Official Description:

This model is an image structure control LoRA trained on Qwen-Image, utilizing an In Context technical approach. It supports multiple conditions: canny, depth, lineart, softedge, normal, and openpose. The training framework is built on DiffSynth-Studio, and the dataset used is Qwen-Image-Self-Generated-Dataset. It is recommended that input prompts start with "Context_Control. ".

Please note that when using Openpose control, due to the unique nature of this control type, it cannot achieve a "point-to-point" control effect similar to other control types.

Reprinted from: Qwen-lmage-In-Context-Control-Union