[Feature Request] Native support for LongCat-Image-Edit model

### Description
I would like to request native support for the **LongCat-Image-Edit** model. It was released nearly a month ago and currently achieves SOTA performance among open-source image editing models.

It supports bilingual (English-Chinese) instructions, precise editing, and has specific capabilities for text rendering within images.

### Model Details
- **HuggingFace:** [meituan-longcat/LongCat-Image-Edit](https://huggingface.co/meituan-longcat/LongCat-Image-Edit)
- **Paper:** [ArXiv 2512.07584](https://arxiv.org/pdf/2512.07584)
- **License:** Apache 2.0

### Implementation Context
The model is currently implemented via `diffusers` using a custom pipeline (`LongCatImageEditPipeline`).

### Important Note on Text Rendering
There is a specific requirement for this model regarding text generation. As stated in their README:

> For both Text-to-Image and Image Editing tasks involving text generation, **you must enclose the target text within single or double quotation marks**.
> The model utilizes a specialized **character-level encoding** strategy specifically for quoted content.

It would be great if the native node implementation could handle this logic or if the prompt parser could support this behavior to ensure high-quality text rendering results.

Thank you!