Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Updates based on code review by @RyanJDick

Browse Source
This commit is contained in:
skunkworxdark 2023-12-09 18:38:07 +00:00
parent 5f37176938
commit 494c2a9b05
3 changed files with 27 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
invokeai/app/invocations/tiles.py
View File

@ -66,7 +66,7 @@ class CalculateImageTilesInvocation(BaseInvocation):
@invocation( @invocation(
"calculate_image_tiles_Even_Split", "calculate_image_tiles_even_split",
title="Calculate Image Tiles Even Split", title="Calculate Image Tiles Even Split",
tags=["tiles"], tags=["tiles"],
category="tiles", category="tiles",
@ -93,7 +93,7 @@ class CalculateImageTilesEvenSplitInvocation(BaseInvocation):
default=0.25, default=0.25,
ge=0, ge=0,
lt=1, lt=1,
description="Overlap amount of tile size (0-1)", description="Overlap between adjacent tiles as a fraction of the tile's dimensions (0-1)",
) )
def invoke(self, context: InvocationContext) -> CalculateImageTilesOutput: def invoke(self, context: InvocationContext) -> CalculateImageTilesOutput:
@ -126,7 +126,8 @@ class CalculateImageTilesMinimumOverlapInvocation(BaseInvocation):
min_overlap: int = InputField( min_overlap: int = InputField(
default=128, default=128,
ge=0, ge=0,
description="minimum tile overlap size (must be a multiple of 8)", multiple_of=8,
description="Minimum overlap between adjacent tiles, in pixels(must be a multiple of 8).",
) )
round_to_8: bool = InputField( round_to_8: bool = InputField(
default=False, default=False,
@ -260,10 +261,12 @@ class MergeTilesToImageInvocation(BaseInvocation, WithMetadata, WithWorkflow):
merge_tiles_with_linear_blending( merge_tiles_with_linear_blending(
dst_image=np_image, tiles=tiles, tile_images=tile_np_images, blend_amount=self.blend_amount dst_image=np_image, tiles=tiles, tile_images=tile_np_images, blend_amount=self.blend_amount
) )
else: elif self.blend_mode == "Seam":
merge_tiles_with_seam_blending( merge_tiles_with_seam_blending(
dst_image=np_image, tiles=tiles, tile_images=tile_np_images, blend_amount=self.blend_amount dst_image=np_image, tiles=tiles, tile_images=tile_np_images, blend_amount=self.blend_amount
) )
else:
raise ValueError(f"Unsupported blend mode: '{self.blend_mode}'.")
# Convert into a PIL image and save # Convert into a PIL image and save
pil_image = Image.fromarray(np_image) pil_image = Image.fromarray(np_image)

23
invokeai/backend/tiles/tiles.py
View File

@ -2,11 +2,12 @@ import math
from typing import Union from typing import Union
import numpy as np import numpy as np
from invokeai.app.invocations.latent import LATENT_SCALE_FACTOR
from invokeai.backend.tiles.utils import TBLR, Tile, paste, seam_blend from invokeai.backend.tiles.utils import TBLR, Tile, paste, seam_blend
def calc_overlap(tiles: list[Tile], num_tiles_x, num_tiles_y) -> list[Tile]: def calc_overlap(tiles: list[Tile], num_tiles_x: int, num_tiles_y: int) -> list[Tile]:
"""Calculate and update the overlap of a list of tiles. """Calculate and update the overlap of a list of tiles.
Args: Args:
@ -110,23 +111,27 @@ def calc_tiles_even_split(
image_width (int): The image width in px. image_width (int): The image width in px.
num_x_tiles (int): The number of tile to split the image into on the X-axis. num_x_tiles (int): The number of tile to split the image into on the X-axis.
num_y_tiles (int): The number of tile to split the image into on the Y-axis. num_y_tiles (int): The number of tile to split the image into on the Y-axis.
overlap (int, optional): The target overlap amount of the tiles size. Defaults to 0. overlap (float, optional): The target overlap amount of the tiles size. Defaults to 0.
Returns: Returns:
list[Tile]: A list of tiles that cover the image shape. Ordered from left-to-right, top-to-bottom. list[Tile]: A list of tiles that cover the image shape. Ordered from left-to-right, top-to-bottom.
""" """
# Ensure tile size is divisible by 8 # Ensure tile size is divisible by 8
if image_width % 8 != 0 or image_height % 8 != 0: if image_width % LATENT_SCALE_FACTOR != 0 or image_height % LATENT_SCALE_FACTOR != 0:
raise ValueError(f"image size (({image_width}, {image_height})) must be divisible by 8") raise ValueError(f"image size (({image_width}, {image_height})) must be divisible by 8")
# Calculate the overlap size based on the percentage and adjust it to be divisible by 8 (rounding up) # Calculate the overlap size based on the percentage and adjust it to be divisible by 8 (rounding up)
overlap_x = 8 * math.ceil(int((image_width / num_tiles_x) * overlap) / 8) overlap_x = LATENT_SCALE_FACTOR * math.ceil(int((image_width / num_tiles_x) * overlap) / LATENT_SCALE_FACTOR)
overlap_y = 8 * math.ceil(int((image_height / num_tiles_y) * overlap) / 8) overlap_y = LATENT_SCALE_FACTOR * math.ceil(int((image_height / num_tiles_y) * overlap) / LATENT_SCALE_FACTOR)
# Calculate the tile size based on the number of tiles and overlap, and ensure it's divisible by 8 (rounding down) # Calculate the tile size based on the number of tiles and overlap, and ensure it's divisible by 8 (rounding down)
tile_size_x = 8 * math.floor(((image_width + overlap_x * (num_tiles_x - 1)) // num_tiles_x) / 8) tile_size_x = LATENT_SCALE_FACTOR * math.floor(
tile_size_y = 8 * math.floor(((image_height + overlap_y * (num_tiles_y - 1)) // num_tiles_y) / 8) ((image_width + overlap_x * (num_tiles_x - 1)) // num_tiles_x) / LATENT_SCALE_FACTOR
)
tile_size_y = LATENT_SCALE_FACTOR * math.floor(
((image_height + overlap_y * (num_tiles_y - 1)) // num_tiles_y) / LATENT_SCALE_FACTOR
)
# tiles[y * num_tiles_x + x] is the tile for the y'th row, x'th column. # tiles[y * num_tiles_x + x] is the tile for the y'th row, x'th column.
tiles: list[Tile] = [] tiles: list[Tile] = []
@ -196,13 +201,13 @@ def calc_tiles_min_overlap(
for tile_idx_y in range(num_tiles_y): for tile_idx_y in range(num_tiles_y):
top = (tile_idx_y * (image_height - tile_height)) // (num_tiles_y - 1) if num_tiles_y > 1 else 0 top = (tile_idx_y * (image_height - tile_height)) // (num_tiles_y - 1) if num_tiles_y > 1 else 0
if round_to_8: if round_to_8:
top = 8 * (top // 8) top = LATENT_SCALE_FACTOR * (top // LATENT_SCALE_FACTOR)
bottom = top + tile_height bottom = top + tile_height
for tile_idx_x in range(num_tiles_x): for tile_idx_x in range(num_tiles_x):
left = (tile_idx_x * (image_width - tile_width)) // (num_tiles_x - 1) if num_tiles_x > 1 else 0 left = (tile_idx_x * (image_width - tile_width)) // (num_tiles_x - 1) if num_tiles_x > 1 else 0
if round_to_8: if round_to_8:
left = 8 * (left // 8) left = LATENT_SCALE_FACTOR * (left // LATENT_SCALE_FACTOR)
right = left + tile_width right = left + tile_width
tile = Tile( tile = Tile(

12
invokeai/backend/tiles/utils.py
View File

@ -33,10 +33,10 @@ def paste(dst_image: np.ndarray, src_image: np.ndarray, box: TBLR, mask: Optiona
"""Paste a source image into a destination image. """Paste a source image into a destination image.
Args: Args:
dst_image (torch.Tensor): The destination image to paste into. Shape: (H, W, C). dst_image (np.array): The destination image to paste into. Shape: (H, W, C).
src_image (torch.Tensor): The source image to paste. Shape: (H, W, C). H and W must be compatible with 'box'. src_image (np.array): The source image to paste. Shape: (H, W, C). H and W must be compatible with 'box'.
box (TBLR): Box defining the region in the 'dst_image' where 'src_image' will be pasted. box (TBLR): Box defining the region in the 'dst_image' where 'src_image' will be pasted.
mask (Optional[torch.Tensor]): A mask that defines the blending between 'src_image' and 'dst_image'. mask (Optional[np.array]): A mask that defines the blending between 'src_image' and 'dst_image'.
Range: [0.0, 1.0], Shape: (H, W). The output is calculate per-pixel according to Range: [0.0, 1.0], Shape: (H, W). The output is calculate per-pixel according to
`src * mask + dst * (1 - mask)`. `src * mask + dst * (1 - mask)`.
""" """
@ -55,8 +55,8 @@ def seam_blend(ia1: np.ndarray, ia2: np.ndarray, blend_amount: int, x_seam: bool
It is assumed that input images will be RGB np arrays and are the same size. It is assumed that input images will be RGB np arrays and are the same size.
Args: Args:
ia1 (torch.Tensor): Image array 1 Shape: (H, W, C). ia1 (np.array): Image array 1 Shape: (H, W, C).
ia2 (torch.Tensor): Image array 2 Shape: (H, W, C). ia2 (np.array): Image array 2 Shape: (H, W, C).
x_seam (bool): If the images should be blended on the x axis or not. x_seam (bool): If the images should be blended on the x axis or not.
blend_amount (int): The size of the blur to use on the seam. Half of this value will be used to avoid the edges of the image. blend_amount (int): The size of the blur to use on the seam. Half of this value will be used to avoid the edges of the image.
""" """
@ -74,7 +74,7 @@ def seam_blend(ia1: np.ndarray, ia2: np.ndarray, blend_amount: int, x_seam: bool
return result return result
# Assume RGB and convert to grey # Assume RGB and convert to grey
iag1 = np.dot(ia1, [0.2989, 0.5870, 0.1140]) iag1 = np.dot(ia1, [0.2989, 0.5870, 0.1140]) # BT.601 perceived brightness
iag2 = np.dot(ia2, [0.2989, 0.5870, 0.1140]) iag2 = np.dot(ia2, [0.2989, 0.5870, 0.1140])
# Calc Difference between the images # Calc Difference between the images