Unverified50% confidenceReleaseExact time
Tencent Hunyuan, in collaboration with Fudan University and Zhejiang University, open-sourced Prism under the MIT license; by reducing redundant computation in high-resolution training, it achieves approximately 2.5× speedup in joint native 2K video and audio generation training.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/8/2026
First Seen
Valid until: 1/6/2027
Sources
Related Entities
Related Claims
VerifiedMixed-precision training can typically increase training speed by 1.5–2 times and reduce VRAM usage by nearly half.62% similarUnverifiedStable Video Diffusion 的训练流程分为三个阶段：低分辨率图像预训练、精选视频数据视频微调、高质量数据高分辨率微调62% similarUnverified混合精度训练在不显著损失模型精度的前提下，可将训练速度提升约2倍，显存占用降低近一半62% similarUnverified选择GPU版本的LibTorch可以将训练速度提升一到两个数量级，尤其在涉及大量矩阵运算的深度网络中62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/987267API
curl https://kongchang.com/api/v1/knowledge/claims/987267MCP
get_claim(id=987267)