The Internet is full of AI slop. But that does not mean AI cannot make good content.
One thing is certain - low effort content is never valued anywhere. Good news? you do not need a Ph.D. in 2026 to make your AI ad look premium. A few simple things decide whether your video looks cheap or classy.
This is what we have learnt making ads
Three artists worth watching this week
Video models this week
Seedance 2.5 - the long single-take. Up to 30 seconds in one native pass at full 1920x1080, no upscale step, and up to 50 references per generation (30 images, 10 video, 10 audio) against 2.0's nine images and three clips. New in 2.5: a single voice, music or sound-effect track drives pacing, beat-matching and lip-sync across 10+ languages. Region-level editing swaps a subject or replaces the music while the rest of the frame stays untouched. Reach for it when the brief is one continuous 20–30s spot.
MiniMax H3 - the reference-heavy multi-shot. 5 to 15 seconds at up to 2K with native stereo audio, and one generation takes up to 9 images, 3 video clips and 3 audio files. It reads each for a different thing: who the character is, how they move, how the camera behaves, what voice comes out. It also does multiple shots inside one clip, which is why our jewellery sequence came out of it at a fraction of Seedance's cost and turnaround.
Wan 3.0 - the flexible-input one. 30 seconds in one pass at up to 1080p, holding up to 20 references across image, video, audio, documents and webpages. Hand it a deck or a PDF and it reads the content and builds a sequence from it. You can also reselect a time interval and regenerate only that part.
Image models this week
GPT Image 2.5 Sunburst - the precision tier. Built for premium work that needs tight control across edits, with strong subject preservation from reference photos, output to 3840px and transparent backgrounds. Changes hold across a long edit chain instead of drifting. This is the campaign-creative and product-shot model.
Nano Banana 2 - worth a naming note in the issue, since most people still say Nano Banana Pro and the board lists this as gemini-3.1-flash-image. it is what our image skills are built around. Speed and reference handling are why it survived our pipeline while higher-ranked models did not.
GPT Image 2 (medium) - the settled one. When you need a result you can predict rather than a result that might be better, this is the one.