Back to Details

grok-media

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Grok Media

Grok 媒体生成

Use this skill when working with xAI media models in OpenMontage.

在OpenMontage中使用xAI媒体模型时，请使用此技能。

Models

模型

```
grok-imagine-image
```
for image generation and image editing
```
grok-imagine-video
```
for text-to-video, image-to-video, and reference-image video

```
grok-imagine-image
```
：用于图像生成与图像编辑
```
grok-imagine-video
```
：用于文本转视频、图像转视频以及参考图像生成视频

Authentication

认证

Env var:
```
XAI_API_KEY
```
Base URL:
```
https://api.x.ai/v1
```
Header:
```
Authorization: Bearer $XAI_API_KEY
```

环境变量：
```
XAI_API_KEY
```
基础URL：
```
https://api.x.ai/v1
```
请求头：
```
Authorization: Bearer $XAI_API_KEY
```

Image API

图像API

Text-to-image

文本转图像

Endpoint:
```
POST /images/generations
```
Core fields:
- ```
model
```
- ```
prompt
```
- ```
n
```
- ```
aspect_ratio
```
- ```
resolution
```

接口端点：
```
POST /images/generations
```
核心字段：
- ```
model
```
- ```
prompt
```
- ```
n
```
- ```
aspect_ratio
```
- ```
resolution
```

Image edit

图像编辑

Endpoint:
```
POST /images/edits
```
Use
```
image
```
for one source image
Use
```
images
```
for multi-image compositing
Each source image can be:
- a public HTTPS URL
- a base64 data URI

接口端点：
```
POST /images/edits
```
使用
```
image
```
参数传入单张源图片
使用
```
images
```
参数进行多图片合成
每张源图片可以是：
- 公开的HTTPS链接
- Base64数据URI

Image prompting

图像提示词技巧

Grok responds well to direct natural language
For edits, describe only the intended change and preserve everything else implicitly
For multi-image merges, explicitly name how each source contributes
Prefer one strong scene description over long style-stacking

Grok对直接的自然语言指令响应良好
对于编辑操作，仅描述预期的修改内容，其余部分会默认保留
对于多图片融合，需明确说明每张源图片的作用
优先使用清晰的单一场景描述，而非堆砌多种风格

Video API

视频API

Generation

生成流程

Endpoint:
```
POST /videos/generations
```
Polling endpoint:
```
GET /videos/{request_id}
```
Success state:
```
status == "done"
```
Failure states to handle explicitly:
```
failed
```
,
```
expired
```

接口端点：
```
POST /videos/generations
```
轮询接口：
```
GET /videos/{request_id}
```
成功状态：
```
status == "done"
```
需要显式处理的失败状态：
```
failed
```
、
```
expired
```

Modes

模式

Text-to-video:
- prompt-only generation
Image-to-video:
- use
```
image: {"url": ...}
```
- this anchors the starting frame
Reference-to-video:
- use
```
reference_images: [{"url": ...}, ...]
```
- this influences who/what appears in the video without locking the first frame
- prompts can reference inputs with placeholders like
```
<IMAGE_1>
```
  ,
```
<IMAGE_2>
```

文本转视频：
- 仅通过提示词生成
图像转视频：
- 使用
```
image: {"url": ...}
```
  参数
- 以此锚定起始帧
参考图像转视频：
- 使用
```
reference_images: [{"url": ...}, ...]
```
  参数
- 这会影响视频中出现的人物/物体，但不会锁定第一帧
- 提示词中可使用
```
<IMAGE_1>
```
  、
```
<IMAGE_2>
```
  等占位符引用输入的图片

Video constraints

视频限制

Grok video is best treated as short-form generation
Current output resolutions are
```
480p
```
and
```
720p
```
Reference-image video supports multiple images and is useful for product placement, wardrobe transfer, and identity consistency
Download outputs promptly; provider URLs may be temporary

Grok视频最适合用于短内容生成
当前支持的输出分辨率为
```
480p
```
和
```
720p
```
参考图像生成视频支持多张图片输入，适用于产品植入、服装迁移以及角色一致性保持等场景
请及时下载输出内容；服务商提供的链接可能是临时的

Pricing

定价

```
grok-imagine-image
```
:
```
$0.02
```
per generated image
```
grok-imagine-image
```
edits/composites: add
```
$0.002
```
per input image
```
grok-imagine-video
```
:
- ```
480p
```
  :
```
$0.05
```
  per second
- ```
720p
```
  :
```
$0.07
```
  per second
```
grok-imagine-video
```
image-conditioned requests: add
```
$0.002
```
per input image

```
grok-imagine-image
```
：每张生成图片收费
```
$0.02
```
```
grok-imagine-image
```
编辑/合成：每张输入图片额外收取
```
$0.002
```
```
grok-imagine-video
```
：
- ```
480p
```
  ：每秒收费
```
$0.05
```
- ```
720p
```
  ：每秒收费
```
$0.07
```
```
grok-imagine-video
```
图像条件请求：每张输入图片额外收取
```
$0.002
```

Grok-Specific Prompt Guidance

Grok专属提示词指南

Images

图像

Start with subject, action, setting
Add one style anchor, not five
For edits:
- describe the desired modification
- keep the rest of the image stable by omission, not by writing a giant preservation list

从主体、动作、场景开始描述
添加一种风格定位，而非五种
对于编辑：
- 描述期望的修改内容
- 通过省略而非罗列大量保留项来保持图像其余部分稳定

Video

视频

Keep prompts scene-local: one shot, one main motion idea, one emotional beat
For reference-conditioned video, explicitly map source images to roles:
- person from
```
<IMAGE_1>
```
- jacket from
```
<IMAGE_2>
```
- product from
```
<IMAGE_3>
```
Camera and pacing language helps:
- slow push-in
- handheld follow
- locked-off medium shot
- high-energy whip pan transition

提示词聚焦单一场景：一个镜头、一个核心动作、一种情绪基调
对于参考图像驱动的视频，需明确将源图片映射到对应角色：
- 来自
```
<IMAGE_1>
```
  的人物
- 来自
```
<IMAGE_2>
```
  的夹克
- 来自
```
<IMAGE_3>
```
  的产品
使用镜头和节奏相关的描述词会有帮助：
- 缓慢推进镜头
- 手持跟拍
- 固定中景镜头
- 高能量快速摇移转场

Good Fits

适用场景

Image style transfer
Image compositing from multiple sources
Reference-conditioned short video
Product-led motion clips
Character-consistent scenes without hard first-frame lock

图像风格迁移
多源图片合成
参考图像驱动的短视频生成
产品导向的动态片段
无需严格锁定第一帧的角色一致性场景

Weak Fits

不适用场景

Long-form clip generation
Heavy reliance on deterministic seeds
Overloaded prompts with multiple scene changes

长片段生成
高度依赖确定性种子
包含多个场景变化的过载提示词

Failure Handling

故障处理

If generation submission succeeds but polling expires, surface it as a provider/runtime issue
If a request fails, preserve the endpoint, mode, and prompt summary in the error
Do not silently substitute a different provider after xAI was selected without user approval

如果生成提交成功但轮询超时，需将其标记为服务商/运行时问题
如果请求失败，需在错误信息中保留接口端点、模式以及提示词摘要
在未获得用户许可的情况下，请勿在选择xAI后默认替换为其他服务商