#### Model Capabilities

# Referencing Files as Input

Anywhere an Imagine endpoint accepts a public URL or base64-encoded image/video, you can substitute a `file_id` from your [Files API](/developers/files) storage. The file is fetched server-side from your private storage, so:

* No bandwidth uploading the same image twice — useful for iterative editing loops.
* The original file stays private (no need to make it public to use it as an input).
* Works with both uploaded files and assets generated by earlier Imagine calls (via [`storage_options`](/developers/model-capabilities/imagine/files/outputs)).

The referenced file must be the correct content type for the endpoint (images: PNG/JPEG/WebP; videos: MP4) and must be fully uploaded.

## Editing a stored image

```python customLanguage="pythonXAI"
import os
import xai_sdk

client = xai_sdk.Client(api_key=os.getenv("XAI_API_KEY"))

response = client.image.sample(
    prompt="Add a party hat to the dog",
    model="grok-imagine-image-quality",
    image_file_id="file_7de029f4-eb66-42ee-87f8-b2a9d9e7466a",  # instead of image_url
)

print(response.url)
```

```bash
curl -s -X POST https://api.x.ai/v1/images/edits \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-imagine-image-quality",
    "prompt": "Add a party hat to the dog",
    "image": { "file_id": "file_7de029f4-eb66-42ee-87f8-b2a9d9e7466a" },
    "response_format": "url"
  }'
```

## Editing with multiple stored images

```python customLanguage="pythonXAI"
response = client.image.sample(
    prompt="Blend these two scenes into one cohesive composition",
    model="grok-imagine-image-quality",
    image_file_ids=[
        "file_7de029f4-eb66-42ee-87f8-b2a9d9e7466a",
        "file_2cd998e7-bf12-44aa-92c8-e3d1f1c1234f",
    ],
)
```

```bash
# Each images entry independently carries url or file_id — mix kinds within a single request.
curl -s -X POST https://api.x.ai/v1/images/edits \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-imagine-image-quality",
    "prompt": "Blend these two scenes into one cohesive composition",
    "images": [
      { "file_id": "file_7de029f4-eb66-42ee-87f8-b2a9d9e7466a" },
      { "url": "https://example.com/scene-b.jpg" }
    ],
    "response_format": "url"
  }'
```

## Image-to-video from a stored first frame

```python customLanguage="pythonXAI"
response = client.video.generate(
    prompt="Pan across the scene as the sky darkens",
    model="grok-imagine-video",
    duration=5,
    image_file_id="file_7de029f4-eb66-42ee-87f8-b2a9d9e7466a",
)

print(response.url)
```

```bash
curl -s -X POST https://api.x.ai/v1/videos/generations \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-imagine-video",
    "prompt": "Pan across the scene as the sky darkens",
    "duration": 5,
    "image": { "file_id": "file_7de029f4-eb66-42ee-87f8-b2a9d9e7466a" }
  }'
```

## Editing a stored video

```python customLanguage="pythonXAI"
response = client.video.generate(
    prompt="Add rain and a moody atmosphere",
    model="grok-imagine-video",
    video_file_id="file_5be118c3-da55-31dd-76e7-a1b8c8d6355b",
)
```

```bash
curl -s -X POST https://api.x.ai/v1/videos/edits \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-imagine-video",
    "prompt": "Add rain and a moody atmosphere",
    "video": { "file_id": "file_5be118c3-da55-31dd-76e7-a1b8c8d6355b" }
  }'
```

## Reference-to-video with multiple stored images

```python customLanguage="pythonXAI"
response = client.video.generate(
    prompt="A woman in this dress walks down a city street at night",
    model="grok-imagine-video",
    duration=5,
    reference_image_file_ids=[
        "file_5be118c3-da55-31dd-76e7-a1b8c8d6355b",  # subject
        "file_2cd998e7-bf12-44aa-92c8-e3d1f1c1234f",  # outfit
    ],
)
```

```bash
# Each reference_images entry independently carries url or file_id — mix kinds within a single request.
curl -s -X POST https://api.x.ai/v1/videos/generations \
  -H "Authorization: Bearer $XAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-imagine-video",
    "prompt": "A woman in this dress walks down a city street at night",
    "duration": 5,
    "reference_images": [
      { "file_id": "file_5be118c3-da55-31dd-76e7-a1b8c8d6355b" },
      { "url": "https://example.com/dress.jpg" }
    ]
  }'
```

## Related

* [Files API Integration](/developers/model-capabilities/imagine/files) — Overview + capstone example showing inputs and outputs together.
* [Persisting Generated Output](/developers/model-capabilities/imagine/files/outputs) — The output side: `storage_options`, public URLs, expiry semantics.
* [Managing Files](/developers/files/managing-files) — Upload, list, retrieve, update, and delete files.