Unverified50% confidenceFactExact time
Early video generation models such as Runway Gen-1 relied primarily on text guidance.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedRunway's video generation model has gone through an iterative journey from Gen-1 and Gen-2 to Gen-3 Alpha.73% similarUnverifiedAI 视频生成工具第一阶段以 2022 年前后的 Runway Gen-1 为代表，核心是对已有素材的风格化处理71% similarUnverifiedDifferent video models show significant differences in prompt format preferences: Runway Gen-3 favors natural language descriptions, Kling has its own keyword system for camera movements, and H3 tends toward structured storyboard-style instructions.71% similarUnverifiedRunway的Gen-1（2023年初）实现视频到视频风格转换，Gen-2（2023年中）首次支持纯文本生成视频，Gen-3 Alpha（2024年中）支持10秒高质量输出70% similarUnverifiedThe Wan video generation model supports two generation modes: Text-to-Video and Image-to-Video.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/911499API
curl https://kongchang.com/api/v1/knowledge/claims/911499MCP
get_claim(id=911499)