sketchkit.colorization package

Subpackages

• sketchkit.colorization.models package
  • Submodules
  • sketchkit.colorization.models.controlnet_lineart module
    • ControlNetLineartModel
      • ControlNetLineartModel.generate()
  • sketchkit.colorization.models.controlnet_scribble module
    • ControlNetScribbleModel
      • ControlNetScribbleModel.generate()
  • Module contents
    • ControlNetLineartModel
      • ControlNetLineartModel.generate()
    • ControlNetScribbleModel
      • ControlNetScribbleModel.generate()

Submodules

sketchkit.colorization.colorizer module

Colorizer for sketch colorization tasks.

This class provides functionality to colorize vector sketches using various AI methods.

class sketchkit.colorization.colorizer.Colorizer(method: str = 'controlnet_lineart', device: str = 'cuda', **kwargs: Any)

Bases: object

A class for sketch colorization.

This class provides functionality to colorize vector sketches using various AI methods.

method

The colorization method that is used.

Type:

str

device

The device that is used.

Type:

str

_model

The loaded AI model instance.

_generate_with_control_image(control_image: Image, prompt: str, size: int | Tuple[int, int], **kwargs: Any) → Image

Generate colorized image using control image.

_prepare_control_image(image: ndarray | Image) → Image

Prepare control image from rasterized sketch or PIL image.

_run_with_image(image: Image | ndarray, prompt: str, size: int | Tuple[int, int] | None, input_size: Tuple[int, int] | None, **kwargs: Any) → Image

Run colorization with Image input.

_run_with_sketch(sketch: Sketch, prompt: str, size: int | Tuple[int, int] | None, input_size: Tuple[int, int] | None, **kwargs: Any) → Image

Run colorization with Sketch input.

_sketch_to_raster(sketch: Sketch, size: int | Tuple[int, int] = 512, background_color: Tuple[float, float, float] = (1, 1, 1), stroke_width: int = 3, fit_canvas: bool = True) → ndarray

Convert sketch to rasterized image using CairoRenderer.

run(input_data: Sketch | Image | ndarray, prompt: str = 'vibrant colors, anime style', size: int | Tuple[int, int] | None = None, input_size: Tuple[int, int] | None = None, **kwargs: Any) → Image

Colorize the input sketch or image.

Parameters:

• input_data – Input can be: - Sketch: Vector sketch object - Image.Image: PIL Image object - np.ndarray: Numpy array image

• prompt – Text description guiding the colorization.

• size – Output image size (int for square, tuple for rectangle). If None, for Sketch input, uses sketch’s height and width; for Image input, uses the image size.

• input_size – Optional input resize dimensions (height, width). If provided, the input will be resized before processing.

Keyword Args for Generation Control:

stroke_width (int): Stroke width for rasterization. Defaults to 2. fit_canvas (bool): Whether to fit sketch to canvas. Defaults to True. num_inference_steps (int): Number of inference steps. Defaults to 20. guidance_scale (float): CFG scale for text guidance. Defaults to 7.5. controlnet_conditioning_scale (float): ControlNet conditioning scale. Defaults to 1.0. negative_prompt (str): Negative prompt to avoid unwanted features.

Defaults to “blurry, low quality, distorted”.

seed (int): Random seed for reproducibility. Optional.

Returns:

Colorized image as PIL Image.

Module contents

Sketch Colorization

This module provides a unified API for colorizing vector sketches.

class sketchkit.colorization.Colorizer(method: str = 'controlnet_lineart', device: str = 'cuda', **kwargs: Any)

Bases: object

A class for sketch colorization.

This class provides functionality to colorize vector sketches using various AI methods.

method

The colorization method that is used.

Type:

str

device

The device that is used.

Type:

str

_model

The loaded AI model instance.

_generate_with_control_image(control_image: Image, prompt: str, size: int | Tuple[int, int], **kwargs: Any) → Image

Generate colorized image using control image.

_prepare_control_image(image: ndarray | Image) → Image

Prepare control image from rasterized sketch or PIL image.

_run_with_image(image: Image | ndarray, prompt: str, size: int | Tuple[int, int] | None, input_size: Tuple[int, int] | None, **kwargs: Any) → Image

Run colorization with Image input.

_run_with_sketch(sketch: Sketch, prompt: str, size: int | Tuple[int, int] | None, input_size: Tuple[int, int] | None, **kwargs: Any) → Image

Run colorization with Sketch input.

_sketch_to_raster(sketch: Sketch, size: int | Tuple[int, int] = 512, background_color: Tuple[float, float, float] = (1, 1, 1), stroke_width: int = 3, fit_canvas: bool = True) → ndarray

Convert sketch to rasterized image using CairoRenderer.

run(input_data: Sketch | Image | ndarray, prompt: str = 'vibrant colors, anime style', size: int | Tuple[int, int] | None = None, input_size: Tuple[int, int] | None = None, **kwargs: Any) → Image

Colorize the input sketch or image.

Parameters:

• input_data – Input can be: - Sketch: Vector sketch object - Image.Image: PIL Image object - np.ndarray: Numpy array image

• prompt – Text description guiding the colorization.

• size – Output image size (int for square, tuple for rectangle). If None, for Sketch input, uses sketch’s height and width; for Image input, uses the image size.

• input_size – Optional input resize dimensions (height, width). If provided, the input will be resized before processing.

Keyword Args for Generation Control:

stroke_width (int): Stroke width for rasterization. Defaults to 2. fit_canvas (bool): Whether to fit sketch to canvas. Defaults to True. num_inference_steps (int): Number of inference steps. Defaults to 20. guidance_scale (float): CFG scale for text guidance. Defaults to 7.5. controlnet_conditioning_scale (float): ControlNet conditioning scale. Defaults to 1.0. negative_prompt (str): Negative prompt to avoid unwanted features.

Defaults to “blurry, low quality, distorted”.

seed (int): Random seed for reproducibility. Optional.

Returns:

Colorized image as PIL Image.