# Overview

AI-powered image enhancement and manipulation on CLORE.AI GPUs.

## Available Guides

| Tool                                                                               | Use Case              |
| ---------------------------------------------------------------------------------- | --------------------- |
| [Real-ESRGAN](https://docs.clore.ai/guides/image-processing/real-esrgan-upscaling) | Image/video upscaling |
| [GFPGAN](https://docs.clore.ai/guides/image-processing/gfpgan-face-restore)        | Face restoration      |
| [ControlNet](https://docs.clore.ai/guides/image-processing/controlnet-advanced)    | Guided generation     |
| [Segment Anything](https://docs.clore.ai/guides/image-processing/segment-anything) | Object segmentation   |
| [Depth Anything](https://docs.clore.ai/guides/image-processing/depth-anything)     | Depth estimation      |
| [ICLight](https://docs.clore.ai/guides/image-processing/iclight)                   | Relighting            |

## Common Tasks

| Task              | Tool             |
| ----------------- | ---------------- |
| Upscale 2x-4x     | Real-ESRGAN      |
| Fix blurry faces  | GFPGAN           |
| Remove background | Segment Anything |
| Add depth         | Depth Anything   |
| Change lighting   | ICLight          |

## GPU Requirements

Most tools run on 8GB+ VRAM. RTX 3060 or better recommended.

## Related Guides

* [Image Generation](https://docs.clore.ai/guides/image-generation/image-generation)
* [Video Processing](https://docs.clore.ai/guides/video-processing/video-processing)
* [Face Identity](https://docs.clore.ai/guides/face-and-identity/face-identity)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.clore.ai/guides/image-processing/image-processing.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.