# Proteus v0.2 - Core.Today AI API

> Popular anime-focused image model (12M+ runs) — high-quality anime and illustration styles with img2img and inpainting support. The go-to for anime avatars and webtoon-style art.

- **Provider**: Proteus
- **Model ID**: datacte/proteus-v0.2
- **Category**: Image Generation
- **Credits**: 35 per image (num_outputs billed per image)
- **Speed**: Medium
- **Quality**: High

## Features
- Anime and illustration specialization
- img2img and inpainting with mask
- Up to 4 outputs per run (billed per image)
- Fine guidance following at low CFG

## Use Cases
- Anime avatars and characters
- Webtoon-style illustration
- Game character concepts
- Anime-style marketing art

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Optional
- **prompt**: string (default: black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed) - Image description (anime tags work well)
- **negative_prompt**: string (default: worst quality, low quality) - What to avoid
- **image**: string - Input image for img2img
- **mask**: string - Inpainting mask
- **width**: integer (default: 1024) - Output width
- **height**: integer (default: 1024) - Output height
- **num_outputs**: integer (default: 1) - Number of images (1-4). Billed per image
- **scheduler**: string (default: KarrasDPM) - scheduler
  Options: DDIM, DPMSolverMultistep, HeunDiscrete, KarrasDPM, K_EULER_ANCESTRAL, K_EULER, PNDM
- **num_inference_steps**: integer (default: 20) - Number of denoising steps. 20 to 35 steps for more detail, 20 steps for faster results.
- **guidance_scale**: number (default: 7.5) - CFG scale (1-50)
- **prompt_strength**: number (default: 0.8) - Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
- **seed**: integer - Random seed
- **apply_watermark**: boolean (default: true) - Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
- **disable_safety_checker**: boolean (default: false) - Disable safety checker for generated images. This feature is only available through the API. See https://replicate.com/docs/how-does-replicate-work#safety

## Examples

### Anime Character
Generate an anime-style character portrait
```json
{
  "model": "datacte/proteus-v0.2",
  "input": {
    "prompt": "anime girl with silver hair, cherry blossom background, soft lighting, best quality, highly detailed",
    "width": 1024,
    "height": 1024
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Booru-style tags ('best quality, highly detailed, anime') work great in prompts
- Keep guidance_scale around 7-8; Proteus follows prompts well without high CFG
- Use img2img with a rough sketch for pose-controlled anime art

## Documentation
https://replicate.com/datacte/proteus-v0.2