Unverified50% confidenceReleaseExact time
Alibaba has launched the new Tongyi Wanxiang 2.7 video model, supporting full multimodal coverage of text, image, video, and audio, and connecting the entire pipeline of generation and editing.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/30/2026
First Seen
Valid until: 11/28/2026
Sources
Related Entities
Related Claims
UnverifiedMainstream video generation models including Sora (OpenAI), Wan2.1 (Alibaba), and CogVideoX (Zhipu) have all adopted the DiT or its variant architecture.70% similarUnverifiedThe second phase of AI video generation tools, represented by models such as Sora and Kling in 2023–2024, achieved direct text-to-video generation.70% similarVerifiedA new AI video creation tool allows users to feed in 3–5 viral video samples, enabling the AI to learn the production logic of that type of video and generate works in the same style based on the user's own material.69% similarUnverifiedThe Wan video generation model supports two generation modes: Text-to-Video and Image-to-Video.68% similarUnverifiedCurrent mainstream text-to-video models are generally based on diffusion model architectures, generating coherent video frame sequences by extending image generation capability along the temporal dimension.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/823705API
curl https://kongchang.com/api/v1/knowledge/claims/823705MCP
get_claim(id=823705)