match motion, grain, light and colour so the cut is a story decision rather than a seam.
- Matching generated and photographed images
- Build one hybrid sequence
- The integration notes
Method step 2, Build
Build a full sound pass, with licences and consent recorded for every element in it.
- Sound design against wallpaper
- Build the complete sound pass
- The cue sheet and consent record
Method step 3, Deploy
Picture lock through to a master and a vertical derivative that pass quality control.
- The finishing pipeline
- Finish the locked cut and export both versions
- The QC checklist and archive structure
Method step 5, Document
Screen the film, defend the decisions, and publish the case study behind it.
- The case study behind the film
- Screen the film, take critique, and revise
- The BTS breakdown and delivery checklist
Requirements
- A phone or camera, and a computer that can run an editing application.
- One story you want to tell, in 60 to 180 seconds.
- Three hours a week for eight weeks, plus filming and generation time.
- The right to film your locations and participants. The labs supply the release forms.
About this course
This course begins with story, photography, cinematography, sound, performance and editing, and only then asks when to shoot, when to generate, when to composite and when to leave a shot alone. That order is the whole argument: craft decides whether a shot means anything, and the tools decide how it gets made.
Patrick Kriwanek, Academic Dean at The Berkeley Film School, leads the five craft modules. Roan Weigert records the applied-AI track, and his published book on applied AI in media production is the spine of that half of the subject matter. Both critique the capstone.
Twelve modules run the same shape throughout: a recorded lesson, a guided lab on your own footage or approved material, and one artifact you keep. Model comparisons are recorded as replaceable labs, so a new release dates one recording rather than the course.
The capstone is a finished 60 to 180 second hybrid film plus the evidence behind it: a treatment, a shot list, a lookbook, a continuity bible, a generation log, a cue sheet, a rights and provenance record, and a behind-the-scenes breakdown of what craft and what AI each contributed.
Completion record
Finish Hybrid filmmaking: traditional craft and applied AI and your record is issued the same moment
Ticking the last lesson issues it. It arrives with your name on it, downloads as a PDF or an image, and carries a reference that anyone you send it to can check on this site.
What is printed on it
- Your name
- As it is on your account, with your photograph if you added one.
- The course
- Hybrid filmmaking: traditional craft and applied AI, and confirmation that all 36 lessons in it are complete.
- A reference
- Unique, permanent, and readable aloud over a phone.
- The date
- The day you finished, recorded when it happened.
Common questions
It is free. The first module of every course opens instantly, and one free account unlocks the rest of that course. Everything on this site is free to use.
A course completes when your workflow runs live and you have measured it. You record a baseline in module 1, launch the workflow into a working environment, then measure the same thing again. That pairing is what makes the completion record worth sharing.
Yes. The first module of every course plays for everyone, with a free account needed only from module 2.
Name, role, organization, and a few questions about the workflow you want to improve. It takes about a minute, and it is what lets the guided labs use your own workflow as the project.
One workflow you own, permission to change it, and the tools your team already uses. Applied AI infrastructure fundamentals also assumes a computer you can install software on, hybrid filmmaking assumes a phone or camera, and AI starter for small business runs on everyday business tools. Every course supplies sample data for the labs where your own material is restricted.
A one-page record inside the course. Before you launch, you note a baseline on time, cost, or quality. After you launch, you measure again. The sheet holds both numbers and the difference between them.
Instructor
Roan Weigert
Records all five courses
Hackathon judge and AI content creator, and host of the AI Insights San Francisco podcast. Writes this curriculum and records every core lesson.
Other courses
The other four courses
Each one takes a different kind of work through the same five steps. Pick the one closest to your job.
You buildA campaign-to-pipeline workflowApplied AI for go-to-market
One permissioned campaign-to-pipeline workflow, built on your own data and measured after launch.
You buildA responsible implementation packAI education, ethics and data compliance
Teaching and learning decisions first, then the policies, data rules and reviews that make them safe to adopt.
You buildA small AI service, deployedApplied AI infrastructure fundamentals
The whole picture of an AI system, taught to the depth one real deployment needs.
You buildTwo workflows in thirty daysAI starter for small business
Two safe AI workflows in daily use within thirty days, with the business result written down.
Start with module 1
Story, audience and film grammar
Open to everyone, with no account. You finish it holding a treatment, beat sheet and reference board.