Qwen Image ControlNet Union This repository provides a unified ControlNet that supports 4 common control types (canny, soft edge, depth, pose) for Qwen Image. Model Cards This ControlNet consists of 5 double blocks copied from the pretrained transformer layers. We train the model from scratch for 50K steps using a dataset of 10M high quality general and human images. We train at 1328x1328 resolution in BFloat16, batch size=64, learning rate=4e 5. We set the text drop ratio to 0.10. This model supports multiple control modes, including canny, soft edge, depth, pose. You can use it just as a normal ControlNet. Showcases Inference Inference Setting You can adjust control strength via controlnet conditioning scale. Canny: use cv2.Canny, set controlnet conditioning scale in [0.8, 1.0] Soft Edge: use AnylineDetector, set controlnet conditioning scale in [0.8, 1.0] Depth: use depth anything, set controlnet conditioning scale in [0.8, 1.0] Pose: use DWPose, set controlnet conditioning scale in [0.8, 1.0] We strongly recommend using detailed prompts, especially when include text elements. For example, use "a poster with text 'InstantX Team' on the top" instead of "a poster". For multiple co…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy