free counter
Tech

Stable Diffusion Text-Prompt-Based Inpainting Replace Hair, Fashion

This project can help you do prompt-based inpainting without needing to paint the mask – using Stable Diffusion and Clipseg

Open In Colab

It’s currently a notebook based project but we are able to convert it right into a Gradio Web UI.

It requires 3 mandatory inputs.

  1. Input Image URL
  2. Prompt of the part in the input image that you would like to displace
  3. Output Prompt

There are specific parameters that you could tune

  1. Mask Precision
  2. Stable Diffusion Generation Strength

Step-by-Step Tutorial – https://www.youtube.com/watch?v=bv1Wur3DvZ0

Inital Req:

Requires:

  • GPU (runs fine on Google Colab Tesla T4)

patttinson

Read More

Related Articles

Leave a Reply

Your email address will not be published.

Back to top button

Adblock Detected

Please consider supporting us by disabling your ad blocker