PixVerse 6 视频延展: AI Video Editor
使用 PixVerse V6 为现有视频延展新画面。模型会分析结尾片段并生成无缝延续，同时提供可选的风格控制。
使用 PixVerse V6 为现有视频延展新画面。模型会分析结尾片段并生成无缝延续，同时提供可选的风格控制。
About this model
PixVerse V6 视频延展会分析视频的最后几帧并向前生成新内容，从而无缝延续现有视频。支持最高 1080p 分辨率、最长 15 秒的延展时长、艺术风格预设以及可选的 AI 生成音频。
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | From $0.033/s (360p, no audio) to $0.150/s (1080p, with audio) | Per-second pricing on the generated extension. Default 720p without audio: $0.059/s. |
| Fal.ai | Nicht verfügbar | PixVerse V6 video extend is not available on Fal.ai. |
| Replicate | Nicht verfügbar | PixVerse V6 video extend is not available on Replicate. |
Per-second pricing on the generated extension. Default 720p without audio: $0.059/s.
PixVerse V6 video extend is not available on Fal.ai.
PixVerse V6 video extend is not available on Replicate.
** Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | 所需Video延展内容的文本描述。 | As the gravity distortion intensifies, the entire city begins folding and rotating like a shifting maze. The woman is pulled upward as gravity flips vertically, forcing her to run along the side of a skyscraper. Buildings detach and float into the sky while chunks of the street break apart beneath her feet.
She leaps onto a drifting car that is spinning mid-air, using it as a moving platform. Explosions of sparks and debris burst around her as nearby structures collapse inward. The camera whips around her in a fast orbit, then suddenly dives downward as gravity snaps again.
She falls briefly before landing on an upside-down street where vehicles are sliding overhead. A massive section of the city tears loose and begins spiraling into a vortex in the sky. She sprints toward stability as the environment continues warping, with gravity shifting in rapid pulses and the camera continuously rotating to match the changing orientation. |
| Video URL | string | URL of the input video to extend. | https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/pixverse-v6-t2v.mp4 |
| Auflösung | Enum (4 options) | AusgabeVideo的Auflösung。 | 720p |
| Dauer (Sekunden)（秒） | int | Extension length in seconds. | 5 |
| 生成Audio | boolean | Enable AI-generated audio for the extended video. | false |
| 风格 | Enum (5 options) | Optional artistic style to apply to the extended video. | - |
| 负面Prompt | string | 描述生成的Video延展中应避免内容的文本。 | - |
所需Video延展内容的文本描述。
As the gravity distortion intensifies, the entire city begins folding and rotating like a shifting maze. The woman is pulled upward as gravity flips vertically, forcing her to run along the side of a skyscraper. Buildings detach and float into the sky while chunks of the street break apart beneath her feet.
She leaps onto a drifting car that is spinning mid-air, using it as a moving platform. Explosions of sparks and debris burst around her as nearby structures collapse inward. The camera whips around her in a fast orbit, then suddenly dives downward as gravity snaps again.
She falls briefly before landing on an upside-down street where vehicles are sliding overhead. A massive section of the city tears loose and begins spiraling into a vortex in the sky. She sprints toward stability as the environment continues warping, with gravity shifting in rapid pulses and the camera continuously rotating to match the changing orientation.URL of the input video to extend.
https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/pixverse-v6-t2v.mp4AusgabeVideo的Auflösung。
720pExtension length in seconds.
5Enable AI-generated audio for the extended video.
falseOptional artistic style to apply to the extended video.
-描述生成的Video延展中应避免内容的文本。
-Developer documentation
提供视频：通过 video_url 字段提供现有视频的 URL。
编写延续Prompt：描述视频接下来应该发生什么，例如新的动作、场景变化或环境转变。
选择分辨率和时长：选择Ausgabe质量（360p–1080p）以及要添加的时长（1–15 秒）。
应用风格（可选）：从 anime、3d_animation、clay、comic 或 cyberpunk 中选择一种，为延展内容应用艺术化外观。
添加负面Prompt（可选）：描述生成画面中需要避免的内容。
启用音频（可选）：切换 generate_audio_switch 以加入 AI 生成音频。
提交并轮询：API 返回 request_id。轮询 GET /api/v1/predictions/{request_id}/result，直到状态为 completed。
Frequently asked
Ausgabe仅包含新生成的延展画面，不包含完整的合并视频。你可以自行将原始视频和延展片段拼接起来。
可选风格包括 anime、3d_animation、clay、comic 和 cyberpunk。将 style 字段留空即可按照原始视频的风格生成。
费用按生成延展内容的秒数计算，并随分辨率变化。生成音频还会按秒收取附加费用。
支持任何可公开访问的视频 URL。为获得最佳兼容性，建议使用 MP4。