Mannequins / Pose Dummies (Qwen-Image-Edit 2509)

Creates pose dummy mannequins from reference images.

The intended use case is to use the resulting images as pose references for pose transfer or for LoRA training.

Training (target) images were generated by Nano Banana Pro.

Sample prompt (pretty much what I used on Nano Banana to generate the training data):

Generate a picture of abstract CGI mannequins in the exact same pose as the people in the image. The mannequins should have fingers, toes, and an abstract representation of facial expression. The mannequins do not have any hair. They have perfectly clean gray skin with a black wireframe overlaid on top without any discolorations. The background of the image is a plain featureless middle gray void. Do not include any objects the people in the image may or may not be interacting with.

You can get somewhat similar results out of base Qwen-Image-Edit with appropriate prompting, but it is a lot less consistent in my experience.

It seems to work okay with cfg = 1.0 and steps = 20. Higher cfg values can produce better results, but may affect how faithful the result is.
The 8-step Lightning LoRA can also be very viable.

Notes:

• The wireframe is optional (it should go away if it's not mentioned in the prompt).

• The colors of the skin, wireframe, and background are adjustable.