sketchkit.sketch2image package

Subpackages

• sketchkit.sketch2image.models package
  • Submodules
  • sketchkit.sketch2image.models.controlnet module
    • ControlNetModel
      • ControlNetModel.generate()
  • sketchkit.sketch2image.models.pix2pix module
    • Pix2PixModel
      • Pix2PixModel.generate()
  • sketchkit.sketch2image.models.t2i_adapter module
    • T2IAdapterModel
      • T2IAdapterModel.generate()
  • Module contents
    • ControlNetModel
      • ControlNetModel.generate()
    • Pix2PixModel
      • Pix2PixModel.generate()
    • T2IAdapterModel
      • T2IAdapterModel.generate()

Submodules

sketchkit.sketch2image.image_generator module

ImageGenerator for sketch-to-image conversion tasks.

This class provides functionality to convert vector sketches to realistic images using various AI methods.

class sketchkit.sketch2image.image_generator.ImageGenerator(method: str = 'controlnet', device: str = 'cuda', **kwargs: Any)

Bases: object

A class for sketch-to-image conversion.

This class provides functionality to convert vector sketches to realistic images using various AI methods.

method

The conversion method that is used.

Type:

str

device

The device that is used.

Type:

str

_model

The loaded AI model instance.

_prepare_control_image(image: ndarray | Image) → Image

Prepare control image from rasterized sketch or PIL image.

_prepare_t2i_adapter_image(image: ndarray | Image) → Image

Special preparation for T2I-Adapter edge detection.

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

Run ControlNet-based sketch-to-image conversion.

_run_pix2pix(control_image: Image, prompt: str, size: int | Tuple[int, int], **kwargs: Any) → Image

Run Pix2Pix-based sketch-to-image conversion.

_run_t2i_adapter(control_image: Image, prompt: str, size: int | Tuple[int, int], **kwargs: Any) → Image

Run T2I-Adapter-based sketch-to-image conversion.

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

Run sketch-to-image conversion 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 sketch-to-image conversion 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 = 'a realistic photo', size: int | Tuple[int, int] | None = None, input_size: Tuple[int, int] | None = None, **kwargs: Any) → Image

Convert the input sketch or image to realistic 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 image generation.

• 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 3. 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. adapter_conditioning_scale (float): T2I-Adapter conditioning scale. Defaults to 1.0. image_guidance_scale (float): Pix2Pix image guidance scale. Defaults to 1.0. seed (int): Random seed for reproducibility. Optional.

Returns:

Generated image as PIL Image.

Module contents

Sketch-to-Image Conversions

This module provides a unified API for converting vector sketches into realistic images.

class sketchkit.sketch2image.ImageGenerator(method: str = 'controlnet', device: str = 'cuda', **kwargs: Any)

Bases: object

A class for sketch-to-image conversion.

This class provides functionality to convert vector sketches to realistic images using various AI methods.

method

The conversion method that is used.

Type:

str

device

The device that is used.

Type:

str

_model

The loaded AI model instance.

_prepare_control_image(image: ndarray | Image) → Image

Prepare control image from rasterized sketch or PIL image.

_prepare_t2i_adapter_image(image: ndarray | Image) → Image

Special preparation for T2I-Adapter edge detection.

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

Run ControlNet-based sketch-to-image conversion.

_run_pix2pix(control_image: Image, prompt: str, size: int | Tuple[int, int], **kwargs: Any) → Image

Run Pix2Pix-based sketch-to-image conversion.

_run_t2i_adapter(control_image: Image, prompt: str, size: int | Tuple[int, int], **kwargs: Any) → Image

Run T2I-Adapter-based sketch-to-image conversion.

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

Run sketch-to-image conversion 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 sketch-to-image conversion 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 = 'a realistic photo', size: int | Tuple[int, int] | None = None, input_size: Tuple[int, int] | None = None, **kwargs: Any) → Image

Convert the input sketch or image to realistic 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 image generation.

• 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 3. 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. adapter_conditioning_scale (float): T2I-Adapter conditioning scale. Defaults to 1.0. image_guidance_scale (float): Pix2Pix image guidance scale. Defaults to 1.0. seed (int): Random seed for reproducibility. Optional.

Returns:

Generated image as PIL Image.