ControlNet Scribble

Input

Prompt

Steps

Scheduler

Seed

Input Image

Uploaded

Output

output


ControlNet Scribble

ControlNet is a neural network architechture that can be used to control pretrained large diffusion models to support additional input conditions. The purpose of ControlNet-Scribble is to enable conditional input of raw outlines or scribbled drawings to control large diffusion models and facilitate related applications.

Weights

These weights were trained on stable diffusion 1.5.

Features

  • User Sketching: ControlNet Scribble help Controlling Stable Diffusion with Human scribbles and transform raw sketches into stunning images

Applications

ControlNet Scribble can be utilized in various applications, such as:

  • Art generation
  • Scene creation
  • Animation and game development
  • Character creation
  • Product design

Getting Started

For more detailed instructions, refer to the API documentation and resources available on Github.

Github

https://github.com/lllyasviel/ControlNet

License

Apache License 2.0