Name: powerpdw AutoVid Chibi Anime Image Generator API
Brand: magicapi
SKU: api-magicapi-cute-anime-image-generator-powerpdw-autovid-chibi
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎎 Chibi Anime Image Generator API (powerpdw AutoVid Chibi)

## Overview
AutoVid Chibi, published by powerpdw, is a LoRA fine-tune of FLUX for cute anime-style images in the chibi (super-deformed) style.

Send a `prompt` and the API returns a list of 1 to 4 image URLs (`num_outputs`). You can choose the FLUX `dev` or `schnell` base model, the aspect ratio and the output format, and turn on `go_fast` for faster generation. Add an input `image` for image-to-image, or an `image` and a `mask` for inpainting.

## Features
- **Chibi anime style**: small, cute, super-deformed characters.
- **Two base models**: `dev` (default, best around 28 steps) or `schnell` (4 steps).
- **Fast mode**: `go_fast` runs a speed-optimized fp8 version.
- **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` from 256 to 1440.
- **Image-to-image and inpainting**: pass `image`, and `mask` for inpainting.
- **1 to 4 images per request**: set `num_outputs`.
- **Output formats**: `webp` (default), `jpg` or `png`.

## Use Cases
1. **Stickers and emotes**: cute characters for chat apps and streams.
2. **Story and video scenes**: chibi scenes for short videos and comics.
3. **Avatars**: playful profile pictures.
4. **Merchandise art**: designs for prints, keychains and apparel.

## Visual Examples
### Example Input
Prompt: two friends unpacking moving boxes in a cozy living room, one holding a potted plant, with the style line "STYLE: chibitoon, chibi style, super-deformed cute body; full-body characters, entire figure in frame, centered subjects."

Settings: `model` `dev`, `go_fast` `true`, `aspect_ratio` `1:1`, `num_inference_steps` `28`, `guidance_scale` `7`, `output_format` `png`. The `height` of `300` is ignored because `aspect_ratio` is not `custom`.

```json
{
  "model": "dev",
  "height": 300,
  "prompt": "Background: cozy small apartment living room with moving boxes, warm lamp light.\n\nTwo friends unpack boxes together, one holds a small potted plant and smiles.\n\nSTYLE: chibitoon, chibi style, super-deformed cute body; full-body characters, entire figure in frame, centered subjects.",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 7,
  "output_quality": 80,
  "prompt_strength": 1,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}
```

### Example Output
![Example output: two chibi characters unpacking boxes in a cozy living room](https://blog.api.market/wp-content/uploads/2026/10/autovid-chibi-output-1waapy1v-api-market.png)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | Yes |  |  | Text prompt for the generated image. Including the trigger word used when the LoRA was trained makes its style more likely to appear. |
| `image` | string (URL) | No | none |  | Input image (URL) for image-to-image or inpainting mode. When set, `aspect_ratio`, `width` and `height` are ignored. |
| `mask` | string (URL) | No | none |  | Mask image (URL) for inpainting mode. When set, `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 to run. `dev` works best with about 28 inference 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 for the diffusion process. Lower values can look more realistic. Values of 2, 2.5, 3 and 3.5 are good starting points. |
| `seed` | integer | No | none |  | Random seed. Set it to reproduce a result. |
| `output_format` | string | No | `webp` | `webp`, `jpg`, `png` | Format of the output images. |
| `output_quality` | integer | No | `80` | 0 to 100 | Quality when saving the output images, from 0 (lowest) to 100 (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) version of the 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 | Strength of the main LoRA. Values between 0 and 1 work best for standard inference; with `go_fast` the value is multiplied by 1.5. |
| `extra_lora` | string | No | none |  | Extra LoRA weights to load on top of the main LoRA: a Hugging Face model reference, a CivitAI model reference or a direct .safetensors file URL. |
| `extra_lora_scale` | number | No | `1` | -1 to 3 | Strength of the extra LoRA. Values between 0 and 1 work best for standard inference; with `go_fast` the value is multiplied by 1.5. |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.015 per API unit.
- **1 API unit = 1 request with up to 8 seconds of processing.** A request that takes longer is billed one more unit for each started 8-second block (for example, 19 seconds of processing is 3 units, $0.045).
- More images (`num_outputs`), more steps and the `dev` model take longer and can add units; `schnell` and `go_fast` are faster.
- **Example cost**: the example request (one image with `go_fast`) took 7.5 seconds of processing, which is 1 unit ($0.015).
- **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/cute-anime-image-generator-powerpdw-autovid-chibi`

### 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/cute-anime-image-generator-powerpdw-autovid-chibi/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "a01dc4a8c788b4826e72c9c50fd7d0b0f7da2cbe323e8ca4b286f4f02fdde23e",
    "input": {
      "model": "dev",
      "height": 300,
      "prompt": "Background: cozy small apartment living room with moving boxes, warm lamp light.\n\nTwo friends unpack boxes together, one holds a small potted plant and smiles.\n\nSTYLE: chibitoon, chibi style, super-deformed cute body; full-body characters, entire figure in frame, centered subjects.",
      "go_fast": true,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 1,
      "aspect_ratio": "1:1",
      "output_format": "png",
      "guidance_scale": 7,
      "output_quality": 80,
      "prompt_strength": 1,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }'
```

Response (201 Created):
```json
{
  "id": "1waapy1vtsrmy0d1f1q8r70mxm",
  "version": "a01dc4a8c788b4826e72c9c50fd7d0b0f7da2cbe323e8ca4b286f4f02fdde23e",
  "status": "starting",
  "created_at": "2026-10-26T13:37:32.789Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/cute-anime-image-generator-powerpdw-autovid-chibi/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "1waapy1vtsrmy0d1f1q8r70mxm",
  "status": "succeeded",
  "output": [
    "https://blog.api.market/wp-content/uploads/2026/10/autovid-chibi-output-1waapy1v-api-market.png"
  ],
  "error": null,
  "created_at": "2026-10-26T13:37:32.789Z",
  "started_at": "2026-10-26T13:37:33.029Z",
  "completed_at": "2026-10-26T13:37:40.494Z"
}
```

`output` is an array of image URLs, one per generated image (`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`, `num_outputs` above 4 or a `height` below 256.
- **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
Requests are rate limited to keep usage fair. If you receive a 429 response, wait and retry with exponential backoff.

## 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/cute-anime-image-generator-powerpdw-autovid-chibi";

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: "a01dc4a8c788b4826e72c9c50fd7d0b0f7da2cbe323e8ca4b286f4f02fdde23e", 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",
  "height": 300,
  "prompt": "Background: cozy small apartment living room with moving boxes, warm lamp light.\n\nTwo friends unpack boxes together, one holds a small potted plant and smiles.\n\nSTYLE: chibitoon, chibi style, super-deformed cute body; full-body characters, entire figure in frame, centered subjects.",
  "go_fast": true,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 7,
  "output_quality": 80,
  "prompt_strength": 1,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}).then((output) => output.forEach((url) => console.log(url)));
```

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

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/cute-anime-image-generator-powerpdw-autovid-chibi"


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": "a01dc4a8c788b4826e72c9c50fd7d0b0f7da2cbe323e8ca4b286f4f02fdde23e", "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")


output = create_and_wait_for_prediction({
    "model": "dev",
    "height": 300,
    "prompt": "Background: cozy small apartment living room with moving boxes, warm lamp light.\n\nTwo friends unpack boxes together, one holds a small potted plant and smiles.\n\nSTYLE: chibitoon, chibi style, super-deformed cute body; full-body characters, entire figure in frame, centered subjects.",
    "go_fast": True,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 1,
    "aspect_ratio": "1:1",
    "output_format": "png",
    "guidance_scale": 7,
    "output_quality": 80,
    "prompt_strength": 1,
    "extra_lora_scale": 1,
    "num_inference_steps": 28,
})
for url in output:
    print(url)
```

## FAQ
- **How do I get the chibi look?**
  - Describe the scene and add a style line as in the example prompt ("chibitoon, chibi style, super-deformed cute body"). `lora_scale` sets how strongly the style is applied.
- **How many images does one request return?**
  - Between 1 and 4, set by `num_outputs` (default 1). `output` is always a list of URLs.
- **Why was `height` ignored in the example?**
  - `width` and `height` only apply when `aspect_ratio` is `custom`. The example used `1:1`.
- **Can I edit an existing image?**
  - Yes. Send it as `image` for image-to-image (`prompt_strength` sets how much changes), or add a `mask` to inpaint only part of it.
- **How much does a request cost?**
  - $0.015 for each started 8 seconds of processing. The example (one image with `go_fast`) took 7.5 seconds and cost 1 unit ($0.015); more images or steps take longer and add units.
- **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 or need assistance, you can reach out to us through the embedded chat on the bottom right corner of the page or send an email to hello@magicapi.com.


Generate cute chibi anime images from text with the AutoVid Chibi FLUX LoRA, with image-to-image and inpainting. $0.015 per request, pay as you go.