# Clarity Upscaler

> The famous creative upscaler (30M+ runs). Re-imagines details while upscaling — controllable creativity/resemblance, prompt guidance, and up to high scale factors.

- **Provider**: replicate
- **Model ID**: philz1337x/clarity-upscaler
- **Category**: image_upscale_restore
- **Credits**: 60 per request
- **Pricing Type**: fixed

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `image` (string, **required**): input image
- `downscaling` (boolean, optional): Downscale the image before upscaling. Can improve quality and speed for images with high resolution but lower quality (Default: `False`)
- `sharpen` (number, optional): Sharpen the image after upscaling. The higher the value, the more sharpening is applied. 0 for no sharpening (Default: `0`; Range: min: 0, max: 10)
- `tiling_height` (integer, optional): Fractality, set lower tile height for a high Fractality (Default: `144`; Options: `16`, `32`, `48`, `64`, `80`, `96`, `112`, `128`, `144`, `160`, `176`, `192`, `208`, `224`, `240`, `256`)
- `seed` (integer, optional): Random seed. Leave blank to randomize the seed (Default: `1337`)
- `tiling_width` (integer, optional): Fractality, set lower tile width for a high Fractality (Default: `112`; Options: `16`, `32`, `48`, `64`, `80`, `96`, `112`, `128`, `144`, `160`, `176`, `192`, `208`, `224`, `240`, `256`)
- `lora_links` (string, optional): Link to a lora file you want to use in your upscaling. Multiple links possible, seperated by comma (Default: ``)
- `custom_sd_model` (string, optional) (Default: ``)
- `resemblance` (number, optional): Resemblance, try from 0.3 - 1.6 (Default: `0.6`; Range: min: 0, max: 3)
- `pattern` (boolean, optional): Upscale a pattern with seamless tiling (Default: `False`)
- `downscaling_resolution` (integer, optional): Downscaling resolution (Default: `768`)
- `handfix` (string, optional): Use clarity to fix hands in the image (Default: `disabled`; Options: `disabled`, `hands_only`, `image_and_hands`)
- `scale_factor` (number, optional): Scale factor (Default: `2`)
- `scheduler` (string, optional): scheduler (Default: `DPM++ 3M SDE Karras`; Options: `DPM++ 2M Karras`, `DPM++ SDE Karras`, `DPM++ 2M SDE Exponential`, `DPM++ 2M SDE Karras`, `Euler a`, `Euler`, `LMS`, `Heun`, `DPM2`, `DPM2 a`, `DPM++ 2S a`, `DPM++ 2M`, `DPM++ SDE`, `DPM++ 2M SDE`, `DPM++ 2M SDE Heun`, `DPM++ 2M SDE Heun Karras`, `DPM++ 2M SDE Heun Exponential`, `DPM++ 3M SDE`, `DPM++ 3M SDE Karras`, `DPM++ 3M SDE Exponential`, `DPM fast`, `DPM adaptive`, `LMS Karras`, `DPM2 Karras`, `DPM2 a Karras`, `DPM++ 2S a Karras`, `Restart`, `DDIM`, `PLMS`, `UniPC`)
- `output_format` (string, optional): Format of the output images (Default: `png`; Options: `webp`, `jpg`, `png`)
- `negative_prompt` (string, optional): Negative Prompt (Default: `(worst quality, low quality, normal quality:2) JuggernautNegative-neg`)
- `dynamic` (number, optional): HDR, try from 3 - 9 (Default: `6`; Range: min: 1, max: 50)
- `creativity` (number, optional): Creativity, try from 0.3 - 0.9 (Default: `0.35`; Range: min: 0, max: 1)
- `prompt` (string, optional): Prompt (Default: `masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>`)
- `sd_model` (string, optional): Stable Diffusion model checkpoint (Default: `juggernaut_reborn.safetensors [338b85bc4f]`; Options: `epicrealism_naturalSinRC1VAE.safetensors [84d76a0328]`, `juggernaut_reborn.safetensors [338b85bc4f]`, `flat2DAnimerge_v45Sharp.safetensors`)
- `num_inference_steps` (integer, optional): Number of denoising steps (Default: `18`; Range: min: 1, max: 100)
- `mask` (string, optional): Mask image to mark areas that should be preserved during upscaling

## Example Request

```json
{
  "model": "philz1337x/clarity-upscaler",
  "input": {
    "image": "https://replicate.delivery/pbxt/KiDB5iqtTcxiTI17WASotG1Ei0TNJCztdU6J02pnMYAd8B1X/13_before-4.png",
    "downscaling": false,
    "seed": 1337,
    "tiling_height": 144,
    "lora_links": "",
    "tiling_width": 112,
    "custom_sd_model": "",
    "resemblance": 0.6,
    "downscaling_resolution": 768,
    "scale_factor": 2,
    "scheduler": "DPM++ 3M SDE Karras",
    "negative_prompt": "(worst quality, low quality, normal quality:2) JuggernautNegative-neg",
    "dynamic": 6,
    "creativity": 0.35,
    "prompt": "masterpiece, best quality, highres, <lora:more_details:0.5> <lora:SDXLrender_v2.0:1>",
    "sd_model": "juggernaut_reborn.safetensors [338b85bc4f]",
    "num_inference_steps": 18
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

upscaling, super-resolution, creative-upscale, clarity, detail-enhancement

## Documentation

https://replicate.com/philz1337x/clarity-upscaler