[enhancement]: Adding a Image-Tagger section to help prompts

### Is there an existing issue for this?

- [x] I have searched the existing issues

### Contact Details

luisfilipeac91@gmail.com

### What should this feature add?

I am requesting the development of a dedicated UI section or a button that leverages AI tagger models to automatically generate accurate descriptive prompts from uploaded asset images. This feature would significantly streamline the workflow for users of image generation models, particularly SDXL.

Detailed Description:
Currently, creating high-quality prompts from scratch can be time-consuming and require expert knowledge. Implementing a built-in feature that analyzes an image and automatically outputs a structured text prompt would greatly enhance usability and efficiency.

The functionality would work as follows:

A user uploads an image (e.g., a character, an object, a landscape).

The tool processes the image using a selected Interrogator/Tagger model.

The system generates a comprehensive text prompt listing identified tags (e.g., 1girl, blonde_hair, blue_eyes, looking_at_viewer, jacket, outdoors, daylight).

This generated prompt is then presented to the user in a text box, ready to be used directly or refined as needed before sending it to the image generation model.

We suggest integrating support for established, high-performance tagger models such as:
wd-v1-4-convnext-tagger-v2
wd-v1-4-convnextv2-tagger-v2
wd-v1-4-moat-tagger-v2
wd-v1-4-swinv2-tagger-v2
wd-v1-4-vit-tagger-v2

Key Benefit:
This feature is especially powerful for SDXL workflows. SDXL excels at interpreting and leveraging highly detailed, natural language prompts. By using these taggers to generate rich, descriptive tags from a reference image, users can effortlessly create optimized prompts that unlock SDXL's full potential, leading to higher quality and more faithful output generations.

### Alternatives

Today I use self-hosted image tagger by replicate:
https://replicate.com/zsxkib/wd-image-tagger

### Additional Content
Here's a mockup image