> ## Documentation Index
> Fetch the complete documentation index at: https://docs.creatify.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Gemini Omni Flash 1.1 (Edit) · Video to video

> Edits a video across conversational turns via natural-language instructions while preserving scene coherence, with output resolutions up to 4K.

[← Gemini Omni Flash](/api-documentation/ai-generation/models/gemini-omni-flash)

**Model name:** `gemini-omni-flash-1.1/edit`\
**Generation type:** `video_to_video`\
**Endpoint:** [`POST /api/asset_generator/`](/api-reference/ai-generation/post-ai-generation)

## Pricing

| Resolution | Credits |
| - | - |
| 360p | **3.0** |
| 720p | **10.0** |
| 1080p | **15.0** |
| 4k | **30.0** |

Prices are per output. When a request asks for several outputs, the charge is this price times the number of outputs.

## Quick start

The example uses sample media from our CDN. Swap in publicly accessible URLs for your own files.

<CodeGroup>
  ```bash cURL theme={null}
  curl --request POST \
    --url https://api.creatify.ai/api/asset_generator/ \
    --header 'Content-Type: application/json' \
    --header 'X-API-ID: your-api-id' \
    --header 'X-API-KEY: your-api-key' \
    --data '{
      "model_name": "gemini-omni-flash-1.1/edit",
      "input_params": {
        "prompt": "Change the setting to a bright café while she keeps talking.",
        "video_url": "https://d35ghwdno3nak3.cloudfront.net/tutorial/asset-generator/sample-video.mp4"
      }
    }'
  ```

  ```python Python theme={null}
  import requests

  response = requests.post(
      "https://api.creatify.ai/api/asset_generator/",
      headers={"X-API-ID": "your-api-id", "X-API-KEY": "your-api-key"},
      json={
          "model_name": "gemini-omni-flash-1.1/edit",
          "input_params": {
              "prompt": "Change the setting to a bright café while she keeps talking.",
              "video_url": "https://d35ghwdno3nak3.cloudfront.net/tutorial/asset-generator/sample-video.mp4"
          },
      },
  )
  print(response.json()["id"])
  ```
</CodeGroup>

## Input parameters

Send these fields in `input_params`.

<ParamField body="prompt" type="string" required>
  A simple instruction describing the edit. Add "Keep everything else the same." to preserve the rest of the scene. Voice editing is not supported.

  Minimum characters: `1`.
  Maximum characters: `2000`.
</ParamField>

<ParamField body="video_url" type="string" required>
  URL of the video to edit. Min duration: 3s. Max file size: 20MB.
</ParamField>

<ParamField body="resolution" type="string" default={"720p"}>
  The resolution of the generated video.

  Allowed values: `"360p"`, `"720p"`, `"1080p"`, `"4k"`.
</ParamField>

<Accordion title="Complete JSON schema">
  ```json theme={null}
  {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "required": [
      "prompt",
      "video_url"
    ],
    "properties": {
      "prompt": {
        "type": "string",
        "title": "Prompt",
        "maxLength": 2000,
        "minLength": 1,
        "description": "A simple instruction describing the edit. Add \"Keep everything else the same.\" to preserve the rest of the scene. Voice editing is not supported."
      },
      "video_url": {
        "type": "string",
        "title": "Video URL",
        "min_length": 3,
        "max_length": 10,
        "max_file_size": 20971520,
        "description": "URL of the video to edit. Min duration: 3s. Max file size: 20MB."
      },
      "resolution": {
        "enum": [
          "360p",
          "720p",
          "1080p",
          "4k"
        ],
        "type": "string",
        "title": "Resolution",
        "default": "720p",
        "description": "The resolution of the generated video.",
        "x-advance-settings": true
      }
    }
  }
  ```
</Accordion>

## Response

The request returns the task with `status: "initializing"`. Poll [GET /api/asset\_generator/\{id}/](/api-reference/ai-generation/get-ai-generation-) until `status` is `done` or `failed`, or pass a `webhook_url` to be notified. A finished task lists its files in `assets` and the credits it charged in `credits_used`.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.