Name: Deforum Stable Diffusion API: Text to Video Animation
Brand: magicapi
SKU: api-magicapi-animate-prompts-stable-diffusion-deforum-deforum-stable-diffusion
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎬 Text-to-Video Animation API (Deforum Stable Diffusion)

## Overview
Deforum Stable Diffusion animates text prompts into a video. Each frame is generated with Stable Diffusion while a camera motion (zoom, rotation and pan) moves through the scene, so the picture keeps evolving from frame to frame.

Write the prompts in `animation_prompts`, set the number of frames with `max_frames` and the frame rate with `fps`, and get back the URL of an MP4 video. Motion settings use Deforum's keyframe format, `frame: (value)`.

## Features
- **Prompt schedule**: switch prompts at given frames with `frame: prompt` entries separated by `|`.
- **Camera motion**: `zoom`, `angle`, `translation_x` and `translation_y` take keyframe values such as `0: (1.04)`.
- **Length and frame rate**: `max_frames` from 100 to 1000 (default 100) and `fps` from 10 to 60 (default 15).
- **Color coherence**: keep colors close to the first frame (`Match Frame 0 LAB`, `HSV` or `RGB`) or turn it off with `None`.
- **Samplers**: `klms`, `dpm2`, `dpm2_ancestral`, `heun`, `euler`, `euler_ancestral`, `plms` (default) and `ddim`.
- **Seed**: set a seed to reproduce a result.

## Use Cases
1. **Music and event visuals**: evolving, zooming art loops for screens and streams.
2. **Social clips**: short animated pieces from a written idea.
3. **Art experiments**: morph one scene into another by changing the prompt at set frames.
4. **Backgrounds**: moving abstract or landscape backdrops for videos.

## Visual Examples
### Example Input
Animation prompt: "a beautiful forest by Asher Brown Durand, trending on Artstation"

`max_frames`: `100`, `zoom`: `0: (1.04)`, `angle`: `0:(0)`, `translation_x` and `translation_y`: `0: (0)`, `sampler`: `klms`, `color_coherence`: `Match Frame 0 LAB`. `fps` was left at `15`, so the video is 100 frames long (about 6.7 seconds).

### Example Output
[Watch the example output](https://blog.api.market/wp-content/uploads/2026/10/deforum_stable_diffusion-output-jntnktq4-api-market.mp4)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `max_frames` | integer | No | `100` | `100` to `1000` | Number of frames in the animation |
| `animation_prompts` | string | No | `0: a beautiful portrait of a woman by Artgerm, trending on Artstation` |  | Prompts for the animation as 'frame number: prompt at this frame', with different prompts separated by '\|'. Keep every frame number below max_frames. |
| `angle` | string | No | `0:(0)` |  | Rotation angle schedule for the camera motion, as keyframes in 'frame: (value)' format |
| `zoom` | string | No | `0: (1.04)` |  | Zoom schedule for the camera motion, as keyframes in 'frame: (value)' format |
| `translation_x` | string | No | `0: (0)` |  | Horizontal pan schedule for the camera motion, as keyframes in 'frame: (value)' format |
| `translation_y` | string | No | `0: (0)` |  | Vertical pan schedule for the camera motion, as keyframes in 'frame: (value)' format |
| `color_coherence` | string | No | `Match Frame 0 LAB` | `None`, `Match Frame 0 HSV`, `Match Frame 0 LAB`, `Match Frame 0 RGB` | Keeps colors consistent with the first frame in the chosen color space, or None to turn it off |
| `sampler` | string | No | `plms` | `klms`, `dpm2`, `dpm2_ancestral`, `heun`, `euler`, `euler_ancestral`, `plms`, `ddim` | Sampler used to generate each frame |
| `fps` | integer | No | `15` | `10` to `60` | Frames per second of the output video |
| `seed` | integer | No | none |  | Random seed. Leave empty for a random seed |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.415 per API unit.
- **1 API unit = 1 request with up to 266 seconds of processing.** A request that takes longer uses one unit per started block of 266 seconds (for example, 600 seconds of processing uses 3 units, $1.245).
- More frames take longer to generate and can use more units: the example (100 frames) took about 152 seconds.
- **Example cost**: the example request took 151.7 seconds of processing, which is 1 unit, $0.415.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/animate-prompts-stable-diffusion-deforum-deforum-stable-diffusion`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 5 seconds and an overall timeout of 1800 seconds (30 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/animate-prompts-stable-diffusion-deforum-deforum-stable-diffusion/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
      "version": "e22e77495f2fb83c34d5fae2ad8ab63c0a87b6b573b6208e1535b23b89ea66d6",
      "input": {
        "zoom": "0: (1.04)",
        "angle": "0:(0)",
        "sampler": "klms",
        "max_frames": 100,
        "translation_x": "0: (0)",
        "translation_y": "0: (0)",
        "color_coherence": "Match Frame 0 LAB",
        "animation_prompts": "a beautiful forest by Asher Brown Durand, trending on Artstation"
      }
    }'
```

Response (201 Created):
```json
{
  "id": "jntnktq4bhrne0d1d1f89wkccg",
  "version": "e22e77495f2fb83c34d5fae2ad8ab63c0a87b6b573b6208e1535b23b89ea66d6",
  "status": "starting",
  "created_at": "2026-10-23T10:46:51.994Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/animate-prompts-stable-diffusion-deforum-deforum-stable-diffusion/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "jntnktq4bhrne0d1d1f89wkccg",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/10/deforum_stable_diffusion-output-jntnktq4-api-market.mp4",
  "error": null,
  "created_at": "2026-10-23T10:46:51.994Z",
  "started_at": "2026-10-23T10:48:15.105Z",
  "completed_at": "2026-10-23T10:50:46.838Z"
}
```

`output` is a single URL string pointing to the MP4 video.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a `max_frames` below 100 or a `sampler` that is not in the list.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/animate-prompts-stable-diffusion-deforum-deforum-stable-diffusion";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "e22e77495f2fb83c34d5fae2ad8ab63c0a87b6b573b6208e1535b23b89ea66d6", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 1800000;
  const pollInterval = 5000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 30 minutes");
}

createAndWaitForPrediction({
    "zoom": "0: (1.04)",
    "angle": "0:(0)",
    "sampler": "klms",
    "max_frames": 100,
    "translation_x": "0: (0)",
    "translation_y": "0: (0)",
    "color_coherence": "Match Frame 0 LAB",
    "animation_prompts": "a beautiful forest by Asher Brown Durand, trending on Artstation"
  }).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/animate-prompts-stable-diffusion-deforum-deforum-stable-diffusion"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "e22e77495f2fb83c34d5fae2ad8ab63c0a87b6b573b6208e1535b23b89ea66d6", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 1800
    poll_interval = 5
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 30 minutes")


print(create_and_wait_for_prediction({
    "zoom": "0: (1.04)",
    "angle": "0:(0)",
    "sampler": "klms",
    "max_frames": 100,
    "translation_x": "0: (0)",
    "translation_y": "0: (0)",
    "color_coherence": "Match Frame 0 LAB",
    "animation_prompts": "a beautiful forest by Asher Brown Durand, trending on Artstation"
}))
```

## FAQ
- **How do I change the prompt during the video?**
  - Write `frame: prompt` pairs separated by `|`, for example `0: a forest at dawn | 50: a forest at night`. Keep every frame number below `max_frames`.
- **How long is the video?**
  - `max_frames` divided by `fps`. The defaults (100 frames at 15 fps) give about 6.7 seconds.
- **How do I control the camera?**
  - Set `zoom`, `angle`, `translation_x` and `translation_y` as keyframe values, for example `0: (1.04)` for a slow zoom in from frame 0.
- **How long does a request take?**
  - Minutes rather than seconds. The 100-frame example took about 152 seconds of processing, so poll every few seconds.
- **What does one request cost?**
  - One unit ($0.415) covers up to 266 seconds of processing. The example took 151.7 seconds, so it cost $0.415. Longer videos can use more units.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page. You can also email our support team at hello@magicapi.com.


Turn text prompts into evolving Stable Diffusion animations with keyframed camera motion using Deforum. Pay as you go, no monthly fee.