Qwen-Image-DiffSynth-ControlNets

Note: All model files below must be downloaded via the LM Downloader client. If you do not have the client, Download >>>

DiffSynth-ControlNets include a model patch that supports three different control modes: canny, depth, and inpaint. And a LoRA for image structure control, trained based on Qwen-Image, adopting the In Context technical approach. It supports multiple conditions: canny, depth, lineart, softedge, normal, and openpose.

Name	Size	Target Dir
qwen_image_canny_diffsynth_controlnet.safetensors	2.27 GB	model_patches
qwen_image_depth_diffsynth_controlnet.safetensors	2.27 GB	model_patches
qwen_image_inpaint_diffsynth_controlnet.safetensors	2.27 GB	model_patches
qwen_image_union_diffsynth_lora.safetensors	943.91 MB	loras