# Illusion Diffusion

Illusion Diffusion creates artistic and surreal visuals using advanced diffusion algorithms

## API Information

- **Model Slug:** illusion-diffusion-hq
- **Branded URL:** https://www.eachlabs.ai/stability/illusion-diffusion/illusion-diffusion-hq
- **Provider:** Stability AI
- **Category:** Image to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Per-second pricing based on provider predict_time. Rate: $0.00108/sec from GPU tier.
- **Estimated Processing Time:** 9 seconds
- **Last Updated:** 2026-04-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/illusion-diffusion-hq

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Per-second pricing based on provider predict_time. Rate: $0.00108/sec from GPU tier.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Per-second pricing based on provider predict_time. Rate: $0.00108/sec from GPU tier. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | The prompt to guide QR Code generation. |
| qr_code_content | string | No | - | - | The website/content your QR Code will point to. |
| negative_prompt | string | No | ugly, disfigured, low quality, blurry, nsfw | - | The negative prompt to guide image generation. |
| num_inference_steps | integer | No | 40 | 20–100 | Number of diffusion steps |
| guidance_scale | number | No | 7.5 | 1–30 | Scale for classifier-free guidance |
| seed | integer | No | -1 | - | Seed |
| width | integer | No | 768 | - | Width out the output image |
| height | integer | No | 768 | - | Height out the output image |
| num_outputs | integer | No | 1 | 1–4 | Number of outputs |
| image | string | No | - | image/jpeg, image/png, image/jpg, image/webp | Input image. If none is provided, a QR code will be generated |
| controlnet_conditioning_scale | number | No | 1 | 0–4 | The outputs of the controlnet are multiplied by `controlnet_conditioning_scale` before they are added to the residual in the original unet. |
| border | integer | No | 1 | 0–4 | QR code border size |
| qrcode_background | string | No | gray | gray,white | An enumeration. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "illusion-diffusion-hq",
  "input": {
    "prompt": "(masterpiece:1.4), (best quality), (detailed), Medieval village scene with busy streets and castle in the distance"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated image)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "X-API-Key: YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `X-API-Key` |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**illusion-diffusion-hq — Image-to-Image AI Model**

illusion-diffusion-hq from Stability revolutionizes **image-to-image AI model** workflows by transforming single composite images into layered, manipulable RGBA components using advanced diffusion algorithms, enabling surreal artistic edits and 2.5D animations without manual separation. Developed as part of the illusion-diffusion family, this model excels at decomposing complex visuals like anime characters into semantic body parts with pixel-perfect transparency and hidden geometry, solving the challenge of intricate layer stratification such as interleaving hair strands. Users searching for **Stability image-to-image** tools find illusion-diffusion-hq ideal for high-fidelity reconstructions at 1024x1024 resolution, producing outputs ready for real-time animation and professional applications.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `X-API-Key: YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.