Name: Anything V4.0 API: Anime Text to Image Generator
Brand: magicapi
SKU: api-magicapi-anime-style-image-generator-cjwbw-anything-v4-0
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎨 Anime Text-to-Image Generator API (cjwbw Anything V4.0)

## Overview
Anything V4.0 is a Stable Diffusion model tuned for anime-style images, published by cjwbw. Its developer describes it as producing high-quality, highly detailed anime-style images.

Send a text `prompt` (tag-style prompts such as "1boy, bishounen, casual" work well with this model) and the API returns a list of image URLs. You choose the size from a fixed list (128 to 1024 pixels per side), 1 or 4 images per request, the scheduler, the guidance scale and the number of denoising steps.

## Features
- **Anime-style text to image**: generate anime illustrations and characters from a `prompt`.
- **Negative prompt**: list what you do not want to see with `negative_prompt`.
- **Fixed sizes**: `width` and `height` each accept 128, 256, 512, 640, 704, 768, 896 or 1024 (default 512). The largest supported size is 1024 x 768 or 768 x 1024.
- **1 or 4 images**: `num_outputs` is either 1 or 4.
- **Schedulers**: `DDIM`, `K_EULER`, `DPMSolverMultistep` (default), `K_EULER_ANCESTRAL`, `PNDM`, `KLMS`.
- **Guidance and steps**: `guidance_scale` from 1 to 20 (default 7), `num_inference_steps` from 1 to 500 (default 20).
- **Seed**: set `seed` to reproduce a result; leave it empty for a random seed.

## Use Cases
1. **Anime characters**: character portraits and scenes for games, stories and fan projects.
2. **Avatars and profile art**: square anime-style images at 512 x 512.
3. **Storyboards and concept sketches**: quick anime-style drafts of a scene.
4. **Picking from variations**: request 4 images at once and keep the best.

## Visual Examples
### Example Input
Prompt: "1boy, bishounen, casual, indoors, sitting, coffee shop, bokeh"

Settings: `width` 512, `height` 512, `scheduler` `DPMSolverMultistep`, `num_outputs` 1, `guidance_scale` 7, `num_inference_steps` 20.

### Example Output
![Anything V4.0 output generated from the coffee shop example prompt](https://blog.api.market/wp-content/uploads/2026/10/anything-v4-0-output-pa8d5pwc-api-market-1.png)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | No | `1boy, bishounen, casual, indoors, sitting, coffee shop, bokeh` |  | Input prompt |
| `negative_prompt` | string | No | none |  | What you do not want to see in the image. Ignored when not using guidance |
| `width` | integer | No | `512` | `128`, `256`, `512`, `640`, `704`, `768`, `896`, `1024` | Width of the output image. Maximum size is 1024x768 or 768x1024 because of memory limits |
| `height` | integer | No | `512` | `128`, `256`, `512`, `640`, `704`, `768`, `896`, `1024` | Height of the output image. Maximum size is 1024x768 or 768x1024 because of memory limits |
| `num_outputs` | integer | No | `1` | `1`, `4` | Number of images to output |
| `num_inference_steps` | integer | No | `20` | 1 to 500 | Number of denoising steps |
| `guidance_scale` | number | No | `7` | 1 to 20 | Scale for classifier-free guidance |
| `scheduler` | string | No | `DPMSolverMultistep` | `DDIM`, `K_EULER`, `DPMSolverMultistep`, `K_EULER_ANCESTRAL`, `PNDM`, `KLMS` | Scheduler to use |
| `seed` | integer | No | none |  | Random seed. Leave blank to randomize the seed |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.0016 per API unit.
- **1 API unit = 1 successful request with up to 6 seconds of processing.** A request that takes longer is billed one more unit for each started block of 6 seconds (for example, 10 seconds of processing is 2 units, $0.0032).
- Larger sizes, more steps and 4 images per request take longer to process and can use more than one unit.
- **Example cost**: the example request above took 5.8 seconds of processing, so it used 1 API unit and cost $0.0016.
- **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/anime-style-image-generator-cjwbw-anything-v4-0`

### 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/anime-style-image-generator-cjwbw-anything-v4-0/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "42a996d39a96aedc57b2e0aa8105dea39c9c89d9d266caf6bb4327a1c191b061",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "1boy, bishounen, casual, indoors, sitting, coffee shop, bokeh",
      "scheduler": "DPMSolverMultistep",
      "num_outputs": 1,
      "guidance_scale": 7,
      "num_inference_steps": 20
    }
  }'
```

Response (201 Created):
```json
{
  "id": "pa8d5pwcxxrgc0d1cckvrqdrg0",
  "version": "42a996d39a96aedc57b2e0aa8105dea39c9c89d9d266caf6bb4327a1c191b061",
  "status": "starting",
  "created_at": "2026-10-22T10:28:19.109Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/anime-style-image-generator-cjwbw-anything-v4-0/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "pa8d5pwcxxrgc0d1cckvrqdrg0",
  "status": "succeeded",
  "output": [
    "https://blog.api.market/wp-content/uploads/2026/10/anything-v4-0-output-pa8d5pwc-api-market-1.png"
  ],
  "error": null,
  "created_at": "2026-10-22T10:28:19.109Z",
  "started_at": "2026-10-22T10:31:44.265Z",
  "completed_at": "2026-10-22T10:31:50.096Z"
}
```

`output` is a list of PNG image URLs, one per 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 `width` that is not in the list or `num_outputs` other than 1 or 4.
- **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.
- Sizes above 1024 x 768 (or 768 x 1024) can exceed the model's memory; use a smaller size if a request fails.
- 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/anime-style-image-generator-cjwbw-anything-v4-0";

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: "42a996d39a96aedc57b2e0aa8105dea39c9c89d9d266caf6bb4327a1c191b061", 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({
  width: 512,
  height: 512,
  prompt: "1boy, bishounen, casual, indoors, sitting, coffee shop, bokeh",
  scheduler: "DPMSolverMultistep",
  num_outputs: 1,
  guidance_scale: 7,
  num_inference_steps: 20
}).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/anime-style-image-generator-cjwbw-anything-v4-0"


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": "42a996d39a96aedc57b2e0aa8105dea39c9c89d9d266caf6bb4327a1c191b061", "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({
    "width": 512,
    "height": 512,
    "prompt": "1boy, bishounen, casual, indoors, sitting, coffee shop, bokeh",
    "scheduler": "DPMSolverMultistep",
    "num_outputs": 1,
    "guidance_scale": 7,
    "num_inference_steps": 20
}))
```

## FAQ
- **What prompt style works best?**
  - The model's default prompt is a list of comma-separated tags ("1boy, bishounen, casual, indoors, sitting, coffee shop, bokeh"). Short tag lists like this describe subject, setting and style.
- **How many images can I get per request?**
  - 1 or 4, set with `num_outputs`. Other values are rejected.
- **What is the largest image I can generate?**
  - 1024 x 768 or 768 x 1024. Larger combinations can run out of memory.
- **How is a request billed?**
  - $0.0016 per request for up to 6 seconds of processing, plus one more unit for each further started block of 6 seconds. The example request (512 x 512, 20 steps, 1 image) took 5.8 seconds and cost $0.0016.
- **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 anime-style images from text prompts with Anything V4.0, a Stable Diffusion model, in sizes up to 1024 x 768. $0.0016 per request, pay as you go.