Outfit To Outfit – ControlNet (outfit2outfit)

This is a ControlNet model! This model requires ControlNet!

Model Details

This model aims to allow users to modify what a subject is wearing in a given image while keeping the subject, background and pose consistent.

I’ve produced good results in txt2img, img2img as well as inpainting.
I’ve produced good results with images generated with Stable Diffusion as well as with pictures I’ve taken myself.

Installation

Place the .safetensors file into ControlNet’s ‘models’ directory. To use the model, select the ‘outfitToOutfit’ model under ControlNet Model with ‘none’ selected under Preprocessor.

Tips for use

• Images with a clearly defined subject tend to work better.

• Prompts that contain “The same woman” or “The same man” help trigger the model to keep consistency (see sample images)

• This model tends to work best at lower resolutions (close to 512px)

  • If you run into trouble at higher resolutions, try running a first pass at a lower resolution and then using img2img with a lower denoising strength to upscale to a higher resolution while continuing to use your original input image as input to this ControlNet model

• I recommend starting with CFG 3 when using ControlNet weight 1

  • Higher CFG values when combined with high ControlNet weight can lead to burnt looking images.

  • Experiment with ControlNet weights 0.4, 0.5, 0.6, 0.8 and 1. (Lower weight allows for more changes, higher weight tries to keep the output similar to the input)

• When using img2img or inpainting, I recommend starting with 1 denoising strength

  • Experiment with 0.75 denoising strength

• When inpainting, I recommend trying “latent nothing” under Masked content

• Consider lowering the model’s weight when generating higher resolution images

  • The higher the resolution of the output image, the more difficult it tends to be to alter the content of the image from the input image

• The model is biased towards women. When using male subjects, it may be necessary to increase the weight on “man” or masculine features in the prompts to prevent the model from creating a more feminine result (will attempt to fix in future versions)

• If the output isn’t changing enough from the input, try increasing the weight of the prompts or decreasing the weight of the model

• Can work well with other models such as OpenPose ControlNet and Clothing Adjuster Lora

• This model can produce NSFW content. Putting more weight on prompts such as “dressed as” or “wearing a” does a pretty good job of mitigating NSFW generations. I’ve also found using a Clothing Adjuster Lora with a negative weight works well.