Unverified50% confidenceEventExact time
In the video generation test, the facial expression progression in a short video of a female singer singing was coherent, but a nighttime street video had a failure case where a passerby was "cloned" into two people.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/22/2026
First Seen
Valid until: 11/5/2026
Sources
Free Unlimited Claude Code Solution: Agnes AI + CC Switch Setup Guide
bilibiliAPIkeys10/21/2026
Related Entities
Related Claims
UnverifiedFaceless video, which Syllaby is betting heavily on, is one of the fastest-growing short video formats in recent years.57% similarVerifiedTraditional cascaded architectures generate video before adding audio, which leads to problems such as audio-video desynchronization, lip-sync mismatches, and ambient sound being out of step with on-screen actions.56% similarUnverifiedIn the Omni test, the audio was generated together with the video.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1087352API
curl https://kongchang.com/api/v1/knowledge/claims/1087352MCP
get_claim(id=1087352)