sketchkit.image2sketch package

Subpackages

Submodules

sketchkit.image2sketch.generator module

Unified interface for image-to-sketch methods.

class sketchkit.image2sketch.generator.SketchGenerator(method: str = 'SwiftSketch', **kwargs: Any)[source]

Bases: object

Generate sketches with one of the supported image-to-sketch methods.

static create(method: str = 'SwiftSketch', **kwargs: Any) → Any[source]

Create the selected backend.

run(input: Image | ndarray | str | Sequence[Image | ndarray | str], size: int | Tuple[int, int] | None = None) → Sketch | Image | list[Sketch] | list[Image][source]

Generate a sketch from the supplied image input.

Module contents

Unified image-to-sketch interface and backend classes.

class sketchkit.image2sketch.AniLinesModel(*, checkpoint_dir: str | PathLike | None = None, mode: str = 'basic', device: str | device | None = None, binarize: float = -1.0, fp16: bool = True)[source]

Bases: object

High level wrapper around the AniLines LineExtractor.

DEFAULT_CHECKPOINT_DIR = PosixPath('/home/euruson/.cache/sketchkit/image2sketch/anilines')
_infer_single(image: Image, size: int | Tuple[int, int] | None = None) → Image[source]
_initialise_net() → Module[source]
_resolve_model_path() → Path[source]
_to_pil_image(image: Image | ndarray | str | PathLike) → Image[source]
generate(image: Image | ndarray | str | PathLike | Sequence[Image | ndarray | str | PathLike], *, size: int | Tuple[int, int] | None = None) → Image | List[Image][source]
class sketchkit.image2sketch.HEDModel(*, checkpoint_dir: str | PathLike | None = None, auto_download: bool = True, postprocess: bool = True, postprocess_threshold: float = 0.09803921568627451, postprocess_small_edge: int = 5)[source]

Bases: object

High level wrapper around the original HED Caffe model.

MEAN_BGR = (104.00698793, 116.66876762, 122.67891434)
MODEL_FILENAME = 'hed_pretrained_bsds.caffemodel'
MODEL_SHA1 = '2c5d7842f25f880eec62fc610b500c5cf2aa351d'
MODEL_URL = 'https://vcl.ucsd.edu/hed/hed_pretrained_bsds.caffemodel'
static _download_weights(url: str, destination: Path, expected_sha1: str) → None[source]
_infer_single(net: Any, image: Image, size: Tuple[int, int]) → Image[source]
_initialise_net() → Any[source]
static _to_pil_image(image: Image | ndarray | str | PathLike) → Image[source]
static _validate_sha1(path: Path, expected_hex: str) → bool[source]
property checkpoint_dir: Path
ensure_assets() → None[source]

Ensure the pretrained weights are available locally.

generate(image: Image | ndarray | str | PathLike | Sequence[Image | ndarray | str | PathLike], *, size: int | Tuple[int, int] | None = None) → Image | List[Image][source]

Generate edge maps for the provided image(s).

class sketchkit.image2sketch.PhotoSketchModel(*, checkpoint_dir: str | PathLike | None = None, model_name: str = 'pretrained', auto_download: bool = True, device: str | device | None = None, input_size: int = 256)[source]

Bases: object

High level wrapper around the PhotoSketch Pix2Pix generator.

DEFAULT_CHECKPOINT_DIR = PosixPath('/home/euruson/.cache/sketchkit/image2sketch/photosketch')
DEFAULT_INPUT_SIZE = 256
DEFAULT_MODEL_NAME = 'pretrained'
GENERATOR_FILENAME = 'latest_net_G.pth'
GENERATOR_SHA1 = '5968e8f007c650008a265c11f2d2a3887e5840d4'
INPUT_CHANNELS = 3
MODEL_ARCHIVE_NAME = 'photosketch_pretrained.zip'
MODEL_DOWNLOAD_URL = 'https://drive.google.com/uc?export=download&id=1TQf-LyS8rRDDapdcTnEgWzYJllPgiXdj'
MODEL_DRIVE_ID = '1TQf-LyS8rRDDapdcTnEgWzYJllPgiXdj'
NUM_FILTERS = 64
OUTPUT_CHANNELS = 1
RESNET_BLOCKS = 9
_download_and_extract() → None[source]
_extract_archive(archive_path: Path) → None[source]
_initialise_generator() → Module[source]
_install_from_local_archive() → bool[source]
_install_from_local_file() → bool[source]
_prepare_tensor(image: Image) → Tensor[source]
static _resolve_device(device: str | device | None) → device[source]
static _resolve_size(size: int | Tuple[int, int]) → Tuple[int, int][source]
_tensor_to_image(tensor: Tensor, size: Tuple[int, int]) → Image[source]
static _to_pil_image(image: Image | ndarray | str | PathLike) → Image[source]
static _validate_sha1(path: Path, expected: str) → bool[source]
property checkpoint_dir: Path
ensure_assets() → None[source]

Ensure that the pretrained PhotoSketch weights exist locally.

generate(image: Image | ndarray | str | PathLike | Sequence[Image | ndarray | str | PathLike], *, size: int | Tuple[int, int] | None = None) → Image | List[Image][source]

Generate sketch images for the provided image input(s).

generate_batch(images: Sequence[Image | ndarray | str | PathLike], *, size: int | Tuple[int, int] | None = None) → List[Image][source]

Generate sketches for a batch of images.

class sketchkit.image2sketch.SketchGenerator(method: str = 'SwiftSketch', **kwargs: Any)[source]

Bases: object

Generate sketches with one of the supported image-to-sketch methods.

static create(method: str = 'SwiftSketch', **kwargs: Any) → Any[source]

Create the selected backend.

run(input: Image | ndarray | str | Sequence[Image | ndarray | str], size: int | Tuple[int, int] | None = None) → Sketch | Image | list[Sketch] | list[Image][source]

Generate a sketch from the supplied image input.

class sketchkit.image2sketch.SwiftSketchModel(*, device: str | device | None = None, use_refine: bool = True, guidance_param: float = 2.5, fix_scale: bool = True, checkpoint_dir: str | PathLike | None = None, auto_download: bool = True, mask_model_factory: Callable[[device], Module] | None = None, feature_extractor_factory: Callable[[device, str], Module] | None = None, diffusion_factory: Callable[[SimpleNamespace], Tuple[Module, object]] | None = None, refine_model_factory: Callable[[SimpleNamespace], Module] | None = None)[source]

Bases: object

High level wrapper around the SwiftSketch diffusion pipeline.

static _control_points_to_sketch(control_points: Tensor, canvas_size: Tuple[int, int]) → Sketch[source]
_default_diffusion_factory(args: SimpleNamespace) → Tuple[Module, object][source]
_default_feature_extractor_factory(device: device, image_features_type: str) → Module[source]
_default_mask_model_factory(device: device) → Module[source]
static _device_index(device: device) → int[source]
_ensure_archive(archive_path: Path, url: str) → None[source]
static _find_model_member(zf: ZipFile, folder: str) → str[source]
_initialise_pipeline() → None[source]
static _load_args(archive_path: Path, folder: str) → SimpleNamespace[source]
_load_state_dict(archive_path: Path, folder: str) → dict[source]
static _resolve_device(device: str | device | None) → device[source]

Determine which device SwiftSketch should run on.

By default, a CUDA-capable GPU is required. Users can override the selection via the SKETCHKIT_SWIFTSKETCH_DEVICE environment variable or by explicitly passing a device argument. When neither is supplied and CUDA is unavailable, the model refuses to run unless the SKETCHKIT_ALLOW_CPU_FALLBACK environment variable is set to "1". This makes it possible to exercise the pipeline on CPU for testing while keeping the production default focused on GPU runtimes.

static _resolve_size(size: int | Tuple[int, int]) → Tuple[int, int][source]
static _to_pil_image(image: Image | ndarray | str | PathLike) → Image[source]
property checkpoint_dir: Path
property device: device
ensure_assets() → None[source]

Ensure that the model archives are available locally.

generate(image: Image | ndarray | str | PathLike | Sequence[Image | ndarray | str | PathLike], size: int | Tuple[int, int] | None = None) → Sketch | List[Sketch][source]

Generate sketches for the provided image(s).

generate_batch(images: Sequence[Image | ndarray | str | PathLike], *, size: int | Tuple[int, int] | None = None) → List[Sketch][source]
property model_archive_path: Path
property refine_archive_path: Path