I added Qwen-Image 2.1 + LoRA support to TensorSharp (GGUF, local inference)

TensorSharp, an open-source inference engine, now supports local inference for Qwen-Image 2.1, enabling text-to-image generation and image editing. This update also includes support for Qwen-Image 2.1's LoRA adapters. Users can try specific adapters like Pruna with a command-line interface, specifying configurations, LoRA files, prompts, and image dimensions. The developer is interested in user feedback regarding useful LoRAs and the performance of accelerated ones.