Unverified50% confidenceFactExact time
Tian Keyu's team has built its own 200,000-symbol visual dictionary, paired with one hour of video training, aiming to reduce the cost of generating one second of video to one tenth, with the full model planned for release in 2027 and currently no product available.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedThe low/zero-prerequisite phase of the course used more than 60 videos and approximately 20 hours to complete a full-stack general-purpose permission system.66% similarUnverifiedThe article's source material comes from a single product demo video, and the claim of building 11 agents in five minutes is a vendor statement lacking third-party verification.63% similarUnverifiedA developer used a single RTX PRO 6000 and spent 3.5 days training a 210-million-parameter text-to-image diffusion Transformer (DiT) from scratch on 4.2 million images at 256² resolution.63% similarUnverified一个视频手动发布下来至少需要10到20分钟，覆盖四个及以上平台会显著消耗创作热情62% similarUnverifiedSomeone trained a 22-million-parameter language model from random weights on a gaming laptop with 4GB of VRAM62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1010070API
curl https://kongchang.com/api/v1/knowledge/claims/1010070MCP
get_claim(id=1010070)