Pouring coffee

Continuous slow-motion pour, the level rises plausibly and backlit steam rises throughout.

Correct low-viscosity stream, turbulence and steam, no artifacts.

Accurate stream breakup, refraction and steam dispersal, no artifacts.

Accurate turbulence, crema forms with correct surface tension, no gel artifacts.

Continuous pour with plausible refraction and rising steam.

Continuous pour with plausible refraction and steam, no looping artifacts.

Accurate turbulence, foam and steam, no artifacts.

Continuous pour into clear glass with a level that rises plausibly and backlit steam. Cuts to a second angle at about 3.5 seconds, which the prompt did not ask for.

Continuous slow-motion pour into clear glass, with the level rising and backlit steam, in one take.

Continuous pour with a rising level and backlit steam, shown as three shots (side, top-down, steam) rather than one take. Cuts measured with ffmpeg.

Accurate low-viscosity turbulence and foam; no gel artifacts (better physics than Sora on this one).

Pour stream is oddly clean with almost no splash turbulence or droplets against the glass wall.

Pour stream thins and disappears from frame with no pouring vessel ever shown (common product-shot framing, not a strong defect) and surface bubbles look somewhat static. Verified via frames: stream absence at end is real but mild, treated as minor rather than severe.

FAILURE MODE: coffee inside the cup forms unnatural gel-like ribbed layers instead of turbulent mixing (00:02.5-00:07.0), despite a good initial pour stream.