Add SeFi-Image pipeline

### Model/Pipeline/Scheduler description

We are proposing the integration of SeFi-Image into Diffusers.

SeFi-Image is a text-to-image model family built with Semantic-First Diffusion. It separates image generation into semantic and texture latent streams, denoising the semantic structure slightly ahead of texture details so the texture stream receives a cleaner structural anchor during generation.

Key characteristics:

- Semantic-first generation: separates semantic and texture latents and advances the semantic denoising stream to improve structural consistency.
- Generation-reconstruction trade-off: combines a compact semantic latent for easier generation with a high-fidelity texture latent for reconstruction detail.
- Multiple model scales and variants: 1B/2B/5B Base checkpoints, 5B RL checkpoint, and 1B/2B/5B Turbo checkpoints.
- Few-step Turbo inference: Turbo checkpoints default to 4 denoising steps with guidance scale 1.0.
- Standard text-to-image usage: prompt-to-image generation at 1024x1024 by default.

The proposed Diffusers integration adds:

- `SeFiTransformer2DModel`
- `SeFiPipeline`
- an original-checkpoint conversion script
- API documentation
- fast model and pipeline tests

The current implementation was validated with the real `SeFi-Image/SeFi-Image-1B-turbo` checkpoint, including conversion, 1024x1024 inference parity against a reference output, and CPU offload smoke testing.

### Open source status

- [x] The model implementation is available.
- [x] The model weights are available (Only relevant if addition is not a scheduler).

### Provide useful links for the implementation

- GitHub repository: https://github.com/jmliu206/SeFi-Image
- Project page: https://jmliu206.github.io/sefi-web/
- Technical report: https://arxiv.org/pdf/2606.22568
- Hugging Face organization / model collection: https://huggingface.co/SeFi-Image
- Example checkpoints:
- https://huggingface.co/SeFi-Image/SeFi-Image-1B-Base
- https://huggingface.co/SeFi-Image/SeFi-Image-2B-Base
- https://huggingface.co/SeFi-Image/SeFi-Image-5B-Base
- https://huggingface.co/SeFi-Image/SeFi-Image-5B-RL
- https://huggingface.co/SeFi-Image/SeFi-Image-1B-turbo
- https://huggingface.co/SeFi-Image/SeFi-Image-2B-turbo
- https://huggingface.co/SeFi-Image/SeFi-Image-5B-turbo
- Diffusers implementation PR: https://github.com/huggingface/diffusers/pull/14084

### Additional context

This is an official integration proposal from the SeFi-Image authors/maintainers. The draft PR is already open with the implementation and validation results, and can be adjusted based on maintainer feedback on the desired scope or API shape.

Inizia con la PR di implementazione #14084 e il repository SeFi-Image per comprendere il SeFiTransformer2DModel proposto, SeFiPipeline, lo script di conversione, la documentazione e i test. Il lavoro è completato quando l'integrazione viene accettata con la conversione, la parità dell'output di riferimento 1024x1024, uno smoke test del CPU offload e test rapidi del modello e della pipeline.

Scritto dal modello di indicizzazione a partire dal testo della issue.