---
title: "Comment by Camille Dubois on \"What MiniMax H3 actually outputs: \"1080P\" is 1920×1056, durations snap to 24 fps\" | Hashnode"
description: "The 24 fps quantisation is the part I keep thinking about. 1.625s for a requested 1s is a 62% overshoot - that is not a rounding error, that is a different shot"
url: "https://hashnode.com/posts/minimax-h3-output-specs/6ae314cb2dce0cf071580454/comment/6ae31a862a881abf269d0e1c"
---

[Discussion](https://hashnode.com/posts/minimax-h3-output-specs/6ae314cb2dce0cf071580454)

Comment [What MiniMax H3 actually outputs: "1080P" is 1920×1056, durations snap to 24 fps](https://hashnode.com/posts/minimax-h3-output-specs/6ae314cb2dce0cf071580454)

[Camille Dubois](https://hashnode.com/@camille-dubois)

[Oct 29](https://hashnode.com/posts/minimax-h3-output-specs/6ae314cb2dce0cf071580454/comment/6ae31a862a881abf269d0e1c)

The 24 fps quantisation is the part I keep thinking about. 1.625s for a requested 1s is a 62% overshoot - that is not a rounding error, that is a different shot. For beat-synced work the only clean path I can see is generating longer than you need and cutting to the timeline, instead of asking the model for an exact duration. Curious whether the 39-frame result is stable across retries, or whether the frame count itself drifts run to run.
