refactor(controlnet): align Qwen-Image-2.1 with merged Fun ControlNet and bump upstream deps

feat: add Qwen-Image-2.1 ControlNet support, consolidate unified pipeline, and significantly reduce frontend components

feat: add Ming-Image architecture & Prompt Enhancer and update upstream deps

refactor: simplify Qwen-Image-2.1 prompt enhancer and update dependencies

feat: add Qwen-Image-2.1 prompt enhancer

refactor(injectors): consolidate boogu and qwen-2.1 into reference_image with flexible max_images

Add Qwen-Image-2.1 architecture model.

Krea-2 Identity Edit injector: Add image scaling before VAE encode.

Add SenseNova-U1.5 architecture model.

Fix PiD Injector.

Add High-Level API/MCP Tools

Upload krea2_style_reference_injector.py

Optimize workflows and configuration files, and standardize file naming.

Add Boogu Edit Injector.

Add Krea-2 Reference Edit injector.

Add Qwen-Image Edit injector.

Add Krea-2 Identity Edit injector.

Add Mage-Flow architecture model.

Add JoyAI-Image architecture model.

Add AuraFlow architecture model.

Add Anima ControlNet-LLLite, HiDream-01 smoothing/reference & PID injectors

Add Krea-2 architecture and Krea-2 ControlNet injector

Add PID (Pixel Diffusion Decoder) injector

Refactor UI event handlers into subpackage

Add IP-Adapter, Style & Reference Latent injectors

Add ControlNet, DiffSynth ControlNet & VAE injectors

Add LoRA injector to replace pre-merged LoRAs

Add Reference Latent Chains

Add matrix-style dynamic workflows: task_type x model_type x chain_inject; rename Space to ImageGen