# Instant ID - Anime Generator

Turn a face into 3D, emoji, pixel art, video game, claymation or toy

## API Information

- **Model Slug:** instant-id-ip-adapter
- **Branded URL:** https://www.eachlabs.ai/tencent/instant-id/instant-id-ip-adapter
- **Provider:** Tencent
- **Category:** Image to Image
- **Output Type:** array
- **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:** 12 seconds
- **Last Updated:** 2026-04-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/instant-id-ip-adapter

## 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 |
|-----------|------|----------|---------|-------------|-------------|
| image | string | Yes | - | image/jpeg, image/png, image/jpg, image/webp | An image of a person to be converted |
| style | string | No | 3D | 3D,Emoji,Video game,Pixels,Clay,Toy | An enumeration. |
| prompt | string | No | a person | - | Text prompt for image generation |
| negative_prompt | string | No | - | - | Things you do not want in the image |
| denoising_strength | number | No | 0.65 | 0–1 | How much of the original image to keep. 1 is the complete destruction of the original image, 0 is the original image |
| prompt_strength | number | No | 4.5 | 0–20 | Strength of the prompt. This is the CFG scale, higher numbers lead to stronger prompt, lower numbers will keep more of a likeness to the original. |
| control_depth_strength | number | No | 0.8 | 0–1 | Strength of depth controlnet. The bigger this is, the more controlnet affects the output. |
| instant_id_strength | number | No | 1 | 0–1 | How strong the InstantID will be. |
| seed | integer | No | - | - | Fix the random seed for reproducibility |
| custom_lora_url | string | No | - | - | - |
| lora_scale | number | No | 1 | 0–1 | How strong the LoRA will be |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "instant-id-ip-adapter",
  "input": {
    "image": "https://cdn.eachlabs.ai/ipfs/KW7Getr2zD5ECxySdBZtLmPa322lNkXrpkMdKcmxeaDmq2b1/MTk4MTczMTkzNzI1Mjg5NjYy.webp"
  }
}'
```

## Output Schema

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

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "array",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer 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 `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**instant-id-ip-adapter — Image-to-Image AI Model**

Developed by Tencent as part of the **instant-id** family, **instant-id-ip-adapter** is an advanced **image-to-image AI model** that transforms a single face image into diverse styles like 3D renders, emojis, pixel art, video game characters, claymation, or toy figures while preserving facial identity. This Tencent image-to-image tool solves the challenge of style transfer without losing key identity features, enabling creators to generate stylized portraits instantly for gaming, animation, or social media. Ideal for developers seeking an **instant-id-ip-adapter API** or users exploring **image-to-image AI models**, it leverages IP-Adapter technology for precise control over artistic reinterpretations.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer 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.