Making Things With AI

A plain, honest tour of generative media. How image models actually work, why hands and text used to break and what that predicts, how people really edit, what video still cannot do, the consent line on voice cloning, where generated music stands legally, and the genuinely unsettled question of who owns any of it — plus the labelling duties that are already law in several countries.

1. 1What the model is actually doing7 minAn image model does not draw. It removes noise from static, over and over, steered by your words.
2. 2Writing a prompt that gets what you meant7 minWrite the caption that would have sat under the picture you want, not a wish list of adjectives.
3. 3What hands and text told us7 minThese models nail local texture and fail global constraints — anything you must count, spell, or match across a picture.
4. 4Editing what you already have8 minPrompting gets you a starting frame; masks, denoise strength and structural inputs get you a finished image.
5. 5Video, and what it still cannot do8 minVideo models produce shots, not films; plan the edit and budget for the takes you throw away.
6. 6Voice, and the line you do not cross9 minClone a voice only with the owner's informed, written, revocable consent — and tell the audience before they believe it.
7. 7Music, and whose music it learned from8 minGenerated music can still infringe a real melody, and "a model wrote it" is not a defence.
8. 8Who owns it, and who has to say it is AI12 minOwnership of AI output differs by country and is genuinely unsettled; the duty to label it is not.