Unverified50% confidenceFactExact time
The model contains approximately 20.8 million parameters, with channel counts progressing as 96→192→384, and supports generating 16-frame video clips at a resolution of 64×64.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDuring text-to-video generation, the system performs video dimension alignment—for example, aligning 400×400 to a multiple of 32 to meet the input requirements of the generation model.79% similarUnverified20.8 million parameters may be too small for video generation tasks, and the low resolution of 64×64 limits the ability to express detail.75% similarUnverified千问3.8 27B是27.8B的稠密模型，支持图像和视频原生多模态输入，原生262K上下文75% similarUnverified一段16帧、分辨率256×256、patch大小16×16的视频送入Transformer会产生4096个token75% similarVerifiedA raw video of 512×512 resolution and 24 frames has a data volume of approximately 18 MB, which is reduced to approximately 1/96 of the original after VAE compression into the 64×64×4 latent variable space.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/910702API
curl https://kongchang.com/api/v1/knowledge/claims/910702MCP
get_claim(id=910702)