Video course
Craft better video, one lesson at a time
Learn framing, camera, light, prompts and delivery through short lessons and practice.
Ten levels of video craft and AI generation. Study a short set of cards, practise recall, then answer five questions. Free, with no account. Answers and progress stay in this browser; export a backup to keep them.
- Recall an answer before revealing it. Compare your response with the explanation and tell the course whether you remembered it.
- Each card links to its source. Craft principles are guidance; vendor capabilities are dated claims.
- Review cards return according to your answers. Coverage means seen, not mastered; review accuracy reflects your own assessments.
Take the course with you
Choose a level
1. What generation actually is
How a model turns a sentence into pixels, and what it is not doing.
- Diffusion, in plain terms
- Latent space
- Seeds and reproducibility
- What a prompt is and is not
- Why the same prompt gives a different result
2. Reading a frame
Shot size, angle, and what the framing says before anyone speaks.
- Shot scale and relative boundaries
- High, low and canted angles
- Point of view
- Lead room and composition
3. The camera
Camera travel, rotation, focus and zoom, with the differences made explicit.
- Pan, tilt, tracking and crane
- Zoom and rack focus
- Whip pans and reframing
- Camera trajectory conditioning versus a motion prior
- Parallax
- Dolly zoom, slider and jib
- Handheld and body-mounted stabilization
4. Light
Key, fill, backlight, colour and the work of shaping a scene.
- Key, fill, back
- Hard and soft, and what makes the difference
- Named setups
- Colour temperature
- Motivated versus decorative light
5. The lens and the look
Focal length, aperture, focus and matching a finished look.
- Prime and zoom lenses
- Focal length and field of view
- Aperture and depth of field
- Focus pulling
- Matching shots in a grade
6. Writing a prompt
Prompt decisions, a worked product shot and the limits of text control.
- Prompt decisions and a suggested order
- Text encoders and conditioning
- Sampling and guidance
- Why prompts are not exact instructions
- A worked fragrance prompt, with its choices separated
7. What models can and cannot do
Capability, reference versus first frame, and duration caps.
- Start and end frame inputs
- Native audio and negative prompt fields
- Open weights and API access
- Duration limits and model economics
- Identity and temporal consistency
8. Sound
Ambience, spot effects and music, and which tags a vendor documents.
- Sound layers and dialogue clarity
- Space outside the frame
- Documented voice tags
- Community music tags and their limits
9. Delivery
Aspect ratio, platform safe zones in real pixels, and where the subject goes.
- Aspect ratios
- Safe zones in exact pixels, per platform
- Why the safe box is not centred
- Permanent versus conditional overlays
- What crops when a platform re-frames you
10. Judgement
Provenance, licences, not established, and diagnosing your own failures.
- Training data and copyright uncertainty
- Open versus closed weights
- Diagnosing generation failures
- Separating a vendor claim from evidence
Your progress belongs to you
Course pages do not load analytics. Your answers are not transmitted to Shotcraft.
- No streaks, lives or leaderboard. Return whenever you want.
- No payment or account is required. Export your progress before clearing browser data.