Support on Patreon

A tool to create input images

Use the prompt: put the clothes on the left onto the person on the right.

Strength: 1.5

Notes:

• This first version seems to not transfer complex patterns very well but adheres to the model's body shape very well supporting a very wide range of body types.

• I recommend a good upscaler like SeedVR2 to finalize the output as some of the fine details will be lost.

• Doesn't work consistently with shoes, hats or other accessories

ComfyUI Workflow is the official Qwen Edit Workflow template tuned to fp8_e4m3fn + 4steps (but i usually do 6 to 8 steps) with an extra LoadLoraModelOnly node to load the lora. If you'd like a specific LORA trained, send me a message. Commissions are open.

Trained with AI Toolkit: