Name: Latent Consistency Model API: Super Fast Image Generator
Brand: magicapi
SKU: api-magicapi-super-fast-image-generator-fofr-latent-consistency-model
Availability: InStock
Author: API Market

Shashank Agarwal

# ⚡ Fast Image Generator API (fofr Latent Consistency Model)

## Overview
This API runs a Latent Consistency Model (LCM), packaged by fofr, that generates images in very few denoising steps (1 to 8 are recommended). Its developer describes it as taking about 0.6 seconds per image.

Send a text `prompt` for text-to-image, add an `image` for image-to-image, or add a `control_image` to guide the composition with Canny edge ControlNet. Each request returns a list of image URLs: `num_images` per prompt, and you can send several prompts on separate lines.

## Features
- **Few-step generation**: 8 denoising steps by default; 1 to 8 are recommended.
- **Image-to-image**: pass an `image` and set `prompt_strength` (0 to 1) to control how much of it is changed.
- **Canny ControlNet**: pass a `control_image`; its Canny edges guide the layout. Tune `controlnet_conditioning_scale`, `control_guidance_start`/`control_guidance_end` and the Canny thresholds.
- **Batching**: up to 50 images per prompt with `num_images`, and several prompts per request (one per line in `prompt`).
- **Sizing strategy**: use `width`/`height`, or size the output from the input image or the control image.
- **Archive option**: `archive_outputs` archives the output images.
- **Seed**: set `seed` to reproduce a result.

## Use Cases
1. **Quick drafts and previews**: test prompts and compositions cheaply before using a slower model.
2. **Large batches**: generate many candidates of one prompt, or several prompts, in one request.
3. **Restyling images**: turn a photo into a painting or another style with image-to-image.
4. **Layout-guided images**: keep the outlines of a reference picture with the Canny ControlNet.

## Visual Examples
### Example Input
Input image (image-to-image):

![Input image used for image-to-image](https://blog.api.market/wp-content/uploads/2026/10/latent-consistency-model-input-api-market-1.png)

```json
{
  "image": "https://blog.api.market/wp-content/uploads/2026/10/latent-consistency-model-input-api-market-1.png",
  "width": 768,
  "height": 768,
  "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
  "num_images": 1,
  "guidance_scale": 8,
  "archive_outputs": false,
  "prompt_strength": 0.45,
  "sizing_strategy": "width/height",
  "lcm_origin_steps": 50,
  "canny_low_threshold": 100,
  "num_inference_steps": 4,
  "canny_high_threshold": 200,
  "control_guidance_end": 1,
  "control_guidance_start": 0,
  "controlnet_conditioning_scale": 2
}
```

### Example Output
![Latent Consistency Model output: self-portrait oil painting of a cyborg with golden hair, made from the input image](https://blog.api.market/wp-content/uploads/2026/10/latent-consistency-model-output-y1nnr1th-api-market.jpg)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | No | `Self-portrait oil painting, a beautiful cyborg with golden hair, 8k` |  | Text prompt. For multiple prompts, enter each on a new line. |
| `width` | integer | No | `768` |  | Width of output image. Lower if out of memory. |
| `height` | integer | No | `768` |  | Height of output image. Lower if out of memory. |
| `sizing_strategy` | string | No | `width/height` | `width/height`, `input_image`, `control_image` | How to size the output: use width/height, or resize based on the input image or the control image |
| `image` | string (URL) | No | none |  | Input image for img2img |
| `prompt_strength` | number | No | `0.8` | 0 to 1 | Prompt strength when using img2img. 1.0 corresponds to full destruction of information in the image. |
| `num_images` | integer | No | `1` | 1 to 50 | Number of images per prompt |
| `num_inference_steps` | integer | No | `8` | 1 to 50 | Number of denoising steps. Recommend 1 to 8 steps. |
| `guidance_scale` | number | No | `8` | 1 to 20 | Scale for classifier-free guidance |
| `lcm_origin_steps` | integer | No | `50` | minimum 1 | LCM origin steps |
| `seed` | integer | No | none |  | Random seed. Leave blank to randomize the seed. |
| `control_image` | string (URL) | No | none |  | Image for ControlNet conditioning |
| `controlnet_conditioning_scale` | number | No | `2` | 0.1 to 4 | ControlNet conditioning scale |
| `control_guidance_start` | number | No | `0` | 0 to 1 | ControlNet start |
| `control_guidance_end` | number | No | `1` | 0 to 1 | ControlNet end |
| `canny_low_threshold` | number | No | `100` | 1 to 255 | Canny low threshold |
| `canny_high_threshold` | number | No | `200` | 1 to 255 | Canny high threshold |
| `archive_outputs` | boolean | No | `false` |  | Option to archive the output images |
| `disable_safety_checker` | boolean | No | `false` |  | Disable the safety checker for generated images |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.0019 per API unit.
- **1 API unit = 1 request covering up to 1 second of processing.** A request that processes for longer uses one unit per started second (for example 2.5 seconds = 3 units, $0.0057). Large batches (`num_images`, several prompts) and bigger sizes take longer.
- **Example cost**: the example request processed for 0.94 seconds = 1 API unit = **$0.0019**.
- **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/super-fast-image-generator-fofr-latent-consistency-model`

### 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 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/super-fast-image-generator-fofr-latent-consistency-model/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "683d19dc312f7a9f0428b04429a9ccefd28dbf7785fef083ad5cf991b65f406f",
    "input": {
      "image": "https://blog.api.market/wp-content/uploads/2026/10/latent-consistency-model-input-api-market-1.png",
      "width": 768,
      "height": 768,
      "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
      "num_images": 1,
      "guidance_scale": 8,
      "archive_outputs": false,
      "prompt_strength": 0.45,
      "sizing_strategy": "width/height",
      "lcm_origin_steps": 50,
      "canny_low_threshold": 100,
      "num_inference_steps": 4,
      "canny_high_threshold": 200,
      "control_guidance_end": 1,
      "control_guidance_start": 0,
      "controlnet_conditioning_scale": 2
    }
  }'
```

Response (201 Created):
```json
{
  "id": "y1nnr1thc5rne0d1ccpsptq1rg",
  "version": "683d19dc312f7a9f0428b04429a9ccefd28dbf7785fef083ad5cf991b65f406f",
  "status": "starting",
  "created_at": "2026-10-22T10:34:36.936Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/super-fast-image-generator-fofr-latent-consistency-model/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "y1nnr1thc5rne0d1ccpsptq1rg",
  "status": "succeeded",
  "output": [
    "https://blog.api.market/wp-content/uploads/2026/10/latent-consistency-model-output-y1nnr1th-api-market.jpg"
  ],
  "error": null,
  "created_at": "2026-10-22T10:34:36.936Z",
  "started_at": "2026-10-22T10:35:18.673Z",
  "completed_at": "2026-10-22T10:35:19.613Z"
}
```

`output` is a list of file URLs: `num_images` images for each prompt line.

### 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 `num_images` above 50 or a `sizing_strategy` 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/super-fast-image-generator-fofr-latent-consistency-model";

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: "683d19dc312f7a9f0428b04429a9ccefd28dbf7785fef083ad5cf991b65f406f", 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 = 600000;
  const pollInterval = 1000;
  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 10 minutes");
}

createAndWaitForPrediction({
  image: "https://blog.api.market/wp-content/uploads/2026/10/latent-consistency-model-input-api-market-1.png",
  width: 768,
  height: 768,
  prompt: "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
  num_images: 1,
  guidance_scale: 8,
  archive_outputs: false,
  prompt_strength: 0.45,
  sizing_strategy: "width/height",
  lcm_origin_steps: 50,
  canny_low_threshold: 100,
  num_inference_steps: 4,
  canny_high_threshold: 200,
  control_guidance_end: 1,
  control_guidance_start: 0,
  controlnet_conditioning_scale: 2
}).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/super-fast-image-generator-fofr-latent-consistency-model"


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": "683d19dc312f7a9f0428b04429a9ccefd28dbf7785fef083ad5cf991b65f406f", "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 = 600
    poll_interval = 1
    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 10 minutes")


print(create_and_wait_for_prediction({
    "image": "https://blog.api.market/wp-content/uploads/2026/10/latent-consistency-model-input-api-market-1.png",
    "width": 768,
    "height": 768,
    "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
    "num_images": 1,
    "guidance_scale": 8,
    "archive_outputs": False,
    "prompt_strength": 0.45,
    "sizing_strategy": "width/height",
    "lcm_origin_steps": 50,
    "canny_low_threshold": 100,
    "num_inference_steps": 4,
    "canny_high_threshold": 200,
    "control_guidance_end": 1,
    "control_guidance_start": 0,
    "controlnet_conditioning_scale": 2
}))
```

## FAQ
- **How many steps should I use?**
  - 1 to 8 `num_inference_steps` are recommended (default 8). The example used 4 steps.
- **How do I generate several different prompts in one request?**
  - Put each prompt on its own line in `prompt`. Each line produces `num_images` images.
- **Do I need an input image?**
  - No. Without `image` or `control_image` the model generates from the prompt alone. Add `image` for image-to-image (lower `prompt_strength` keeps more of the original) or `control_image` to follow its Canny edges.
- **How is a large batch billed?**
  - By processing time: one API unit ($0.0019) per started second. The 1-image example took 0.94 seconds, so it cost one unit.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.

## 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.


Fast few-step image generation with a Latent Consistency Model: text-to-image, image-to-image, Canny ControlNet and up to 50 images per prompt.