Unverified50% confidenceOpinionExact time
The author believes that the official image-to-video workflow that was modified from the original is slow and produces poor results, and that a self-built simplified workflow yields better results.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/16/2026
First Seen
Valid until: 12/15/2026
Sources
Related Entities
Related Claims
Unverified多模态大模型在视频问答的事实回忆准确率极低，即便经过监督微调也难以改善64% similarUnverifiedThe system has a low error rate, with a strange description (such as missing a checkmate) occurring approximately once every 20 videos.63% similarUnverified大模型的性能提升已经明显放缓，最近新版本的评分甚至不一定超越之前的模型，能力基本已定型63% similarUnverifiedWith the advancement of model distillation, consistency models, and inference acceleration technologies, the cost of video generation is expected to drop by an order of magnitude within the next 1–2 years.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/924451API
curl https://kongchang.com/api/v1/knowledge/claims/924451MCP
get_claim(id=924451)