SyncAI.news, a Varaisys broadcasting
When a Larger Guidance Scale Repairs Text-to-Video Failures and When It Does Not
TK

Taewon Kang, Matthias Zwicker

· 1 min read

ResearcharXiv cs.CV

When a Larger Guidance Scale Repairs Text-to-Video Failures and When It Does Not

arXiv:2611.23025v1 Announce Type: new Abstract: When a text-to-video diffusion model ignores part of a prompt, the usual first fix is to raise the classifier-free guidance scale. This paper is a measurement study of when that fix works. On Mochi, the same increase repairs failures on rare compositions ("a snowy beach") beyond what generating again does, does not repair negations ("a highway with no vehicles"), where it fixes fewer failures than generating again does, and changes nothing for events that must happen late in a clip ("a sandcastle that a wave washes flat"). Which of these happens can be known in advance, from the prompt and one inexpensive score. The score, which we call demand, measures how strongly the denoiser reacts to the part of the prompt that the failed video leaves out, and it is read from the first quarter of denoising, before any video exists. Our main finding is a condition: raising the scale is effective only when the prompt contains no negation and no event tied to a specific time, and when demand is sufficiently high, with recovery clearly higher above a fitted threshold than below it. Published corrections for the three failure types, used as fixed probes, behave as this account predicts. A short decision rule follows: before generating again, a user can tell whether the most common fix is worth trying, and what to use when it is not.

Original source

This story was published by arXiv cs.CV and written by Taewon Kang, Matthias Zwicker. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News