使用 Grok Imagine Video 1.5 Preview 根据图像生成视频,支持多种화면 비율和分辨率,以及最长 15 秒的时长。
About this model
Grok Imagine Video 1.5 Preview 是一款先进的이미지 투 비디오模型,可将静态图像转换为流畅、高质量的视频。它支持 1 到 15 秒的时长以及最高 720p 的分辨率,擅长在各种화면 비율下生成电影感动画。无论是竖屏、横屏还是方形格式,该模型都能仅凭一张参考图像提供流畅运动和稳定的视觉质量。
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $0.08/sec at 480p, $0.14/sec at 720p (default 8s = $0.64) | Pay-as-you-go with no subscription required. Credits deducted per generation. |
| Fal.ai | 제공되지 않음 | This model is not available on Fal.ai. |
| Replicate | 제공되지 않음 | This model is not available on Replicate. |
Pay-as-you-go with no subscription required. Credits deducted per generation.
This model is not available on Fal.ai.
This model is not available on Replicate.
** Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| 프롬프트 | string | 用于비디오生成的文本描述。 | The whale suddenly begins swimming through the apartment as if the room is underwater. Furniture crashes into walls, water bursts outward, and the whale breaks through multiple rooms while the camera follows beside it. |
| 이미지 URL | array | Upload or provide up to 7 image URLs to use as reference input for video generation. | https://cdn.muapi.ai/assets/grok-imagine-video-1-5-preview.jpg |
| 화면 비율 | Enum (8 options) | Aspect ratio for the generated video. Use 'auto' to match the input image. | auto |
| 해상도 | Enum (2 options) | 출력비디오的해상도。 | 480p |
| 재생 시간 (초)(秒) | int | 비디오재생 시간(秒)。 | 8 |
用于비디오生成的文本描述。
The whale suddenly begins swimming through the apartment as if the room is underwater. Furniture crashes into walls, water bursts outward, and the whale breaks through multiple rooms while the camera follows beside it.Upload or provide up to 7 image URLs to use as reference input for video generation.
https://cdn.muapi.ai/assets/grok-imagine-video-1-5-preview.jpgAspect ratio for the generated video. Use 'auto' to match the input image.
auto출력비디오的해상도。
480p비디오재생 시간(秒)。
8Developer documentation
上传图像:通过 images_list 字段提供一个或多个图像 URL。支持 JPEG、PNG、WebP(每张最大 20MB)。
编写프롬프트(可选):描述你想要的运动或场景,例如:“一个人走过霓虹灯照亮的城市,镜头缓慢向右摇摄。”
设置时长:选择 1 到 15 秒。默认值为 8 秒。
选择화면 비율:选择 auto 以匹配입력 파라미터图像尺寸,或指定 16:9、9:16、1:1、4:3、3:4、3:2 或 2:3。
选择分辨率:选择 480p 以更快生成,或选择 720p 以获得更高质量的출력 결과。
提交并轮询:API 会立即返回 request_id。轮询 GET /api/v1/predictions/{request_id}/result,直到 status 为 completed。
Frequently asked
不需要,프롬프트是可选的。你只提交图像也可以,模型会根据视觉内容为其添加动画。加入描述性프롬프트可以更好地控制运动和场景。
你可以在 `images_list` 字段中提供多个图像 URL。模型会将它们作为视频生成的参考帧。
480p 生成更快,并且每秒费用更低。720p 会출력 결과更清晰的高分辨率结果,适合最终交付或对视觉质量要求较高的内容。
模型支持 auto、1:1、16:9、9:16、4:3、3:4、3:2 和 2:3。使用 'auto' 可以保留입력 파라미터图像的原始比例。