---
title: "通过 RunAPI 在爱马仕 (Hermes Agent) 中使用 Luma — 视频修改 API"
url: "https://runapi.ai/zh-CN/hermes-luma.md"
canonical: "https://runapi.ai/zh-CN/hermes-luma"
locale: "zh-CN"
model: "luma"
---

# 在 Hermes Agent 中使用 Luma。

Luma Ray 3.2 通过提示词驱动的变换修改现有视频，同时保持空间一致性和 3D 场景结构。发送源视频 URL 和描述变换的文本提示词——Luma 会以富有氛围的光照、环境细节以及物理一致的镜头运动重新渲染素材。Hermes Agent 通过 RunAPI 自定义端点调用它。

## API example

```bash
curl -X POST https://runapi.ai/api/v1/luma/modify_video \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "luma-modify-video",
    "prompt": "Transform the scene into a foggy autumn morning with golden light filtering through trees",
    "source_video_url": "https://example.com/park-walk.mp4"
  }'

```

### Response

```json
{
  "task_id": "tsk_abc123",
  "status": "pending",
  "model": "luma-modify-video"
}

```

## How it works

1. **Configure RunAPI** — Set RUNAPI_API_KEY in the environment where Hermes Agent runs. If you already added RunAPI as a custom:runapi provider, the same key handles Luma video modification requests.
2. **Call Luma modify_video** — Send a POST request to the modify_video endpoint with model set to luma-modify-video, the source_video_url pointing to your input footage, and a prompt describing the transformation. Hermes Agent can build and send this request through the custom:runapi provider.
3. **Poll for the result** — The endpoint returns a task_id immediately. Poll the task status endpoint until the status is completed, then read the output video URL from the response. Video modification typically takes 30-120 seconds depending on complexity.

## Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| `model` | `string` | Required. Use luma-modify-video. |
| `prompt` | `string` | Required. Text description of the desired video transformation — style changes, lighting, atmosphere, or scene edits. |
| `source_video_url` | `string` | Required. URL of the source video to modify. Must be a publicly accessible MP4 or MOV file. |
| `watermark` | `boolean` | Optional. Whether to add a watermark to the output video. |
| `callback_url` | `string` | Optional. Webhook URL that receives a POST when the task completes. |

## FAQ

### What kind of transformations can Luma modify_video do?

Luma modify_video re-renders existing footage with prompt-driven changes — atmospheric shifts (fog, rain, golden hour), style transfers (cinematic, anime, noir), lighting overhauls, and environmental transformations. It preserves the original camera motion and spatial layout of the scene.

### Does Luma generate audio or sound?

No. Luma Ray 3.2 only modifies the visual track of your source video. If the source has audio, Luma's output is video-only. Use a separate audio model like ElevenLabs or Suno through RunAPI to add sound after the visual transformation is complete.

### Is Luma modify_video synchronous or asynchronous?

Asynchronous. The create endpoint returns a task_id immediately. Poll the task status endpoint or provide a callback_url to receive a webhook when the modified video is ready. Typical processing time is 30-120 seconds.

### Can Hermes Agent chain Luma with video generation models in one workflow?

Yes. A Hermes Agent workflow can generate a video with Kling or Wan, then pass the output URL as source_video_url to Luma modify_video for atmospheric re-rendering — all through the same custom:runapi provider and RUNAPI_API_KEY. Each step uses the same async polling pattern.

### Can Luma maintain character consistency when modifying video?

Luma preserves the original composition and spatial layout, including character positions and proportions. However, fine facial details can drift during heavy style transfers. For best character consistency, keep style changes moderate or use reference images to anchor key subjects.

### Can Hermes Agent apply multiple Luma transformations in sequence?

Yes. Hermes Agent can chain Luma calls -- apply a style change first, then a scene modification, each building on the previous output. This enables complex multi-pass video editing within one workflow.


## Links

- [Hermes Agent 配置指南 →](https://runapi.ai/zh-CN/hermes-agent)
- [Luma 模型 →](https://runapi.ai/zh-CN/models/luma)
- [Model catalog](https://runapi.ai/zh-CN/models)
- [API docs](https://runapi.ai/zh-CN/docs)