onnx ¶
ArtCNN dataclass
¶
ArtCNN(
backend: Any | None = None,
chroma_scaler: KernelT | None = None,
tiles: int | tuple[int, int] | None = None,
tilesize: int | tuple[int, int] | None = None,
overlap: int | tuple[int, int] | None = None,
*,
kernel: KernelT | None = None,
scaler: ScalerT | None = None,
shifter: KernelT | None = None
)
Bases: BaseArtCNN
Super-Resolution Convolutional Neural Networks optimised for anime.
Defaults to C16F64.
backend class-attribute
instance-attribute
¶
backend: Any | None = None
vs-mlrt backend. Will attempt to autoselect the most suitable one with fp16=True if None.
In order of trt > cuda > directml > nncn > cpu.
chroma_scaler class-attribute
instance-attribute
¶
chroma_scaler: KernelT | None = None
Scaler to upscale the chroma with.
Necessary if you're trying to use one of the chroma models but aren't passing a 444 clip.
Bilinear is probably the safe option to use.
kernel class-attribute
instance-attribute
¶
Base kernel to be used for certain scaling/shifting/resampling operations. Must be specified and defaults to catrom
scale_function instance-attribute
¶
scale_function: GenericVSFunction
Scale function called internally when scaling
scaler class-attribute
instance-attribute
¶
Scaler used for scaling operations. Defaults to kernel.
shifter class-attribute
instance-attribute
¶
Kernel used for shifting operations. Defaults to kernel.
tiles class-attribute
instance-attribute
¶
Splits up the frame into multiple tiles. Helps if you're lacking in vram but models may behave differently.
C16F64 dataclass
¶
C16F64(
backend: Any | None = None,
chroma_scaler: KernelT | None = None,
tiles: int | tuple[int, int] | None = None,
tilesize: int | tuple[int, int] | None = None,
overlap: int | tuple[int, int] | None = None,
*,
kernel: KernelT | None = None,
scaler: ScalerT | None = None,
shifter: KernelT | None = None
)
Bases: BaseArtCNN
The current default model. Looks decent and very fast. Good for AA purposes.
This has 16 internal convolution layers with 64 filters each.
backend class-attribute
instance-attribute
¶
backend: Any | None = None
vs-mlrt backend. Will attempt to autoselect the most suitable one with fp16=True if None.
In order of trt > cuda > directml > nncn > cpu.
chroma_scaler class-attribute
instance-attribute
¶
chroma_scaler: KernelT | None = None
Scaler to upscale the chroma with.
Necessary if you're trying to use one of the chroma models but aren't passing a 444 clip.
Bilinear is probably the safe option to use.
kernel class-attribute
instance-attribute
¶
Base kernel to be used for certain scaling/shifting/resampling operations. Must be specified and defaults to catrom
scale_function instance-attribute
¶
scale_function: GenericVSFunction
Scale function called internally when scaling
scaler class-attribute
instance-attribute
¶
Scaler used for scaling operations. Defaults to kernel.
shifter class-attribute
instance-attribute
¶
Kernel used for shifting operations. Defaults to kernel.
tiles class-attribute
instance-attribute
¶
Splits up the frame into multiple tiles. Helps if you're lacking in vram but models may behave differently.
ensure_obj classmethod
¶
ensure_obj(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> BaseScalerT
Source code
186 187 188 189 190 191 192 193 |
|
ensure_scaler ¶
Source code
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
|
from_param classmethod
¶
from_param(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> type[BaseScalerT]
Source code
177 178 179 180 181 182 183 184 |
|
get_clean_kwargs ¶
Source code
199 200 |
|
get_implemented_funcs ¶
Source code
270 271 |
|
get_scale_args ¶
get_scale_args(
clip: VideoNode,
shift: tuple[TopShift, LeftShift] = (0, 0),
width: int | None = None,
height: int | None = None,
*funcs: Callable[..., Any],
**kwargs: Any
) -> KwargsT
Source code
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
|
kernel_radius ¶
kernel_radius() -> int
Source code
195 196 197 |
|
multi ¶
multi(
clip: VideoNode,
multi: float = 2,
shift: tuple[TopShift, LeftShift] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
|
pretty_string ¶
pretty_string() -> str
Source code
202 203 204 205 206 207 208 209 210 211 212 213 214 |
|
scale ¶
scale(
clip: VideoNode,
width: int | None = None,
height: int | None = None,
shift: tuple[float, float] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
|
C16F64_Chroma dataclass
¶
C16F64_Chroma(
backend: Any | None = None,
chroma_scaler: KernelT | None = None,
tiles: int | tuple[int, int] | None = None,
tilesize: int | tuple[int, int] | None = None,
overlap: int | tuple[int, int] | None = None,
*,
kernel: KernelT | None = None,
scaler: ScalerT | None = None,
shifter: KernelT | None = None
)
Bases: BaseArtCNN
The bigger of the two chroma models.
These don't double the input clip and rather just try to enhance the chroma using luma information.
backend class-attribute
instance-attribute
¶
backend: Any | None = None
vs-mlrt backend. Will attempt to autoselect the most suitable one with fp16=True if None.
In order of trt > cuda > directml > nncn > cpu.
chroma_scaler class-attribute
instance-attribute
¶
chroma_scaler: KernelT | None = None
Scaler to upscale the chroma with.
Necessary if you're trying to use one of the chroma models but aren't passing a 444 clip.
Bilinear is probably the safe option to use.
kernel class-attribute
instance-attribute
¶
Base kernel to be used for certain scaling/shifting/resampling operations. Must be specified and defaults to catrom
scale_function instance-attribute
¶
scale_function: GenericVSFunction
Scale function called internally when scaling
scaler class-attribute
instance-attribute
¶
Scaler used for scaling operations. Defaults to kernel.
shifter class-attribute
instance-attribute
¶
Kernel used for shifting operations. Defaults to kernel.
tiles class-attribute
instance-attribute
¶
Splits up the frame into multiple tiles. Helps if you're lacking in vram but models may behave differently.
ensure_obj classmethod
¶
ensure_obj(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> BaseScalerT
Source code
186 187 188 189 190 191 192 193 |
|
ensure_scaler ¶
Source code
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
|
from_param classmethod
¶
from_param(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> type[BaseScalerT]
Source code
177 178 179 180 181 182 183 184 |
|
get_clean_kwargs ¶
Source code
199 200 |
|
get_implemented_funcs ¶
Source code
270 271 |
|
get_scale_args ¶
get_scale_args(
clip: VideoNode,
shift: tuple[TopShift, LeftShift] = (0, 0),
width: int | None = None,
height: int | None = None,
*funcs: Callable[..., Any],
**kwargs: Any
) -> KwargsT
Source code
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
|
kernel_radius ¶
kernel_radius() -> int
Source code
195 196 197 |
|
multi ¶
multi(
clip: VideoNode,
multi: float = 2,
shift: tuple[TopShift, LeftShift] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
|
pretty_string ¶
pretty_string() -> str
Source code
202 203 204 205 206 207 208 209 210 211 212 213 214 |
|
scale ¶
scale(
clip: VideoNode,
width: int | None = None,
height: int | None = None,
shift: tuple[float, float] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
|
C16F64_DS dataclass
¶
C16F64_DS(
backend: Any | None = None,
chroma_scaler: KernelT | None = None,
tiles: int | tuple[int, int] | None = None,
tilesize: int | tuple[int, int] | None = None,
overlap: int | tuple[int, int] | None = None,
*,
kernel: KernelT | None = None,
scaler: ScalerT | None = None,
shifter: KernelT | None = None
)
Bases: BaseArtCNN
The same as C16F64 but intended to also sharpen and denoise.
backend class-attribute
instance-attribute
¶
backend: Any | None = None
vs-mlrt backend. Will attempt to autoselect the most suitable one with fp16=True if None.
In order of trt > cuda > directml > nncn > cpu.
chroma_scaler class-attribute
instance-attribute
¶
chroma_scaler: KernelT | None = None
Scaler to upscale the chroma with.
Necessary if you're trying to use one of the chroma models but aren't passing a 444 clip.
Bilinear is probably the safe option to use.
kernel class-attribute
instance-attribute
¶
Base kernel to be used for certain scaling/shifting/resampling operations. Must be specified and defaults to catrom
scale_function instance-attribute
¶
scale_function: GenericVSFunction
Scale function called internally when scaling
scaler class-attribute
instance-attribute
¶
Scaler used for scaling operations. Defaults to kernel.
shifter class-attribute
instance-attribute
¶
Kernel used for shifting operations. Defaults to kernel.
tiles class-attribute
instance-attribute
¶
Splits up the frame into multiple tiles. Helps if you're lacking in vram but models may behave differently.
ensure_obj classmethod
¶
ensure_obj(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> BaseScalerT
Source code
186 187 188 189 190 191 192 193 |
|
ensure_scaler ¶
Source code
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
|
from_param classmethod
¶
from_param(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> type[BaseScalerT]
Source code
177 178 179 180 181 182 183 184 |
|
get_clean_kwargs ¶
Source code
199 200 |
|
get_implemented_funcs ¶
Source code
270 271 |
|
get_scale_args ¶
get_scale_args(
clip: VideoNode,
shift: tuple[TopShift, LeftShift] = (0, 0),
width: int | None = None,
height: int | None = None,
*funcs: Callable[..., Any],
**kwargs: Any
) -> KwargsT
Source code
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
|
kernel_radius ¶
kernel_radius() -> int
Source code
195 196 197 |
|
multi ¶
multi(
clip: VideoNode,
multi: float = 2,
shift: tuple[TopShift, LeftShift] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
|
pretty_string ¶
pretty_string() -> str
Source code
202 203 204 205 206 207 208 209 210 211 212 213 214 |
|
scale ¶
scale(
clip: VideoNode,
width: int | None = None,
height: int | None = None,
shift: tuple[float, float] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
|
C4F32 dataclass
¶
C4F32(
backend: Any | None = None,
chroma_scaler: KernelT | None = None,
tiles: int | tuple[int, int] | None = None,
tilesize: int | tuple[int, int] | None = None,
overlap: int | tuple[int, int] | None = None,
*,
kernel: KernelT | None = None,
scaler: ScalerT | None = None,
shifter: KernelT | None = None
)
Bases: BaseArtCNN
This has 4 internal convolution layers with 32 filters each.
If you need an even faster model.
backend class-attribute
instance-attribute
¶
backend: Any | None = None
vs-mlrt backend. Will attempt to autoselect the most suitable one with fp16=True if None.
In order of trt > cuda > directml > nncn > cpu.
chroma_scaler class-attribute
instance-attribute
¶
chroma_scaler: KernelT | None = None
Scaler to upscale the chroma with.
Necessary if you're trying to use one of the chroma models but aren't passing a 444 clip.
Bilinear is probably the safe option to use.
kernel class-attribute
instance-attribute
¶
Base kernel to be used for certain scaling/shifting/resampling operations. Must be specified and defaults to catrom
scale_function instance-attribute
¶
scale_function: GenericVSFunction
Scale function called internally when scaling
scaler class-attribute
instance-attribute
¶
Scaler used for scaling operations. Defaults to kernel.
shifter class-attribute
instance-attribute
¶
Kernel used for shifting operations. Defaults to kernel.
tiles class-attribute
instance-attribute
¶
Splits up the frame into multiple tiles. Helps if you're lacking in vram but models may behave differently.
ensure_obj classmethod
¶
ensure_obj(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> BaseScalerT
Source code
186 187 188 189 190 191 192 193 |
|
ensure_scaler ¶
Source code
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
|
from_param classmethod
¶
from_param(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> type[BaseScalerT]
Source code
177 178 179 180 181 182 183 184 |
|
get_clean_kwargs ¶
Source code
199 200 |
|
get_implemented_funcs ¶
Source code
270 271 |
|
get_scale_args ¶
get_scale_args(
clip: VideoNode,
shift: tuple[TopShift, LeftShift] = (0, 0),
width: int | None = None,
height: int | None = None,
*funcs: Callable[..., Any],
**kwargs: Any
) -> KwargsT
Source code
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
|
kernel_radius ¶
kernel_radius() -> int
Source code
195 196 197 |
|
multi ¶
multi(
clip: VideoNode,
multi: float = 2,
shift: tuple[TopShift, LeftShift] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
|
pretty_string ¶
pretty_string() -> str
Source code
202 203 204 205 206 207 208 209 210 211 212 213 214 |
|
scale ¶
scale(
clip: VideoNode,
width: int | None = None,
height: int | None = None,
shift: tuple[float, float] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
|
C4F32_Chroma dataclass
¶
C4F32_Chroma(
backend: Any | None = None,
chroma_scaler: KernelT | None = None,
tiles: int | tuple[int, int] | None = None,
tilesize: int | tuple[int, int] | None = None,
overlap: int | tuple[int, int] | None = None,
*,
kernel: KernelT | None = None,
scaler: ScalerT | None = None,
shifter: KernelT | None = None
)
Bases: BaseArtCNN
The smaller of the two chroma models.
These don't double the input clip and rather just try to enhance the chroma using luma information.
backend class-attribute
instance-attribute
¶
backend: Any | None = None
vs-mlrt backend. Will attempt to autoselect the most suitable one with fp16=True if None.
In order of trt > cuda > directml > nncn > cpu.
chroma_scaler class-attribute
instance-attribute
¶
chroma_scaler: KernelT | None = None
Scaler to upscale the chroma with.
Necessary if you're trying to use one of the chroma models but aren't passing a 444 clip.
Bilinear is probably the safe option to use.
kernel class-attribute
instance-attribute
¶
Base kernel to be used for certain scaling/shifting/resampling operations. Must be specified and defaults to catrom
scale_function instance-attribute
¶
scale_function: GenericVSFunction
Scale function called internally when scaling
scaler class-attribute
instance-attribute
¶
Scaler used for scaling operations. Defaults to kernel.
shifter class-attribute
instance-attribute
¶
Kernel used for shifting operations. Defaults to kernel.
tiles class-attribute
instance-attribute
¶
Splits up the frame into multiple tiles. Helps if you're lacking in vram but models may behave differently.
ensure_obj classmethod
¶
ensure_obj(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> BaseScalerT
Source code
186 187 188 189 190 191 192 193 |
|
ensure_scaler ¶
Source code
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
|
from_param classmethod
¶
from_param(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> type[BaseScalerT]
Source code
177 178 179 180 181 182 183 184 |
|
get_clean_kwargs ¶
Source code
199 200 |
|
get_implemented_funcs ¶
Source code
270 271 |
|
get_scale_args ¶
get_scale_args(
clip: VideoNode,
shift: tuple[TopShift, LeftShift] = (0, 0),
width: int | None = None,
height: int | None = None,
*funcs: Callable[..., Any],
**kwargs: Any
) -> KwargsT
Source code
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
|
kernel_radius ¶
kernel_radius() -> int
Source code
195 196 197 |
|
multi ¶
multi(
clip: VideoNode,
multi: float = 2,
shift: tuple[TopShift, LeftShift] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
|
pretty_string ¶
pretty_string() -> str
Source code
202 203 204 205 206 207 208 209 210 211 212 213 214 |
|
scale ¶
scale(
clip: VideoNode,
width: int | None = None,
height: int | None = None,
shift: tuple[float, float] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
|
C4F32_DS dataclass
¶
C4F32_DS(
backend: Any | None = None,
chroma_scaler: KernelT | None = None,
tiles: int | tuple[int, int] | None = None,
tilesize: int | tuple[int, int] | None = None,
overlap: int | tuple[int, int] | None = None,
*,
kernel: KernelT | None = None,
scaler: ScalerT | None = None,
shifter: KernelT | None = None
)
Bases: BaseArtCNN
The same as C4F32 but intended to also sharpen and denoise.
backend class-attribute
instance-attribute
¶
backend: Any | None = None
vs-mlrt backend. Will attempt to autoselect the most suitable one with fp16=True if None.
In order of trt > cuda > directml > nncn > cpu.
chroma_scaler class-attribute
instance-attribute
¶
chroma_scaler: KernelT | None = None
Scaler to upscale the chroma with.
Necessary if you're trying to use one of the chroma models but aren't passing a 444 clip.
Bilinear is probably the safe option to use.
kernel class-attribute
instance-attribute
¶
Base kernel to be used for certain scaling/shifting/resampling operations. Must be specified and defaults to catrom
scale_function instance-attribute
¶
scale_function: GenericVSFunction
Scale function called internally when scaling
scaler class-attribute
instance-attribute
¶
Scaler used for scaling operations. Defaults to kernel.
shifter class-attribute
instance-attribute
¶
Kernel used for shifting operations. Defaults to kernel.
tiles class-attribute
instance-attribute
¶
Splits up the frame into multiple tiles. Helps if you're lacking in vram but models may behave differently.
ensure_obj classmethod
¶
ensure_obj(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> BaseScalerT
Source code
186 187 188 189 190 191 192 193 |
|
ensure_scaler ¶
Source code
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
|
from_param classmethod
¶
from_param(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> type[BaseScalerT]
Source code
177 178 179 180 181 182 183 184 |
|
get_clean_kwargs ¶
Source code
199 200 |
|
get_implemented_funcs ¶
Source code
270 271 |
|
get_scale_args ¶
get_scale_args(
clip: VideoNode,
shift: tuple[TopShift, LeftShift] = (0, 0),
width: int | None = None,
height: int | None = None,
*funcs: Callable[..., Any],
**kwargs: Any
) -> KwargsT
Source code
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
|
kernel_radius ¶
kernel_radius() -> int
Source code
195 196 197 |
|
multi ¶
multi(
clip: VideoNode,
multi: float = 2,
shift: tuple[TopShift, LeftShift] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
|
pretty_string ¶
pretty_string() -> str
Source code
202 203 204 205 206 207 208 209 210 211 212 213 214 |
|
scale ¶
scale(
clip: VideoNode,
width: int | None = None,
height: int | None = None,
shift: tuple[float, float] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
|
R16F96 dataclass
¶
R16F96(
backend: Any | None = None,
chroma_scaler: KernelT | None = None,
tiles: int | tuple[int, int] | None = None,
tilesize: int | tuple[int, int] | None = None,
overlap: int | tuple[int, int] | None = None,
*,
kernel: KernelT | None = None,
scaler: ScalerT | None = None,
shifter: KernelT | None = None
)
Bases: BaseArtCNN
The biggest model. Can compete with or outperform Waifu2x Cunet.
Also quite a bit slower but is less heavy on vram.
backend class-attribute
instance-attribute
¶
backend: Any | None = None
vs-mlrt backend. Will attempt to autoselect the most suitable one with fp16=True if None.
In order of trt > cuda > directml > nncn > cpu.
chroma_scaler class-attribute
instance-attribute
¶
chroma_scaler: KernelT | None = None
Scaler to upscale the chroma with.
Necessary if you're trying to use one of the chroma models but aren't passing a 444 clip.
Bilinear is probably the safe option to use.
kernel class-attribute
instance-attribute
¶
Base kernel to be used for certain scaling/shifting/resampling operations. Must be specified and defaults to catrom
scale_function instance-attribute
¶
scale_function: GenericVSFunction
Scale function called internally when scaling
scaler class-attribute
instance-attribute
¶
Scaler used for scaling operations. Defaults to kernel.
shifter class-attribute
instance-attribute
¶
Kernel used for shifting operations. Defaults to kernel.
tiles class-attribute
instance-attribute
¶
Splits up the frame into multiple tiles. Helps if you're lacking in vram but models may behave differently.
ensure_obj classmethod
¶
ensure_obj(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> BaseScalerT
Source code
186 187 188 189 190 191 192 193 |
|
ensure_scaler ¶
Source code
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
|
from_param classmethod
¶
from_param(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> type[BaseScalerT]
Source code
177 178 179 180 181 182 183 184 |
|
get_clean_kwargs ¶
Source code
199 200 |
|
get_implemented_funcs ¶
Source code
270 271 |
|
get_scale_args ¶
get_scale_args(
clip: VideoNode,
shift: tuple[TopShift, LeftShift] = (0, 0),
width: int | None = None,
height: int | None = None,
*funcs: Callable[..., Any],
**kwargs: Any
) -> KwargsT
Source code
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
|
kernel_radius ¶
kernel_radius() -> int
Source code
195 196 197 |
|
multi ¶
multi(
clip: VideoNode,
multi: float = 2,
shift: tuple[TopShift, LeftShift] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
|
pretty_string ¶
pretty_string() -> str
Source code
202 203 204 205 206 207 208 209 210 211 212 213 214 |
|
scale ¶
scale(
clip: VideoNode,
width: int | None = None,
height: int | None = None,
shift: tuple[float, float] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
|
R8F64 dataclass
¶
R8F64(
backend: Any | None = None,
chroma_scaler: KernelT | None = None,
tiles: int | tuple[int, int] | None = None,
tilesize: int | tuple[int, int] | None = None,
overlap: int | tuple[int, int] | None = None,
*,
kernel: KernelT | None = None,
scaler: ScalerT | None = None,
shifter: KernelT | None = None
)
Bases: BaseArtCNN
A smaller and faster version of R16F96 but very competitive.
backend class-attribute
instance-attribute
¶
backend: Any | None = None
vs-mlrt backend. Will attempt to autoselect the most suitable one with fp16=True if None.
In order of trt > cuda > directml > nncn > cpu.
chroma_scaler class-attribute
instance-attribute
¶
chroma_scaler: KernelT | None = None
Scaler to upscale the chroma with.
Necessary if you're trying to use one of the chroma models but aren't passing a 444 clip.
Bilinear is probably the safe option to use.
kernel class-attribute
instance-attribute
¶
Base kernel to be used for certain scaling/shifting/resampling operations. Must be specified and defaults to catrom
scale_function instance-attribute
¶
scale_function: GenericVSFunction
Scale function called internally when scaling
scaler class-attribute
instance-attribute
¶
Scaler used for scaling operations. Defaults to kernel.
shifter class-attribute
instance-attribute
¶
Kernel used for shifting operations. Defaults to kernel.
tiles class-attribute
instance-attribute
¶
Splits up the frame into multiple tiles. Helps if you're lacking in vram but models may behave differently.
ensure_obj classmethod
¶
ensure_obj(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> BaseScalerT
Source code
186 187 188 189 190 191 192 193 |
|
ensure_scaler ¶
Source code
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
|
from_param classmethod
¶
from_param(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> type[BaseScalerT]
Source code
177 178 179 180 181 182 183 184 |
|
get_clean_kwargs ¶
Source code
199 200 |
|
get_implemented_funcs ¶
Source code
270 271 |
|
get_scale_args ¶
get_scale_args(
clip: VideoNode,
shift: tuple[TopShift, LeftShift] = (0, 0),
width: int | None = None,
height: int | None = None,
*funcs: Callable[..., Any],
**kwargs: Any
) -> KwargsT
Source code
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
|
kernel_radius ¶
kernel_radius() -> int
Source code
195 196 197 |
|
multi ¶
multi(
clip: VideoNode,
multi: float = 2,
shift: tuple[TopShift, LeftShift] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
|
pretty_string ¶
pretty_string() -> str
Source code
202 203 204 205 206 207 208 209 210 211 212 213 214 |
|
scale ¶
scale(
clip: VideoNode,
width: int | None = None,
height: int | None = None,
shift: tuple[float, float] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
|
R8F64_Chroma dataclass
¶
R8F64_Chroma(
backend: Any | None = None,
chroma_scaler: KernelT | None = None,
tiles: int | tuple[int, int] | None = None,
tilesize: int | tuple[int, int] | None = None,
overlap: int | tuple[int, int] | None = None,
*,
kernel: KernelT | None = None,
scaler: ScalerT | None = None,
shifter: KernelT | None = None
)
Bases: BaseArtCNN
The new and fancy big chroma model. These don't double the input clip and rather just try to enhance the chroma using luma information.
backend class-attribute
instance-attribute
¶
backend: Any | None = None
vs-mlrt backend. Will attempt to autoselect the most suitable one with fp16=True if None.
In order of trt > cuda > directml > nncn > cpu.
chroma_scaler class-attribute
instance-attribute
¶
chroma_scaler: KernelT | None = None
Scaler to upscale the chroma with.
Necessary if you're trying to use one of the chroma models but aren't passing a 444 clip.
Bilinear is probably the safe option to use.
kernel class-attribute
instance-attribute
¶
Base kernel to be used for certain scaling/shifting/resampling operations. Must be specified and defaults to catrom
scale_function instance-attribute
¶
scale_function: GenericVSFunction
Scale function called internally when scaling
scaler class-attribute
instance-attribute
¶
Scaler used for scaling operations. Defaults to kernel.
shifter class-attribute
instance-attribute
¶
Kernel used for shifting operations. Defaults to kernel.
tiles class-attribute
instance-attribute
¶
Splits up the frame into multiple tiles. Helps if you're lacking in vram but models may behave differently.
ensure_obj classmethod
¶
ensure_obj(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> BaseScalerT
Source code
186 187 188 189 190 191 192 193 |
|
ensure_scaler ¶
Source code
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
|
from_param classmethod
¶
from_param(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> type[BaseScalerT]
Source code
177 178 179 180 181 182 183 184 |
|
get_clean_kwargs ¶
Source code
199 200 |
|
get_implemented_funcs ¶
Source code
270 271 |
|
get_scale_args ¶
get_scale_args(
clip: VideoNode,
shift: tuple[TopShift, LeftShift] = (0, 0),
width: int | None = None,
height: int | None = None,
*funcs: Callable[..., Any],
**kwargs: Any
) -> KwargsT
Source code
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
|
kernel_radius ¶
kernel_radius() -> int
Source code
195 196 197 |
|
multi ¶
multi(
clip: VideoNode,
multi: float = 2,
shift: tuple[TopShift, LeftShift] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
|
pretty_string ¶
pretty_string() -> str
Source code
202 203 204 205 206 207 208 209 210 211 212 213 214 |
|
scale ¶
scale(
clip: VideoNode,
width: int | None = None,
height: int | None = None,
shift: tuple[float, float] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
|
R8F64_DS dataclass
¶
R8F64_DS(
backend: Any | None = None,
chroma_scaler: KernelT | None = None,
tiles: int | tuple[int, int] | None = None,
tilesize: int | tuple[int, int] | None = None,
overlap: int | tuple[int, int] | None = None,
*,
kernel: KernelT | None = None,
scaler: ScalerT | None = None,
shifter: KernelT | None = None
)
Bases: BaseArtCNN
The same as R8F64 but intended to also sharpen and denoise.
backend class-attribute
instance-attribute
¶
backend: Any | None = None
vs-mlrt backend. Will attempt to autoselect the most suitable one with fp16=True if None.
In order of trt > cuda > directml > nncn > cpu.
chroma_scaler class-attribute
instance-attribute
¶
chroma_scaler: KernelT | None = None
Scaler to upscale the chroma with.
Necessary if you're trying to use one of the chroma models but aren't passing a 444 clip.
Bilinear is probably the safe option to use.
kernel class-attribute
instance-attribute
¶
Base kernel to be used for certain scaling/shifting/resampling operations. Must be specified and defaults to catrom
scale_function instance-attribute
¶
scale_function: GenericVSFunction
Scale function called internally when scaling
scaler class-attribute
instance-attribute
¶
Scaler used for scaling operations. Defaults to kernel.
shifter class-attribute
instance-attribute
¶
Kernel used for shifting operations. Defaults to kernel.
tiles class-attribute
instance-attribute
¶
Splits up the frame into multiple tiles. Helps if you're lacking in vram but models may behave differently.
ensure_obj classmethod
¶
ensure_obj(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> BaseScalerT
Source code
186 187 188 189 190 191 192 193 |
|
ensure_scaler ¶
Source code
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
|
from_param classmethod
¶
from_param(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> type[BaseScalerT]
Source code
177 178 179 180 181 182 183 184 |
|
get_clean_kwargs ¶
Source code
199 200 |
|
get_implemented_funcs ¶
Source code
270 271 |
|
get_scale_args ¶
get_scale_args(
clip: VideoNode,
shift: tuple[TopShift, LeftShift] = (0, 0),
width: int | None = None,
height: int | None = None,
*funcs: Callable[..., Any],
**kwargs: Any
) -> KwargsT
Source code
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
|
kernel_radius ¶
kernel_radius() -> int
Source code
195 196 197 |
|
multi ¶
multi(
clip: VideoNode,
multi: float = 2,
shift: tuple[TopShift, LeftShift] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
|
pretty_string ¶
pretty_string() -> str
Source code
202 203 204 205 206 207 208 209 210 211 212 213 214 |
|
scale ¶
scale(
clip: VideoNode,
width: int | None = None,
height: int | None = None,
shift: tuple[float, float] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
|
ensure_obj classmethod
¶
ensure_obj(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> BaseScalerT
Source code
186 187 188 189 190 191 192 193 |
|
ensure_scaler ¶
Source code
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
|
from_param classmethod
¶
from_param(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> type[BaseScalerT]
Source code
177 178 179 180 181 182 183 184 |
|
get_clean_kwargs ¶
Source code
199 200 |
|
get_implemented_funcs ¶
Source code
270 271 |
|
get_scale_args ¶
get_scale_args(
clip: VideoNode,
shift: tuple[TopShift, LeftShift] = (0, 0),
width: int | None = None,
height: int | None = None,
*funcs: Callable[..., Any],
**kwargs: Any
) -> KwargsT
Source code
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
|
kernel_radius ¶
kernel_radius() -> int
Source code
195 196 197 |
|
multi ¶
multi(
clip: VideoNode,
multi: float = 2,
shift: tuple[TopShift, LeftShift] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
|
pretty_string ¶
pretty_string() -> str
Source code
202 203 204 205 206 207 208 209 210 211 212 213 214 |
|
scale ¶
scale(
clip: VideoNode,
width: int | None = None,
height: int | None = None,
shift: tuple[float, float] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
|
BaseArtCNN dataclass
¶
BaseArtCNN(
backend: Any | None = None,
chroma_scaler: KernelT | None = None,
tiles: int | tuple[int, int] | None = None,
tilesize: int | tuple[int, int] | None = None,
overlap: int | tuple[int, int] | None = None,
*,
kernel: KernelT | None = None,
scaler: ScalerT | None = None,
shifter: KernelT | None = None
)
Bases: _BaseArtCNN
, GenericScaler
backend class-attribute
instance-attribute
¶
backend: Any | None = None
vs-mlrt backend. Will attempt to autoselect the most suitable one with fp16=True if None.
In order of trt > cuda > directml > nncn > cpu.
chroma_scaler class-attribute
instance-attribute
¶
chroma_scaler: KernelT | None = None
Scaler to upscale the chroma with.
Necessary if you're trying to use one of the chroma models but aren't passing a 444 clip.
Bilinear is probably the safe option to use.
kernel class-attribute
instance-attribute
¶
Base kernel to be used for certain scaling/shifting/resampling operations. Must be specified and defaults to catrom
scale_function instance-attribute
¶
scale_function: GenericVSFunction
Scale function called internally when scaling
scaler class-attribute
instance-attribute
¶
Scaler used for scaling operations. Defaults to kernel.
shifter class-attribute
instance-attribute
¶
Kernel used for shifting operations. Defaults to kernel.
tiles class-attribute
instance-attribute
¶
Splits up the frame into multiple tiles. Helps if you're lacking in vram but models may behave differently.
ensure_obj classmethod
¶
ensure_obj(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> BaseScalerT
Source code
186 187 188 189 190 191 192 193 |
|
ensure_scaler ¶
Source code
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
|
from_param classmethod
¶
from_param(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> type[BaseScalerT]
Source code
177 178 179 180 181 182 183 184 |
|
get_clean_kwargs ¶
Source code
199 200 |
|
get_implemented_funcs ¶
Source code
270 271 |
|
get_scale_args ¶
get_scale_args(
clip: VideoNode,
shift: tuple[TopShift, LeftShift] = (0, 0),
width: int | None = None,
height: int | None = None,
*funcs: Callable[..., Any],
**kwargs: Any
) -> KwargsT
Source code
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
|
kernel_radius ¶
kernel_radius() -> int
Source code
195 196 197 |
|
multi ¶
multi(
clip: VideoNode,
multi: float = 2,
shift: tuple[TopShift, LeftShift] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
|
pretty_string ¶
pretty_string() -> str
Source code
202 203 204 205 206 207 208 209 210 211 212 213 214 |
|
scale ¶
scale(
clip: VideoNode,
width: int | None = None,
height: int | None = None,
shift: tuple[float, float] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
|
GenericOnnxScaler dataclass
¶
GenericOnnxScaler(
model: SPathLike,
backend: Any | None = None,
tiles: int | tuple[int, int] | None = None,
tilesize: int | tuple[int, int] | None = None,
overlap: int | tuple[int, int] | None = None,
*,
kernel: KernelT | None = None,
scaler: ScalerT | None = None,
shifter: KernelT | None = None
)
Bases: GenericScaler
Generic scaler class for an onnx model.
backend class-attribute
instance-attribute
¶
backend: Any | None = None
vs-mlrt backend. Will attempt to autoselect the most suitable one with fp16=True if None.
In order of trt > cuda > directml > nncn > cpu.
kernel class-attribute
instance-attribute
¶
Base kernel to be used for certain scaling/shifting/resampling operations. Must be specified and defaults to catrom
scale_function instance-attribute
¶
scale_function: GenericVSFunction
Scale function called internally when scaling
scaler class-attribute
instance-attribute
¶
Scaler used for scaling operations. Defaults to kernel.
shifter class-attribute
instance-attribute
¶
Kernel used for shifting operations. Defaults to kernel.
tiles class-attribute
instance-attribute
¶
Splits up the frame into multiple tiles. Helps if you're lacking in vram but models may behave differently.
ensure_obj classmethod
¶
ensure_obj(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> BaseScalerT
Source code
186 187 188 189 190 191 192 193 |
|
ensure_scaler ¶
Source code
130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 |
|
from_param classmethod
¶
from_param(
scaler: str | type[BaseScalerT] | BaseScalerT | None = None,
/,
func_except: FuncExceptT | None = None,
) -> type[BaseScalerT]
Source code
177 178 179 180 181 182 183 184 |
|
get_clean_kwargs ¶
Source code
199 200 |
|
get_implemented_funcs ¶
Source code
270 271 |
|
get_scale_args ¶
get_scale_args(
clip: VideoNode,
shift: tuple[TopShift, LeftShift] = (0, 0),
width: int | None = None,
height: int | None = None,
*funcs: Callable[..., Any],
**kwargs: Any
) -> KwargsT
Source code
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 |
|
kernel_radius ¶
kernel_radius() -> int
Source code
195 196 197 |
|
multi ¶
multi(
clip: VideoNode,
multi: float = 2,
shift: tuple[TopShift, LeftShift] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
239 240 241 242 243 244 245 246 247 248 249 250 251 252 |
|
pretty_string ¶
pretty_string() -> str
Source code
202 203 204 205 206 207 208 209 210 211 212 213 214 |
|
scale ¶
scale(
clip: VideoNode,
width: int,
height: int,
shift: tuple[float, float] = (0, 0),
**kwargs: Any
) -> VideoNode
Source code
34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 |
|
autoselect_backend ¶
Source code
80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 |
|