Files
nexus/wiki/concepts/图生视频.md
2026-04-14 16:02:50 +08:00

27 lines
964 B
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
title: "图生视频"
type: concept
tags: [AI视频, 生成式AI]
sources: [14ge-mian-fei-ai-tu-sheng-shi-ping-gong-ju.md]
last_updated: 2026-04-14
---
## Definition
Image-to-VideoI2V将静态图片转化为动态视频的AI生成技术。
## Core Attributes
- 输入静态图片jpg/png等
- 控制方式:提示词、动作模板、运镜参数、首尾帧
- 输出动态视频通常2-6秒
- 核心能力:主体一致性、运动控制、风格化
## Related Concepts
- [[主体一致性]]:视频中人物/物体保持与原图一致
- [[运镜控制]]:通过参数控制镜头运动方式
- [[提示词控制]]:通过文本描述控制视频生成
## Tool Ecosystem
中国平台:[[绘蛙AI视频]]、[[智谱清影]]、[[通义万相]]、[[Vidu]]、[[可灵AI]]、[[海螺AI]]、[[即梦AI]]、[[万相营造]]、[[艺映AI]]
海外平台:[[PixVerse]]、[[Video Ocean]]、[[Stable Video]]、[[Viva]]、[[Haiper]]