add support of doubao image

[yuzukumo]

Support text-to-image, image-to-image, multi-image input, and grouped image generation
Support Seedream 5.0 options including size, output_format, watermark, and optional web search

[OrenZhang]

请先执行 pre-commit 格式化代码哈

pip install pre-commit pylint

make lint

[Copilot]

Pull request overview

Adds a new OpenWebUI pipe that integrates Doubao (Seedream 5.0) image generation, including multi-image inputs and Seedream-specific options, returning generated images via OpenWebUI file uploads.

Changes:

• Introduces pipes/doubao_image.py implementing a Doubao image generation pipe.
• Adds message parsing to collect prompts + input images (markdown/file refs and image_url items).
• Uploads returned base64 images to OpenWebUI and formats results as markdown in SSE responses.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[yuzukumo]

Run and pass the developer-required formatting and checks via make lint (pre-commit + pylint)