Name: Flux Red Cinema API: Cinematic Film Still Generator
Brand: magicapi
SKU: api-magicapi-cinematic-flux-text-to-image-halimalrasihi-flux-red-cinema
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎬 Cinematic Film Still Image Generator API (halimalrasihi Flux Red Cinema)

## Overview
Flux Red Cinema is a FLUX LoRA by halimalrasihi that generates images with a cinematic, movie-still look. Its developer says the style is triggered by the word `r3dcma` in the prompt.

Send a text `prompt` to generate up to 4 images. You can also pass an input `image` for image-to-image generation, or an `image` plus a `mask` for inpainting. Each request returns a list of image URLs.

## Features
- **Cinematic style**: include the trigger word `r3dcma` in the prompt to apply the trained style.
- **Two base models**: `dev` (default, best around 28 steps) or `schnell` (needs about 4 steps).
- **Image-to-image and inpainting**: pass `image` (and optionally `mask`); `prompt_strength` controls how much of the input image is replaced.
- **Aspect ratios**: `1:1` (default), `16:9`, `21:9`, `3:2`, `2:3`, `4:5`, `5:4`, `3:4`, `4:3`, `9:16`, `9:21`, or `custom` with `width` and `height` (256 to 1440).
- **Multiple outputs**: `num_outputs` from 1 to 4.
- **LoRA strength**: `lora_scale` for the cinematic LoRA, plus an optional `extra_lora` with its own `extra_lora_scale`.
- **Output formats**: `webp` (default), `jpg` or `png`, with `output_quality` from 0 to 100.
- **Seed**: set `seed` to reproduce a result.

## Use Cases
1. **Concept frames**: movie-still style frames for pitches, mood boards and storyboards.
2. **Editorial and poster art**: dramatic, film-lit portraits and scenes.
3. **Wide shots**: use `21:9` or `16:9` for cinematic framing.
4. **Restyling images**: give an existing picture a film still look with image-to-image mode.

## Visual Examples
### Example Input
Prompt:
```
r3dcma, 35mm movie still;

Cyberpunk geisha, futuristic koshirae, neo-Tokyo aesthetic, armor plates, luminous skin, piercing gaze, digital age samurai, high-fashion editorial, ethereal lighting, cultural fusion masterpiece.

In the style of r3dcma,
```

Settings: `model` `dev`, `lora_scale` 1, `num_outputs` 1, `aspect_ratio` `1:1`, `output_format` `png`, `guidance_scale` 3.5, `output_quality` 80, `num_inference_steps` 28.

### Example Output
![Flux Red Cinema output: a cinematic portrait of a cyberpunk geisha in armor](https://blog.api.market/wp-content/uploads/2026/10/flux-red-cinema-output-y3zss6rq-api-market.jpg)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | Yes |  |  | Prompt for the generated image. Include the trigger word `r3dcma` to activate the trained style. |
| `image` | string (URL) | No | none |  | Input image for image-to-image or inpainting mode. If provided, `aspect_ratio`, `width` and `height` are ignored. |
| `mask` | string (URL) | No | none |  | Image mask for inpainting mode. If provided, `aspect_ratio`, `width` and `height` are ignored. |
| `aspect_ratio` | string | No | `1:1` | `1:1`, `16:9`, `21:9`, `3:2`, `2:3`, `4:5`, `5:4`, `3:4`, `4:3`, `9:16`, `9:21`, `custom` | Aspect ratio of the generated image. `custom` uses `width` and `height` and runs in bf16 mode. |
| `height` | integer | No | none | 256 to 1440 | Height of the generated image. Only used when `aspect_ratio` is `custom`. Rounded to the nearest multiple of 16. Not compatible with `go_fast`. |
| `width` | integer | No | none | 256 to 1440 | Width of the generated image. Only used when `aspect_ratio` is `custom`. Rounded to the nearest multiple of 16. Not compatible with `go_fast`. |
| `prompt_strength` | number | No | `0.8` | 0 to 1 | Prompt strength in image-to-image mode. 1.0 fully replaces the information in the input image. |
| `model` | string | No | `dev` | `dev`, `schnell` | Base model. `dev` works best with about 28 steps, `schnell` needs only 4. |
| `num_outputs` | integer | No | `1` | 1 to 4 | Number of images to generate. |
| `num_inference_steps` | integer | No | `28` | 1 to 50 | Number of denoising steps. More steps can give more detail but take longer. |
| `guidance_scale` | number | No | `3` | 0 to 10 | Guidance scale. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5. |
| `seed` | integer | No | none |  | Random seed for reproducible generation. |
| `output_format` | string | No | `webp` | `webp`, `jpg`, `png` | Format of the output images. |
| `output_quality` | integer | No | `80` | 0 to 100 | Quality of saved images. 100 is best. Not used for `png`. |
| `disable_safety_checker` | boolean | No | `false` |  | Disable the safety checker for generated images. |
| `go_fast` | boolean | No | `false` |  | Run a speed-optimized (fp8 quantized) model. Set to `false` to run in the original bf16. |
| `megapixels` | string | No | `1` | `1`, `0.25` | Approximate number of megapixels of the generated image. |
| `lora_scale` | number | No | `1` | -1 to 3 | How strongly the cinematic LoRA is applied. Values between 0 and 1 work for standard inference; with `go_fast` a 1.5x multiplier is applied. |
| `extra_lora` | string | No | none |  | Extra LoRA weights to load: a Hugging Face model, a CivitAI model or a direct `.safetensors` file URL. |
| `extra_lora_scale` | number | No | `1` | -1 to 3 | How strongly the extra LoRA is applied. Values between 0 and 1 work for standard inference; with `go_fast` a 1.5x multiplier is applied. |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.024 per API unit.
- **1 API unit = one request with up to 14 seconds of processing.** A request that takes longer is billed one more unit for every started 14-second block (for example, 14 to 28 seconds is 2 units, $0.048).
- Settings that add work, such as more `num_outputs` or more `num_inference_steps`, take longer and can use more units.
- **Example cost**: the example request took 17.1 seconds of processing, so it used 2 units ($0.048).
- **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/cinematic-flux-text-to-image-halimalrasihi-flux-red-cinema`

### 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/cinematic-flux-text-to-image-halimalrasihi-flux-red-cinema/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "c2ebb498cc8288d3bd17d92b4b47e007d3d6cda29ac062a0bad59a76a36cfecb",
    "input": {
      "model": "dev",
      "prompt": "r3dcma, 35mm movie still;\n\nCyberpunk geisha, futuristic koshirae, neo-Tokyo aesthetic, armor plates, luminous skin, piercing gaze, digital age samurai, high-fashion editorial, ethereal lighting, cultural fusion masterpiece.\n\nIn the style of r3dcma,",
      "lora_scale": 1,
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 3.5,
      "output_quality": 80,
      "num_inference_steps": 28
    }
  }'
```

Response (201 Created):
```json
{
  "id": "y3zss6rqd1rmw0d1d8gbzk24wm",
  "version": "c2ebb498cc8288d3bd17d92b4b47e007d3d6cda29ac062a0bad59a76a36cfecb",
  "status": "starting",
  "created_at": "2026-10-23T18:57:30.667Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/cinematic-flux-text-to-image-halimalrasihi-flux-red-cinema/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "y3zss6rqd1rmw0d1d8gbzk24wm",
  "status": "succeeded",
  "output": [
    "https://blog.api.market/wp-content/uploads/2026/10/flux-red-cinema-output-y3zss6rq-api-market.jpg"
  ],
  "error": null,
  "created_at": "2026-10-23T18:57:30.667Z",
  "started_at": "2026-10-23T18:57:31.667Z",
  "completed_at": "2026-10-23T18:57:42.667Z"
}
```

`output` is a list of image URLs, one per requested output (`num_outputs`).

### 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 missing `prompt` or an `aspect_ratio` 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/cinematic-flux-text-to-image-halimalrasihi-flux-red-cinema";

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: "c2ebb498cc8288d3bd17d92b4b47e007d3d6cda29ac062a0bad59a76a36cfecb", 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({
  model: "dev",
  prompt: "r3dcma, 35mm movie still;\n\nCyberpunk geisha, futuristic koshirae, neo-Tokyo aesthetic, armor plates, luminous skin, piercing gaze, digital age samurai, high-fashion editorial, ethereal lighting, cultural fusion masterpiece.\n\nIn the style of r3dcma,",
  lora_scale: 1,
  num_outputs: 1,
  aspect_ratio: "1:1",
  output_format: "png",
  guidance_scale: 3.5,
  output_quality: 80,
  num_inference_steps: 28
}).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/cinematic-flux-text-to-image-halimalrasihi-flux-red-cinema"


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": "c2ebb498cc8288d3bd17d92b4b47e007d3d6cda29ac062a0bad59a76a36cfecb", "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({
    "model": "dev",
    "prompt": "r3dcma, 35mm movie still;\n\nCyberpunk geisha, futuristic koshirae, neo-Tokyo aesthetic, armor plates, luminous skin, piercing gaze, digital age samurai, high-fashion editorial, ethereal lighting, cultural fusion masterpiece.\n\nIn the style of r3dcma,",
    "lora_scale": 1,
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 3.5,
    "output_quality": 80,
    "num_inference_steps": 28
}))
```

## FAQ
- **How do I get the cinematic style?**
  - Put the trigger word `r3dcma` in your prompt, as in the example. Raise or lower `lora_scale` to make the style stronger or weaker.
- **Should I use `dev` or `schnell`?**
  - `dev` (default) works best with about 28 `num_inference_steps`. `schnell` needs only about 4 steps, so it finishes faster and uses fewer API units.
- **Can I restyle an existing image?**
  - Yes. Pass it as `image` and set `prompt_strength` (default 0.8; 1.0 replaces the input entirely). Add a `mask` to repaint only part of the image.
- **How many images does one request return?**
  - Between 1 and 4, set by `num_outputs`. More images take longer to generate, so a request can use more than one 14-second API 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`.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## 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.


Generate cinematic film still images from text or an input image with halimalrasihi's Flux Red Cinema FLUX LoRA. $0.024 per call, pay as you go.