# Finegrain Image Enhancer - Inference Endpoint

This repository contains the Inference Endpoint version of the Finegrain Image Enhancer.

## Usage

Send a POST request to the endpoint with:

```json
{
  "image": "base64_encoded_image_data",
  "prompt": "masterpiece, best quality, highres",
  "upscale_factor": 2.0,
  "seed": 42
}
```

Returns:
```json
{
  "enhanced_image": "base64_encoded_enhanced_image",
  "original_size": [width, height],
  "enhanced_size": [width, height]
}
```

## Parameters

- `image` (required): Base64 encoded input image
- `prompt` (optional): Enhancement prompt (default: "masterpiece, best quality, highres")
- `negative_prompt` (optional): Negative prompt (default: "worst quality, low quality, normal quality")
- `seed` (optional): Random seed (default: 42)
- `upscale_factor` (optional): Upscale factor 1-4 (default: 2.0)
- `controlnet_scale` (optional): ControlNet scale 0-1.5 (default: 0.6)
- `controlnet_decay` (optional): ControlNet decay 0.5-1 (default: 1.0)
- `condition_scale` (optional): Condition scale 2-20 (default: 6)
- `tile_width` (optional): Tile width 64-200 (default: 112)
- `tile_height` (optional): Tile height 64-200 (default: 144)
- `denoise_strength` (optional): Denoise strength 0-1 (default: 0.35)
- `num_inference_steps` (optional): Number of steps 1-30 (default: 18)
- `solver` (optional): Solver type "DDIM" or "DPMSolver" (default: "DDIM")