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

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.

feat: increase MAX_LORAS to 10

Add Anima-3.8B-v1.1 architecture model.

Add SenseNova-U1.5 architecture model.

Add Anima-3.8B architecture model.

Add Krea-2 Anythng Controlnet.

Upgrade to Gradio 6

Add MCP tool examples

Fix PiD Injector.

Optimize API/MCP Tools.

Add High-Level API/MCP Tools

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.

Upload pipeline_input_processor.py

Add Mage-Flow architecture model.

Upload 109 files

Add JoyAI-Image architecture model.

Add AuraFlow architecture model.

Add Ideogram-4 and Kandinsky-5 architecture models

Add Boogu-Image and Cosmos-Predict2 architecture models

Add Krea-2 architecture and Krea-2 ControlNet injector

Add PID (Pixel Diffusion Decoder) injector

Refactor UI event handlers into subpackage

Add specialized & anime architectures (Anima, HiDream, Qwen, ERNIE, Hunyuan, Lumina, NewBie...)

Add FLUX.1, FLUX.2-KV, SD3.5 & additional base model architecture recipes

Add LoRA injector to replace pre-merged LoRAs

Add Reference Latent Chains

Add FLUX.2 architecture model

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