cedoysch / flux-fill-redux-try-on

Virtual fitting of clothes

  • Public
  • 116 runs

Run time and cost

This model costs approximately $0.20 to run on Replicate, or 5 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 4 minutes. The predict time for this model varies significantly based on the inputs.

Readme

This model allows users to visualize how the selected clothes will look in the image of a person. The model accepts a photo of a person, an image of clothing, and the type of clothing (upper, lower, or overall – a one-piece outfit). Based on the set parameters, processing takes place using the ComfyUI workflow, which includes image loading and scaling, mask generation, and clothing overlay on the photo.

Input data:

person_image: A photo of the person on whom the clothes will be “applied”.

cloth_image: An image of the selected clothing. Important: for a correct fitting, the image of the clothes must be 1024×1024 pixels in size.

clot_type: The type of clothing where:

upper — outerwear (T-shirt, jacket, etc.),

lower — undergarments (trousers, skirt, etc.),

overall — clothes for the whole body (complex image).

Output data:

A generated image in which clothes are superimposed on a photo of a person. The final image has a size of 1024×768 pixels.