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

Merge branch 'main' into refactor/rename-get-logger

Browse Source
This commit is contained in:
psychedelicious
2023-09-05 10:37:53 +10:00
committed by GitHub
parent 24132a7950 78cc5a7825
commit d8f7c19030
232 changed files with 8608 additions and 11111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
invokeai/backend/image_util/seamless.py
View File

@ -20,7 +20,8 @@ def _conv_forward_asymmetric(self, input, weight, bias):
def configure_model_padding(model, seamless, seamless_axes):
"""
Modifies the 2D convolution layers to use a circular padding mode based on the `seamless` and `seamless_axes` options.
Modifies the 2D convolution layers to use a circular padding mode based on
the `seamless` and `seamless_axes` options.
"""
# TODO: get an explicit interface for this in diffusers: https://github.com/huggingface/diffusers/issues/556
for m in model.modules():

8
invokeai/backend/install/migrate_to_3.py
View File

@ -492,10 +492,10 @@ def _parse_legacy_yamlfile(root: Path, initfile: Path) -> ModelPaths:
loras = paths.get("lora_dir", "loras")
controlnets = paths.get("controlnet_dir", "controlnets")
return ModelPaths(
models=root / models,
embeddings=root / embeddings,
loras=root / loras,
controlnets=root / controlnets,
models=root / models if models else None,
embeddings=root / embeddings if embeddings else None,
loras=root / loras if loras else None,
controlnets=root / controlnets if controlnets else None,
)

1
invokeai/backend/model_management/model_probe.py
View File

@ -50,6 +50,7 @@ class ModelProbe(object):
"StableDiffusionInpaintPipeline": ModelType.Main,
"StableDiffusionXLPipeline": ModelType.Main,
"StableDiffusionXLImg2ImgPipeline": ModelType.Main,
"StableDiffusionXLInpaintPipeline": ModelType.Main,
"AutoencoderKL": ModelType.Vae,
"ControlNetModel": ModelType.ControlNet,
}

102
invokeai/backend/model_management/seamless.py Normal file
View File

@ -0,0 +1,102 @@
from __future__ import annotations
from contextlib import contextmanager
from typing import List, Union
import torch.nn as nn
from diffusers.models import AutoencoderKL, UNet2DConditionModel
def _conv_forward_asymmetric(self, input, weight, bias):
"""
Patch for Conv2d._conv_forward that supports asymmetric padding
"""
working = nn.functional.pad(input, self.asymmetric_padding["x"], mode=self.asymmetric_padding_mode["x"])
working = nn.functional.pad(working, self.asymmetric_padding["y"], mode=self.asymmetric_padding_mode["y"])
return nn.functional.conv2d(
working,
weight,
bias,
self.stride,
nn.modules.utils._pair(0),
self.dilation,
self.groups,
)
@contextmanager
def set_seamless(model: Union[UNet2DConditionModel, AutoencoderKL], seamless_axes: List[str]):
try:
to_restore = []
for m_name, m in model.named_modules():
if isinstance(model, UNet2DConditionModel):
if ".attentions." in m_name:
continue
if ".resnets." in m_name:
if ".conv2" in m_name:
continue
if ".conv_shortcut" in m_name:
continue
"""
if isinstance(model, UNet2DConditionModel):
if False and ".upsamplers." in m_name:
continue
if False and ".downsamplers." in m_name:
continue
if True and ".resnets." in m_name:
if True and ".conv1" in m_name:
if False and "down_blocks" in m_name:
continue
if False and "mid_block" in m_name:
continue
if False and "up_blocks" in m_name:
continue
if True and ".conv2" in m_name:
continue
if True and ".conv_shortcut" in m_name:
continue
if True and ".attentions." in m_name:
continue
if False and m_name in ["conv_in", "conv_out"]:
continue
"""
if isinstance(m, (nn.Conv2d, nn.ConvTranspose2d)):
m.asymmetric_padding_mode = {}
m.asymmetric_padding = {}
m.asymmetric_padding_mode["x"] = "circular" if ("x" in seamless_axes) else "constant"
m.asymmetric_padding["x"] = (
m._reversed_padding_repeated_twice[0],
m._reversed_padding_repeated_twice[1],
0,
0,
)
m.asymmetric_padding_mode["y"] = "circular" if ("y" in seamless_axes) else "constant"
m.asymmetric_padding["y"] = (
0,
0,
m._reversed_padding_repeated_twice[2],
m._reversed_padding_repeated_twice[3],
)
to_restore.append((m, m._conv_forward))
m._conv_forward = _conv_forward_asymmetric.__get__(m, nn.Conv2d)
yield
finally:
for module, orig_conv_forward in to_restore:
module._conv_forward = orig_conv_forward
if hasattr(m, "asymmetric_padding_mode"):
del m.asymmetric_padding_mode
if hasattr(m, "asymmetric_padding"):
del m.asymmetric_padding

51
invokeai/backend/stable_diffusion/diffusers_pipeline.py
View File

@ -144,7 +144,7 @@ def image_resized_to_grid_as_tensor(image: PIL.Image.Image, normalize: bool = Tr
w, h = trim_to_multiple_of(*image.size, multiple_of=multiple_of)
transformation = T.Compose(
[
T.Resize((h, w), T.InterpolationMode.LANCZOS),
T.Resize((h, w), T.InterpolationMode.LANCZOS, antialias=True),
T.ToTensor(),
]
)
@ -358,6 +358,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
callback: Callable[[PipelineIntermediateState], None] = None,
control_data: List[ControlNetData] = None,
mask: Optional[torch.Tensor] = None,
masked_latents: Optional[torch.Tensor] = None,
seed: Optional[int] = None,
) -> tuple[torch.Tensor, Optional[AttentionMapSaver]]:
if init_timestep.shape[0] == 0:
@ -376,28 +377,28 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
latents = self.scheduler.add_noise(latents, noise, batched_t)
if mask is not None:
# if no noise provided, noisify unmasked area based on seed(or 0 as fallback)
if noise is None:
noise = torch.randn(
orig_latents.shape,
dtype=torch.float32,
device="cpu",
generator=torch.Generator(device="cpu").manual_seed(seed or 0),
).to(device=orig_latents.device, dtype=orig_latents.dtype)
latents = self.scheduler.add_noise(latents, noise, batched_t)
latents = torch.lerp(
orig_latents, latents.to(dtype=orig_latents.dtype), mask.to(dtype=orig_latents.dtype)
)
if is_inpainting_model(self.unet):
# You'd think the inpainting model wouldn't be paying attention to the area it is going to repaint
# (that's why there's a mask!) but it seems to really want that blanked out.
# masked_latents = latents * torch.where(mask < 0.5, 1, 0) TODO: inpaint/outpaint/infill
if masked_latents is None:
raise Exception("Source image required for inpaint mask when inpaint model used!")
# TODO: we should probably pass this in so we don't have to try/finally around setting it.
self.invokeai_diffuser.model_forward_callback = AddsMaskLatents(self._unet_forward, mask, orig_latents)
self.invokeai_diffuser.model_forward_callback = AddsMaskLatents(
self._unet_forward, mask, masked_latents
)
else:
# if no noise provided, noisify unmasked area based on seed(or 0 as fallback)
if noise is None:
noise = torch.randn(
orig_latents.shape,
dtype=torch.float32,
device="cpu",
generator=torch.Generator(device="cpu").manual_seed(seed or 0),
).to(device=orig_latents.device, dtype=orig_latents.dtype)
latents = self.scheduler.add_noise(latents, noise, batched_t)
latents = torch.lerp(
orig_latents, latents.to(dtype=orig_latents.dtype), mask.to(dtype=orig_latents.dtype)
)
additional_guidance.append(AddsMaskGuidance(mask, orig_latents, self.scheduler, noise))
try:
@ -557,12 +558,22 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
# compute the previous noisy sample x_t -> x_t-1
step_output = self.scheduler.step(noise_pred, timestep, latents, **conditioning_data.scheduler_args)
# TODO: issue to diffusers?
# undo internal counter increment done by scheduler.step, so timestep can be resolved as before call
# this needed to be able call scheduler.add_noise with current timestep
if self.scheduler.order == 2:
self.scheduler._index_counter[timestep.item()] -= 1
# TODO: this additional_guidance extension point feels redundant with InvokeAIDiffusionComponent.
# But the way things are now, scheduler runs _after_ that, so there was
# no way to use it to apply an operation that happens after the last scheduler.step.
for guidance in additional_guidance:
step_output = guidance(step_output, timestep, conditioning_data)
# restore internal counter
if self.scheduler.order == 2:
self.scheduler._index_counter[timestep.item()] += 1
return step_output
def _unet_forward(

6
invokeai/backend/stable_diffusion/image_degradation/__init__.py
View File

@ -1,6 +0,0 @@
from ldm.modules.image_degradation.bsrgan import ( # noqa: F401
degradation_bsrgan_variant as degradation_fn_bsr,
)
from ldm.modules.image_degradation.bsrgan_light import ( # noqa: F401
degradation_bsrgan_variant as degradation_fn_bsr_light,
)

794
invokeai/backend/stable_diffusion/image_degradation/bsrgan.py
View File

@ -1,794 +0,0 @@
# -*- coding: utf-8 -*-
"""
# --------------------------------------------
# Super-Resolution
# --------------------------------------------
#
# Kai Zhang (cskaizhang@gmail.com)
# https://github.com/cszn
# From 2019/03--2021/08
# --------------------------------------------
"""
import random
from functools import partial
import albumentations
import cv2
import ldm.modules.image_degradation.utils_image as util
import numpy as np
import scipy
import scipy.stats as ss
import torch
from scipy import ndimage
from scipy.interpolate import interp2d
from scipy.linalg import orth
def modcrop_np(img, sf):
"""
Args:
img: numpy image, WxH or WxHxC
sf: scale factor
Return:
cropped image
"""
w, h = img.shape[:2]
im = np.copy(img)
return im[: w - w % sf, : h - h % sf, ...]
"""
# --------------------------------------------
# anisotropic Gaussian kernels
# --------------------------------------------
"""
def analytic_kernel(k):
"""Calculate the X4 kernel from the X2 kernel (for proof see appendix in paper)"""
k_size = k.shape[0]
# Calculate the big kernels size
big_k = np.zeros((3 * k_size - 2, 3 * k_size - 2))
# Loop over the small kernel to fill the big one
for r in range(k_size):
for c in range(k_size):
big_k[2 * r : 2 * r + k_size, 2 * c : 2 * c + k_size] += k[r, c] * k
# Crop the edges of the big kernel to ignore very small values and increase run time of SR
crop = k_size // 2
cropped_big_k = big_k[crop:-crop, crop:-crop]
# Normalize to 1
return cropped_big_k / cropped_big_k.sum()
def anisotropic_Gaussian(ksize=15, theta=np.pi, l1=6, l2=6):
"""generate an anisotropic Gaussian kernel
Args:
ksize : e.g., 15, kernel size
theta : [0, pi], rotation angle range
l1 : [0.1,50], scaling of eigenvalues
l2 : [0.1,l1], scaling of eigenvalues
If l1 = l2, will get an isotropic Gaussian kernel.
Returns:
k : kernel
"""
v = np.dot(
np.array([[np.cos(theta), -np.sin(theta)], [np.sin(theta), np.cos(theta)]]),
np.array([1.0, 0.0]),
)
V = np.array([[v[0], v[1]], [v[1], -v[0]]])
D = np.array([[l1, 0], [0, l2]])
Sigma = np.dot(np.dot(V, D), np.linalg.inv(V))
k = gm_blur_kernel(mean=[0, 0], cov=Sigma, size=ksize)
return k
def gm_blur_kernel(mean, cov, size=15):
center = size / 2.0 + 0.5
k = np.zeros([size, size])
for y in range(size):
for x in range(size):
cy = y - center + 1
cx = x - center + 1
k[y, x] = ss.multivariate_normal.pdf([cx, cy], mean=mean, cov=cov)
k = k / np.sum(k)
return k
def shift_pixel(x, sf, upper_left=True):
"""shift pixel for super-resolution with different scale factors
Args:
x: WxHxC or WxH
sf: scale factor
upper_left: shift direction
"""
h, w = x.shape[:2]
shift = (sf - 1) * 0.5
xv, yv = np.arange(0, w, 1.0), np.arange(0, h, 1.0)
if upper_left:
x1 = xv + shift
y1 = yv + shift
else:
x1 = xv - shift
y1 = yv - shift
x1 = np.clip(x1, 0, w - 1)
y1 = np.clip(y1, 0, h - 1)
if x.ndim == 2:
x = interp2d(xv, yv, x)(x1, y1)
if x.ndim == 3:
for i in range(x.shape[-1]):
x[:, :, i] = interp2d(xv, yv, x[:, :, i])(x1, y1)
return x
def blur(x, k):
"""
x: image, NxcxHxW
k: kernel, Nx1xhxw
"""
n, c = x.shape[:2]
p1, p2 = (k.shape[-2] - 1) // 2, (k.shape[-1] - 1) // 2
x = torch.nn.functional.pad(x, pad=(p1, p2, p1, p2), mode="replicate")
k = k.repeat(1, c, 1, 1)
k = k.view(-1, 1, k.shape[2], k.shape[3])
x = x.view(1, -1, x.shape[2], x.shape[3])
x = torch.nn.functional.conv2d(x, k, bias=None, stride=1, padding=0, groups=n * c)
x = x.view(n, c, x.shape[2], x.shape[3])
return x
def gen_kernel(
k_size=np.array([15, 15]),
scale_factor=np.array([4, 4]),
min_var=0.6,
max_var=10.0,
noise_level=0,
):
""" "
# modified version of https://github.com/assafshocher/BlindSR_dataset_generator
# Kai Zhang
# min_var = 0.175 * sf # variance of the gaussian kernel will be sampled between min_var and max_var
# max_var = 2.5 * sf
"""
# Set random eigen-vals (lambdas) and angle (theta) for COV matrix
lambda_1 = min_var + np.random.rand() * (max_var - min_var)
lambda_2 = min_var + np.random.rand() * (max_var - min_var)
theta = np.random.rand() * np.pi # random theta
noise = -noise_level + np.random.rand(*k_size) * noise_level * 2
# Set COV matrix using Lambdas and Theta
LAMBDA = np.diag([lambda_1, lambda_2])
Q = np.array([[np.cos(theta), -np.sin(theta)], [np.sin(theta), np.cos(theta)]])
SIGMA = Q @ LAMBDA @ Q.T
INV_SIGMA = np.linalg.inv(SIGMA)[None, None, :, :]
# Set expectation position (shifting kernel for aligned image)
MU = k_size // 2 - 0.5 * (scale_factor - 1) # - 0.5 * (scale_factor - k_size % 2)
MU = MU[None, None, :, None]
# Create meshgrid for Gaussian
[X, Y] = np.meshgrid(range(k_size[0]), range(k_size[1]))
Z = np.stack([X, Y], 2)[:, :, :, None]
# Calcualte Gaussian for every pixel of the kernel
ZZ = Z - MU
ZZ_t = ZZ.transpose(0, 1, 3, 2)
raw_kernel = np.exp(-0.5 * np.squeeze(ZZ_t @ INV_SIGMA @ ZZ)) * (1 + noise)
# shift the kernel so it will be centered
# raw_kernel_centered = kernel_shift(raw_kernel, scale_factor)
# Normalize the kernel and return
# kernel = raw_kernel_centered / np.sum(raw_kernel_centered)
kernel = raw_kernel / np.sum(raw_kernel)
return kernel
def fspecial_gaussian(hsize, sigma):
hsize = [hsize, hsize]
siz = [(hsize[0] - 1.0) / 2.0, (hsize[1] - 1.0) / 2.0]
std = sigma
[x, y] = np.meshgrid(np.arange(-siz[1], siz[1] + 1), np.arange(-siz[0], siz[0] + 1))
arg = -(x * x + y * y) / (2 * std * std)
h = np.exp(arg)
h[h < scipy.finfo(float).eps * h.max()] = 0
sumh = h.sum()
if sumh != 0:
h = h / sumh
return h
def fspecial_laplacian(alpha):
alpha = max([0, min([alpha, 1])])
h1 = alpha / (alpha + 1)
h2 = (1 - alpha) / (alpha + 1)
h = [[h1, h2, h1], [h2, -4 / (alpha + 1), h2], [h1, h2, h1]]
h = np.array(h)
return h
def fspecial(filter_type, *args, **kwargs):
"""
python code from:
https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filter/matlab_fspecial.py
"""
if filter_type == "gaussian":
return fspecial_gaussian(*args, **kwargs)
if filter_type == "laplacian":
return fspecial_laplacian(*args, **kwargs)
"""
# --------------------------------------------
# degradation models
# --------------------------------------------
"""
def bicubic_degradation(x, sf=3):
"""
Args:
x: HxWxC image, [0, 1]
sf: down-scale factor
Return:
bicubicly downsampled LR image
"""
x = util.imresize_np(x, scale=1 / sf)
return x
def srmd_degradation(x, k, sf=3):
"""blur + bicubic downsampling
Args:
x: HxWxC image, [0, 1]
k: hxw, double
sf: down-scale factor
Return:
downsampled LR image
Reference:
@inproceedings{zhang2018learning,
title={Learning a single convolutional super-resolution network for multiple degradations},
author={Zhang, Kai and Zuo, Wangmeng and Zhang, Lei},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
pages={3262--3271},
year={2018}
}
"""
x = ndimage.filters.convolve(x, np.expand_dims(k, axis=2), mode="wrap") # 'nearest' | 'mirror'
x = bicubic_degradation(x, sf=sf)
return x
def dpsr_degradation(x, k, sf=3):
"""bicubic downsampling + blur
Args:
x: HxWxC image, [0, 1]
k: hxw, double
sf: down-scale factor
Return:
downsampled LR image
Reference:
@inproceedings{zhang2019deep,
title={Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels},
author={Zhang, Kai and Zuo, Wangmeng and Zhang, Lei},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
pages={1671--1681},
year={2019}
}
"""
x = bicubic_degradation(x, sf=sf)
x = ndimage.filters.convolve(x, np.expand_dims(k, axis=2), mode="wrap")
return x
def classical_degradation(x, k, sf=3):
"""blur + downsampling
Args:
x: HxWxC image, [0, 1]/[0, 255]
k: hxw, double
sf: down-scale factor
Return:
downsampled LR image
"""
x = ndimage.filters.convolve(x, np.expand_dims(k, axis=2), mode="wrap")
# x = filters.correlate(x, np.expand_dims(np.flip(k), axis=2))
st = 0
return x[st::sf, st::sf, ...]
def add_sharpening(img, weight=0.5, radius=50, threshold=10):
"""USM sharpening. borrowed from real-ESRGAN
Input image: I; Blurry image: B.
1. K = I + weight * (I - B)
2. Mask = 1 if abs(I - B) > threshold, else: 0
3. Blur mask:
4. Out = Mask * K + (1 - Mask) * I
Args:
img (Numpy array): Input image, HWC, BGR; float32, [0, 1].
weight (float): Sharp weight. Default: 1.
radius (float): Kernel size of Gaussian blur. Default: 50.
threshold (int):
"""
if radius % 2 == 0:
radius += 1
blur = cv2.GaussianBlur(img, (radius, radius), 0)
residual = img - blur
mask = np.abs(residual) * 255 > threshold
mask = mask.astype("float32")
soft_mask = cv2.GaussianBlur(mask, (radius, radius), 0)
K = img + weight * residual
K = np.clip(K, 0, 1)
return soft_mask * K + (1 - soft_mask) * img
def add_blur(img, sf=4):
wd2 = 4.0 + sf
wd = 2.0 + 0.2 * sf
if random.random() < 0.5:
l1 = wd2 * random.random()
l2 = wd2 * random.random()
k = anisotropic_Gaussian(
ksize=2 * random.randint(2, 11) + 3,
theta=random.random() * np.pi,
l1=l1,
l2=l2,
)
else:
k = fspecial("gaussian", 2 * random.randint(2, 11) + 3, wd * random.random())
img = ndimage.filters.convolve(img, np.expand_dims(k, axis=2), mode="mirror")
return img
def add_resize(img, sf=4):
rnum = np.random.rand()
if rnum > 0.8: # up
sf1 = random.uniform(1, 2)
elif rnum < 0.7: # down
sf1 = random.uniform(0.5 / sf, 1)
else:
sf1 = 1.0
img = cv2.resize(
img,
(int(sf1 * img.shape[1]), int(sf1 * img.shape[0])),
interpolation=random.choice([1, 2, 3]),
)
img = np.clip(img, 0.0, 1.0)
return img
# def add_Gaussian_noise(img, noise_level1=2, noise_level2=25):
# noise_level = random.randint(noise_level1, noise_level2)
# rnum = np.random.rand()
# if rnum > 0.6: # add color Gaussian noise
# img += np.random.normal(0, noise_level / 255.0, img.shape).astype(np.float32)
# elif rnum < 0.4: # add grayscale Gaussian noise
# img += np.random.normal(0, noise_level / 255.0, (*img.shape[:2], 1)).astype(np.float32)
# else: # add noise
# L = noise_level2 / 255.
# D = np.diag(np.random.rand(3))
# U = orth(np.random.rand(3, 3))
# conv = np.dot(np.dot(np.transpose(U), D), U)
# img += np.random.multivariate_normal([0, 0, 0], np.abs(L ** 2 * conv), img.shape[:2]).astype(np.float32)
# img = np.clip(img, 0.0, 1.0)
# return img
def add_Gaussian_noise(img, noise_level1=2, noise_level2=25):
noise_level = random.randint(noise_level1, noise_level2)
rnum = np.random.rand()
if rnum > 0.6: # add color Gaussian noise
img = img + np.random.normal(0, noise_level / 255.0, img.shape).astype(np.float32)
elif rnum < 0.4: # add grayscale Gaussian noise
img = img + np.random.normal(0, noise_level / 255.0, (*img.shape[:2], 1)).astype(np.float32)
else: # add noise
L = noise_level2 / 255.0
D = np.diag(np.random.rand(3))
U = orth(np.random.rand(3, 3))
conv = np.dot(np.dot(np.transpose(U), D), U)
img = img + np.random.multivariate_normal([0, 0, 0], np.abs(L**2 * conv), img.shape[:2]).astype(np.float32)
img = np.clip(img, 0.0, 1.0)
return img
def add_speckle_noise(img, noise_level1=2, noise_level2=25):
noise_level = random.randint(noise_level1, noise_level2)
img = np.clip(img, 0.0, 1.0)
rnum = random.random()
if rnum > 0.6:
img += img * np.random.normal(0, noise_level / 255.0, img.shape).astype(np.float32)
elif rnum < 0.4:
img += img * np.random.normal(0, noise_level / 255.0, (*img.shape[:2], 1)).astype(np.float32)
else:
L = noise_level2 / 255.0
D = np.diag(np.random.rand(3))
U = orth(np.random.rand(3, 3))
conv = np.dot(np.dot(np.transpose(U), D), U)
img += img * np.random.multivariate_normal([0, 0, 0], np.abs(L**2 * conv), img.shape[:2]).astype(np.float32)
img = np.clip(img, 0.0, 1.0)
return img
def add_Poisson_noise(img):
img = np.clip((img * 255.0).round(), 0, 255) / 255.0
vals = 10 ** (2 * random.random() + 2.0) # [2, 4]
if random.random() < 0.5:
img = np.random.poisson(img * vals).astype(np.float32) / vals
else:
img_gray = np.dot(img[..., :3], [0.299, 0.587, 0.114])
img_gray = np.clip((img_gray * 255.0).round(), 0, 255) / 255.0
noise_gray = np.random.poisson(img_gray * vals).astype(np.float32) / vals - img_gray
img += noise_gray[:, :, np.newaxis]
img = np.clip(img, 0.0, 1.0)
return img
def add_JPEG_noise(img):
quality_factor = random.randint(30, 95)
img = cv2.cvtColor(util.single2uint(img), cv2.COLOR_RGB2BGR)
result, encimg = cv2.imencode(".jpg", img, [int(cv2.IMWRITE_JPEG_QUALITY), quality_factor])
img = cv2.imdecode(encimg, 1)
img = cv2.cvtColor(util.uint2single(img), cv2.COLOR_BGR2RGB)
return img
def random_crop(lq, hq, sf=4, lq_patchsize=64):
h, w = lq.shape[:2]
rnd_h = random.randint(0, h - lq_patchsize)
rnd_w = random.randint(0, w - lq_patchsize)
lq = lq[rnd_h : rnd_h + lq_patchsize, rnd_w : rnd_w + lq_patchsize, :]
rnd_h_H, rnd_w_H = int(rnd_h * sf), int(rnd_w * sf)
hq = hq[
rnd_h_H : rnd_h_H + lq_patchsize * sf,
rnd_w_H : rnd_w_H + lq_patchsize * sf,
:,
]
return lq, hq
def degradation_bsrgan(img, sf=4, lq_patchsize=72, isp_model=None):
"""
This is the degradation model of BSRGAN from the paper
"Designing a Practical Degradation Model for Deep Blind Image Super-Resolution"
----------
img: HXWXC, [0, 1], its size should be large than (lq_patchsizexsf)x(lq_patchsizexsf)
sf: scale factor
isp_model: camera ISP model
Returns
-------
img: low-quality patch, size: lq_patchsizeXlq_patchsizeXC, range: [0, 1]
hq: corresponding high-quality patch, size: (lq_patchsizexsf)X(lq_patchsizexsf)XC, range: [0, 1]
"""
isp_prob, jpeg_prob, scale2_prob = 0.25, 0.9, 0.25
sf_ori = sf
h1, w1 = img.shape[:2]
img = img.copy()[: w1 - w1 % sf, : h1 - h1 % sf, ...] # mod crop
h, w = img.shape[:2]
if h < lq_patchsize * sf or w < lq_patchsize * sf:
raise ValueError(f"img size ({h1}X{w1}) is too small!")
hq = img.copy()
if sf == 4 and random.random() < scale2_prob: # downsample1
if np.random.rand() < 0.5:
img = cv2.resize(
img,
(int(1 / 2 * img.shape[1]), int(1 / 2 * img.shape[0])),
interpolation=random.choice([1, 2, 3]),
)
else:
img = util.imresize_np(img, 1 / 2, True)
img = np.clip(img, 0.0, 1.0)
sf = 2
shuffle_order = random.sample(range(7), 7)
idx1, idx2 = shuffle_order.index(2), shuffle_order.index(3)
if idx1 > idx2: # keep downsample3 last
shuffle_order[idx1], shuffle_order[idx2] = (
shuffle_order[idx2],
shuffle_order[idx1],
)
for i in shuffle_order:
if i == 0:
img = add_blur(img, sf=sf)
elif i == 1:
img = add_blur(img, sf=sf)
elif i == 2:
a, b = img.shape[1], img.shape[0]
# downsample2
if random.random() < 0.75:
sf1 = random.uniform(1, 2 * sf)
img = cv2.resize(
img,
(int(1 / sf1 * img.shape[1]), int(1 / sf1 * img.shape[0])),
interpolation=random.choice([1, 2, 3]),
)
else:
k = fspecial("gaussian", 25, random.uniform(0.1, 0.6 * sf))
k_shifted = shift_pixel(k, sf)
k_shifted = k_shifted / k_shifted.sum() # blur with shifted kernel
img = ndimage.filters.convolve(img, np.expand_dims(k_shifted, axis=2), mode="mirror")
img = img[0::sf, 0::sf, ...] # nearest downsampling
img = np.clip(img, 0.0, 1.0)
elif i == 3:
# downsample3
img = cv2.resize(
img,
(int(1 / sf * a), int(1 / sf * b)),
interpolation=random.choice([1, 2, 3]),
)
img = np.clip(img, 0.0, 1.0)
elif i == 4:
# add Gaussian noise
img = add_Gaussian_noise(img, noise_level1=2, noise_level2=25)
elif i == 5:
# add JPEG noise
if random.random() < jpeg_prob:
img = add_JPEG_noise(img)
elif i == 6:
# add processed camera sensor noise
if random.random() < isp_prob and isp_model is not None:
with torch.no_grad():
img, hq = isp_model.forward(img.copy(), hq)
# add final JPEG compression noise
img = add_JPEG_noise(img)
# random crop
img, hq = random_crop(img, hq, sf_ori, lq_patchsize)
return img, hq
# todo no isp_model?
def degradation_bsrgan_variant(image, sf=4, isp_model=None):
"""
This is the degradation model of BSRGAN from the paper
"Designing a Practical Degradation Model for Deep Blind Image Super-Resolution"
----------
sf: scale factor
isp_model: camera ISP model
Returns
-------
img: low-quality patch, size: lq_patchsizeXlq_patchsizeXC, range: [0, 1]
hq: corresponding high-quality patch, size: (lq_patchsizexsf)X(lq_patchsizexsf)XC, range: [0, 1]
"""
image = util.uint2single(image)
jpeg_prob, scale2_prob = 0.9, 0.25
# isp_prob = 0.25 # uncomment with `if i== 6` block below
# sf_ori = sf # uncomment with `if i== 6` block below
h1, w1 = image.shape[:2]
image = image.copy()[: w1 - w1 % sf, : h1 - h1 % sf, ...] # mod crop
h, w = image.shape[:2]
# hq = image.copy() # uncomment with `if i== 6` block below
if sf == 4 and random.random() < scale2_prob: # downsample1
if np.random.rand() < 0.5:
image = cv2.resize(
image,
(int(1 / 2 * image.shape[1]), int(1 / 2 * image.shape[0])),
interpolation=random.choice([1, 2, 3]),
)
else:
image = util.imresize_np(image, 1 / 2, True)
image = np.clip(image, 0.0, 1.0)
sf = 2
shuffle_order = random.sample(range(7), 7)
idx1, idx2 = shuffle_order.index(2), shuffle_order.index(3)
if idx1 > idx2: # keep downsample3 last
shuffle_order[idx1], shuffle_order[idx2] = (
shuffle_order[idx2],
shuffle_order[idx1],
)
for i in shuffle_order:
if i == 0:
image = add_blur(image, sf=sf)
elif i == 1:
image = add_blur(image, sf=sf)
elif i == 2:
a, b = image.shape[1], image.shape[0]
# downsample2
if random.random() < 0.75:
sf1 = random.uniform(1, 2 * sf)
image = cv2.resize(
image,
(
int(1 / sf1 * image.shape[1]),
int(1 / sf1 * image.shape[0]),
),
interpolation=random.choice([1, 2, 3]),
)
else:
k = fspecial("gaussian", 25, random.uniform(0.1, 0.6 * sf))
k_shifted = shift_pixel(k, sf)
k_shifted = k_shifted / k_shifted.sum() # blur with shifted kernel
image = ndimage.filters.convolve(image, np.expand_dims(k_shifted, axis=2), mode="mirror")
image = image[0::sf, 0::sf, ...] # nearest downsampling
image = np.clip(image, 0.0, 1.0)
elif i == 3:
# downsample3
image = cv2.resize(
image,
(int(1 / sf * a), int(1 / sf * b)),
interpolation=random.choice([1, 2, 3]),
)
image = np.clip(image, 0.0, 1.0)
elif i == 4:
# add Gaussian noise
image = add_Gaussian_noise(image, noise_level1=2, noise_level2=25)
elif i == 5:
# add JPEG noise
if random.random() < jpeg_prob:
image = add_JPEG_noise(image)
# elif i == 6:
# # add processed camera sensor noise
# if random.random() < isp_prob and isp_model is not None:
# with torch.no_grad():
# img, hq = isp_model.forward(img.copy(), hq)
# add final JPEG compression noise
image = add_JPEG_noise(image)
image = util.single2uint(image)
example = {"image": image}
return example
# TODO incase there is a pickle error one needs to replace a += x with a = a + x in add_speckle_noise etc...
def degradation_bsrgan_plus(
img,
sf=4,
shuffle_prob=0.5,
use_sharp=True,
lq_patchsize=64,
isp_model=None,
):
"""
This is an extended degradation model by combining
the degradation models of BSRGAN and Real-ESRGAN
----------
img: HXWXC, [0, 1], its size should be large than (lq_patchsizexsf)x(lq_patchsizexsf)
sf: scale factor
use_shuffle: the degradation shuffle
use_sharp: sharpening the img
Returns
-------
img: low-quality patch, size: lq_patchsizeXlq_patchsizeXC, range: [0, 1]
hq: corresponding high-quality patch, size: (lq_patchsizexsf)X(lq_patchsizexsf)XC, range: [0, 1]
"""
h1, w1 = img.shape[:2]
img = img.copy()[: w1 - w1 % sf, : h1 - h1 % sf, ...] # mod crop
h, w = img.shape[:2]
if h < lq_patchsize * sf or w < lq_patchsize * sf:
raise ValueError(f"img size ({h1}X{w1}) is too small!")
if use_sharp:
img = add_sharpening(img)
hq = img.copy()
if random.random() < shuffle_prob:
shuffle_order = random.sample(range(13), 13)
else:
shuffle_order = list(range(13))
# local shuffle for noise, JPEG is always the last one
shuffle_order[2:6] = random.sample(shuffle_order[2:6], len(range(2, 6)))
shuffle_order[9:13] = random.sample(shuffle_order[9:13], len(range(9, 13)))
poisson_prob, speckle_prob, isp_prob = 0.1, 0.1, 0.1
for i in shuffle_order:
if i == 0:
img = add_blur(img, sf=sf)
elif i == 1:
img = add_resize(img, sf=sf)
elif i == 2:
img = add_Gaussian_noise(img, noise_level1=2, noise_level2=25)
elif i == 3:
if random.random() < poisson_prob:
img = add_Poisson_noise(img)
elif i == 4:
if random.random() < speckle_prob:
img = add_speckle_noise(img)
elif i == 5:
if random.random() < isp_prob and isp_model is not None:
with torch.no_grad():
img, hq = isp_model.forward(img.copy(), hq)
elif i == 6:
img = add_JPEG_noise(img)
elif i == 7:
img = add_blur(img, sf=sf)
elif i == 8:
img = add_resize(img, sf=sf)
elif i == 9:
img = add_Gaussian_noise(img, noise_level1=2, noise_level2=25)
elif i == 10:
if random.random() < poisson_prob:
img = add_Poisson_noise(img)
elif i == 11:
if random.random() < speckle_prob:
img = add_speckle_noise(img)
elif i == 12:
if random.random() < isp_prob and isp_model is not None:
with torch.no_grad():
img, hq = isp_model.forward(img.copy(), hq)
else:
print("check the shuffle!")
# resize to desired size
img = cv2.resize(
img,
(int(1 / sf * hq.shape[1]), int(1 / sf * hq.shape[0])),
interpolation=random.choice([1, 2, 3]),
)
# add final JPEG compression noise
img = add_JPEG_noise(img)
# random crop
img, hq = random_crop(img, hq, sf, lq_patchsize)
return img, hq
if __name__ == "__main__":
print("hey")
img = util.imread_uint("utils/test.png", 3)
print(img)
img = util.uint2single(img)
print(img)
img = img[:448, :448]
h = img.shape[0] // 4
print("resizing to", h)
sf = 4
deg_fn = partial(degradation_bsrgan_variant, sf=sf)
for i in range(20):
print(i)
img_lq = deg_fn(img)
print(img_lq)
img_lq_bicubic = albumentations.SmallestMaxSize(max_size=h, interpolation=cv2.INTER_CUBIC)(image=img)["image"]
print(img_lq.shape)
print("bicubic", img_lq_bicubic.shape)
# print(img_hq.shape)
lq_nearest = cv2.resize(
util.single2uint(img_lq),
(int(sf * img_lq.shape[1]), int(sf * img_lq.shape[0])),
interpolation=0,
)
lq_bicubic_nearest = cv2.resize(
util.single2uint(img_lq_bicubic),
(int(sf * img_lq.shape[1]), int(sf * img_lq.shape[0])),
interpolation=0,
)
# img_concat = np.concatenate([lq_bicubic_nearest, lq_nearest, util.single2uint(img_hq)], axis=1)
img_concat = np.concatenate([lq_bicubic_nearest, lq_nearest], axis=1)
util.imsave(img_concat, str(i) + ".png")

704
invokeai/backend/stable_diffusion/image_degradation/bsrgan_light.py
View File

@ -1,704 +0,0 @@
# -*- coding: utf-8 -*-
import random
from functools import partial
import albumentations
import cv2
import ldm.modules.image_degradation.utils_image as util
import numpy as np
import scipy
import scipy.stats as ss
import torch
from scipy import ndimage
from scipy.interpolate import interp2d
from scipy.linalg import orth
"""
# --------------------------------------------
# Super-Resolution
# --------------------------------------------
#
# Kai Zhang (cskaizhang@gmail.com)
# https://github.com/cszn
# From 2019/03--2021/08
# --------------------------------------------
"""
def modcrop_np(img, sf):
"""
Args:
img: numpy image, WxH or WxHxC
sf: scale factor
Return:
cropped image
"""
w, h = img.shape[:2]
im = np.copy(img)
return im[: w - w % sf, : h - h % sf, ...]
"""
# --------------------------------------------
# anisotropic Gaussian kernels
# --------------------------------------------
"""
def analytic_kernel(k):
"""Calculate the X4 kernel from the X2 kernel (for proof see appendix in paper)"""
k_size = k.shape[0]
# Calculate the big kernels size
big_k = np.zeros((3 * k_size - 2, 3 * k_size - 2))
# Loop over the small kernel to fill the big one
for r in range(k_size):
for c in range(k_size):
big_k[2 * r : 2 * r + k_size, 2 * c : 2 * c + k_size] += k[r, c] * k
# Crop the edges of the big kernel to ignore very small values and increase run time of SR
crop = k_size // 2
cropped_big_k = big_k[crop:-crop, crop:-crop]
# Normalize to 1
return cropped_big_k / cropped_big_k.sum()
def anisotropic_Gaussian(ksize=15, theta=np.pi, l1=6, l2=6):
"""generate an anisotropic Gaussian kernel
Args:
ksize : e.g., 15, kernel size
theta : [0, pi], rotation angle range
l1 : [0.1,50], scaling of eigenvalues
l2 : [0.1,l1], scaling of eigenvalues
If l1 = l2, will get an isotropic Gaussian kernel.
Returns:
k : kernel
"""
v = np.dot(
np.array([[np.cos(theta), -np.sin(theta)], [np.sin(theta), np.cos(theta)]]),
np.array([1.0, 0.0]),
)
V = np.array([[v[0], v[1]], [v[1], -v[0]]])
D = np.array([[l1, 0], [0, l2]])
Sigma = np.dot(np.dot(V, D), np.linalg.inv(V))
k = gm_blur_kernel(mean=[0, 0], cov=Sigma, size=ksize)
return k
def gm_blur_kernel(mean, cov, size=15):
center = size / 2.0 + 0.5
k = np.zeros([size, size])
for y in range(size):
for x in range(size):
cy = y - center + 1
cx = x - center + 1
k[y, x] = ss.multivariate_normal.pdf([cx, cy], mean=mean, cov=cov)
k = k / np.sum(k)
return k
def shift_pixel(x, sf, upper_left=True):
"""shift pixel for super-resolution with different scale factors
Args:
x: WxHxC or WxH
sf: scale factor
upper_left: shift direction
"""
h, w = x.shape[:2]
shift = (sf - 1) * 0.5
xv, yv = np.arange(0, w, 1.0), np.arange(0, h, 1.0)
if upper_left:
x1 = xv + shift
y1 = yv + shift
else:
x1 = xv - shift
y1 = yv - shift
x1 = np.clip(x1, 0, w - 1)
y1 = np.clip(y1, 0, h - 1)
if x.ndim == 2:
x = interp2d(xv, yv, x)(x1, y1)
if x.ndim == 3:
for i in range(x.shape[-1]):
x[:, :, i] = interp2d(xv, yv, x[:, :, i])(x1, y1)
return x
def blur(x, k):
"""
x: image, NxcxHxW
k: kernel, Nx1xhxw
"""
n, c = x.shape[:2]
p1, p2 = (k.shape[-2] - 1) // 2, (k.shape[-1] - 1) // 2
x = torch.nn.functional.pad(x, pad=(p1, p2, p1, p2), mode="replicate")
k = k.repeat(1, c, 1, 1)
k = k.view(-1, 1, k.shape[2], k.shape[3])
x = x.view(1, -1, x.shape[2], x.shape[3])
x = torch.nn.functional.conv2d(x, k, bias=None, stride=1, padding=0, groups=n * c)
x = x.view(n, c, x.shape[2], x.shape[3])
return x
def gen_kernel(
k_size=np.array([15, 15]),
scale_factor=np.array([4, 4]),
min_var=0.6,
max_var=10.0,
noise_level=0,
):
""" "
# modified version of https://github.com/assafshocher/BlindSR_dataset_generator
# Kai Zhang
# min_var = 0.175 * sf # variance of the gaussian kernel will be sampled between min_var and max_var
# max_var = 2.5 * sf
"""
# Set random eigen-vals (lambdas) and angle (theta) for COV matrix
lambda_1 = min_var + np.random.rand() * (max_var - min_var)
lambda_2 = min_var + np.random.rand() * (max_var - min_var)
theta = np.random.rand() * np.pi # random theta
noise = -noise_level + np.random.rand(*k_size) * noise_level * 2
# Set COV matrix using Lambdas and Theta
LAMBDA = np.diag([lambda_1, lambda_2])
Q = np.array([[np.cos(theta), -np.sin(theta)], [np.sin(theta), np.cos(theta)]])
SIGMA = Q @ LAMBDA @ Q.T
INV_SIGMA = np.linalg.inv(SIGMA)[None, None, :, :]
# Set expectation position (shifting kernel for aligned image)
MU = k_size // 2 - 0.5 * (scale_factor - 1) # - 0.5 * (scale_factor - k_size % 2)
MU = MU[None, None, :, None]
# Create meshgrid for Gaussian
[X, Y] = np.meshgrid(range(k_size[0]), range(k_size[1]))
Z = np.stack([X, Y], 2)[:, :, :, None]
# Calcualte Gaussian for every pixel of the kernel
ZZ = Z - MU
ZZ_t = ZZ.transpose(0, 1, 3, 2)
raw_kernel = np.exp(-0.5 * np.squeeze(ZZ_t @ INV_SIGMA @ ZZ)) * (1 + noise)
# shift the kernel so it will be centered
# raw_kernel_centered = kernel_shift(raw_kernel, scale_factor)
# Normalize the kernel and return
# kernel = raw_kernel_centered / np.sum(raw_kernel_centered)
kernel = raw_kernel / np.sum(raw_kernel)
return kernel
def fspecial_gaussian(hsize, sigma):
hsize = [hsize, hsize]
siz = [(hsize[0] - 1.0) / 2.0, (hsize[1] - 1.0) / 2.0]
std = sigma
[x, y] = np.meshgrid(np.arange(-siz[1], siz[1] + 1), np.arange(-siz[0], siz[0] + 1))
arg = -(x * x + y * y) / (2 * std * std)
h = np.exp(arg)
h[h < scipy.finfo(float).eps * h.max()] = 0
sumh = h.sum()
if sumh != 0:
h = h / sumh
return h
def fspecial_laplacian(alpha):
alpha = max([0, min([alpha, 1])])
h1 = alpha / (alpha + 1)
h2 = (1 - alpha) / (alpha + 1)
h = [[h1, h2, h1], [h2, -4 / (alpha + 1), h2], [h1, h2, h1]]
h = np.array(h)
return h
def fspecial(filter_type, *args, **kwargs):
"""
python code from:
https://github.com/ronaldosena/imagens-medicas-2/blob/40171a6c259edec7827a6693a93955de2bd39e76/Aulas/aula_2_-_uniform_filter/matlab_fspecial.py
"""
if filter_type == "gaussian":
return fspecial_gaussian(*args, **kwargs)
if filter_type == "laplacian":
return fspecial_laplacian(*args, **kwargs)
"""
# --------------------------------------------
# degradation models
# --------------------------------------------
"""
def bicubic_degradation(x, sf=3):
"""
Args:
x: HxWxC image, [0, 1]
sf: down-scale factor
Return:
bicubicly downsampled LR image
"""
x = util.imresize_np(x, scale=1 / sf)
return x
def srmd_degradation(x, k, sf=3):
"""blur + bicubic downsampling
Args:
x: HxWxC image, [0, 1]
k: hxw, double
sf: down-scale factor
Return:
downsampled LR image
Reference:
@inproceedings{zhang2018learning,
title={Learning a single convolutional super-resolution network for multiple degradations},
author={Zhang, Kai and Zuo, Wangmeng and Zhang, Lei},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
pages={3262--3271},
year={2018}
}
"""
x = ndimage.filters.convolve(x, np.expand_dims(k, axis=2), mode="wrap") # 'nearest' | 'mirror'
x = bicubic_degradation(x, sf=sf)
return x
def dpsr_degradation(x, k, sf=3):
"""bicubic downsampling + blur
Args:
x: HxWxC image, [0, 1]
k: hxw, double
sf: down-scale factor
Return:
downsampled LR image
Reference:
@inproceedings{zhang2019deep,
title={Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels},
author={Zhang, Kai and Zuo, Wangmeng and Zhang, Lei},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
pages={1671--1681},
year={2019}
}
"""
x = bicubic_degradation(x, sf=sf)
x = ndimage.filters.convolve(x, np.expand_dims(k, axis=2), mode="wrap")
return x
def classical_degradation(x, k, sf=3):
"""blur + downsampling
Args:
x: HxWxC image, [0, 1]/[0, 255]
k: hxw, double
sf: down-scale factor
Return:
downsampled LR image
"""
x = ndimage.filters.convolve(x, np.expand_dims(k, axis=2), mode="wrap")
# x = filters.correlate(x, np.expand_dims(np.flip(k), axis=2))
st = 0
return x[st::sf, st::sf, ...]
def add_sharpening(img, weight=0.5, radius=50, threshold=10):
"""USM sharpening. borrowed from real-ESRGAN
Input image: I; Blurry image: B.
1. K = I + weight * (I - B)
2. Mask = 1 if abs(I - B) > threshold, else: 0
3. Blur mask:
4. Out = Mask * K + (1 - Mask) * I
Args:
img (Numpy array): Input image, HWC, BGR; float32, [0, 1].
weight (float): Sharp weight. Default: 1.
radius (float): Kernel size of Gaussian blur. Default: 50.
threshold (int):
"""
if radius % 2 == 0:
radius += 1
blur = cv2.GaussianBlur(img, (radius, radius), 0)
residual = img - blur
mask = np.abs(residual) * 255 > threshold
mask = mask.astype("float32")
soft_mask = cv2.GaussianBlur(mask, (radius, radius), 0)
K = img + weight * residual
K = np.clip(K, 0, 1)
return soft_mask * K + (1 - soft_mask) * img
def add_blur(img, sf=4):
wd2 = 4.0 + sf
wd = 2.0 + 0.2 * sf
wd2 = wd2 / 4
wd = wd / 4
if random.random() < 0.5:
l1 = wd2 * random.random()
l2 = wd2 * random.random()
k = anisotropic_Gaussian(
ksize=random.randint(2, 11) + 3,
theta=random.random() * np.pi,
l1=l1,
l2=l2,
)
else:
k = fspecial("gaussian", random.randint(2, 4) + 3, wd * random.random())
img = ndimage.filters.convolve(img, np.expand_dims(k, axis=2), mode="mirror")
return img
def add_resize(img, sf=4):
rnum = np.random.rand()
if rnum > 0.8: # up
sf1 = random.uniform(1, 2)
elif rnum < 0.7: # down
sf1 = random.uniform(0.5 / sf, 1)
else:
sf1 = 1.0
img = cv2.resize(
img,
(int(sf1 * img.shape[1]), int(sf1 * img.shape[0])),
interpolation=random.choice([1, 2, 3]),
)
img = np.clip(img, 0.0, 1.0)
return img
# def add_Gaussian_noise(img, noise_level1=2, noise_level2=25):
# noise_level = random.randint(noise_level1, noise_level2)
# rnum = np.random.rand()
# if rnum > 0.6: # add color Gaussian noise
# img += np.random.normal(0, noise_level / 255.0, img.shape).astype(np.float32)
# elif rnum < 0.4: # add grayscale Gaussian noise
# img += np.random.normal(0, noise_level / 255.0, (*img.shape[:2], 1)).astype(np.float32)
# else: # add noise
# L = noise_level2 / 255.
# D = np.diag(np.random.rand(3))
# U = orth(np.random.rand(3, 3))
# conv = np.dot(np.dot(np.transpose(U), D), U)
# img += np.random.multivariate_normal([0, 0, 0], np.abs(L ** 2 * conv), img.shape[:2]).astype(np.float32)
# img = np.clip(img, 0.0, 1.0)
# return img
def add_Gaussian_noise(img, noise_level1=2, noise_level2=25):
noise_level = random.randint(noise_level1, noise_level2)
rnum = np.random.rand()
if rnum > 0.6: # add color Gaussian noise
img = img + np.random.normal(0, noise_level / 255.0, img.shape).astype(np.float32)
elif rnum < 0.4: # add grayscale Gaussian noise
img = img + np.random.normal(0, noise_level / 255.0, (*img.shape[:2], 1)).astype(np.float32)
else: # add noise
L = noise_level2 / 255.0
D = np.diag(np.random.rand(3))
U = orth(np.random.rand(3, 3))
conv = np.dot(np.dot(np.transpose(U), D), U)
img = img + np.random.multivariate_normal([0, 0, 0], np.abs(L**2 * conv), img.shape[:2]).astype(np.float32)
img = np.clip(img, 0.0, 1.0)
return img
def add_speckle_noise(img, noise_level1=2, noise_level2=25):
noise_level = random.randint(noise_level1, noise_level2)
img = np.clip(img, 0.0, 1.0)
rnum = random.random()
if rnum > 0.6:
img += img * np.random.normal(0, noise_level / 255.0, img.shape).astype(np.float32)
elif rnum < 0.4:
img += img * np.random.normal(0, noise_level / 255.0, (*img.shape[:2], 1)).astype(np.float32)
else:
L = noise_level2 / 255.0
D = np.diag(np.random.rand(3))
U = orth(np.random.rand(3, 3))
conv = np.dot(np.dot(np.transpose(U), D), U)
img += img * np.random.multivariate_normal([0, 0, 0], np.abs(L**2 * conv), img.shape[:2]).astype(np.float32)
img = np.clip(img, 0.0, 1.0)
return img
def add_Poisson_noise(img):
img = np.clip((img * 255.0).round(), 0, 255) / 255.0
vals = 10 ** (2 * random.random() + 2.0) # [2, 4]
if random.random() < 0.5:
img = np.random.poisson(img * vals).astype(np.float32) / vals
else:
img_gray = np.dot(img[..., :3], [0.299, 0.587, 0.114])
img_gray = np.clip((img_gray * 255.0).round(), 0, 255) / 255.0
noise_gray = np.random.poisson(img_gray * vals).astype(np.float32) / vals - img_gray
img += noise_gray[:, :, np.newaxis]
img = np.clip(img, 0.0, 1.0)
return img
def add_JPEG_noise(img):
quality_factor = random.randint(80, 95)
img = cv2.cvtColor(util.single2uint(img), cv2.COLOR_RGB2BGR)
result, encimg = cv2.imencode(".jpg", img, [int(cv2.IMWRITE_JPEG_QUALITY), quality_factor])
img = cv2.imdecode(encimg, 1)
img = cv2.cvtColor(util.uint2single(img), cv2.COLOR_BGR2RGB)
return img
def random_crop(lq, hq, sf=4, lq_patchsize=64):
h, w = lq.shape[:2]
rnd_h = random.randint(0, h - lq_patchsize)
rnd_w = random.randint(0, w - lq_patchsize)
lq = lq[rnd_h : rnd_h + lq_patchsize, rnd_w : rnd_w + lq_patchsize, :]
rnd_h_H, rnd_w_H = int(rnd_h * sf), int(rnd_w * sf)
hq = hq[
rnd_h_H : rnd_h_H + lq_patchsize * sf,
rnd_w_H : rnd_w_H + lq_patchsize * sf,
:,
]
return lq, hq
def degradation_bsrgan(img, sf=4, lq_patchsize=72, isp_model=None):
"""
This is the degradation model of BSRGAN from the paper
"Designing a Practical Degradation Model for Deep Blind Image Super-Resolution"
----------
img: HXWXC, [0, 1], its size should be large than (lq_patchsizexsf)x(lq_patchsizexsf)
sf: scale factor
isp_model: camera ISP model
Returns
-------
img: low-quality patch, size: lq_patchsizeXlq_patchsizeXC, range: [0, 1]
hq: corresponding high-quality patch, size: (lq_patchsizexsf)X(lq_patchsizexsf)XC, range: [0, 1]
"""
isp_prob, jpeg_prob, scale2_prob = 0.25, 0.9, 0.25
sf_ori = sf
h1, w1 = img.shape[:2]
img = img.copy()[: w1 - w1 % sf, : h1 - h1 % sf, ...] # mod crop
h, w = img.shape[:2]
if h < lq_patchsize * sf or w < lq_patchsize * sf:
raise ValueError(f"img size ({h1}X{w1}) is too small!")
hq = img.copy()
if sf == 4 and random.random() < scale2_prob: # downsample1
if np.random.rand() < 0.5:
img = cv2.resize(
img,
(int(1 / 2 * img.shape[1]), int(1 / 2 * img.shape[0])),
interpolation=random.choice([1, 2, 3]),
)
else:
img = util.imresize_np(img, 1 / 2, True)
img = np.clip(img, 0.0, 1.0)
sf = 2
shuffle_order = random.sample(range(7), 7)
idx1, idx2 = shuffle_order.index(2), shuffle_order.index(3)
if idx1 > idx2: # keep downsample3 last
shuffle_order[idx1], shuffle_order[idx2] = (
shuffle_order[idx2],
shuffle_order[idx1],
)
for i in shuffle_order:
if i == 0:
img = add_blur(img, sf=sf)
elif i == 1:
img = add_blur(img, sf=sf)
elif i == 2:
a, b = img.shape[1], img.shape[0]
# downsample2
if random.random() < 0.75:
sf1 = random.uniform(1, 2 * sf)
img = cv2.resize(
img,
(int(1 / sf1 * img.shape[1]), int(1 / sf1 * img.shape[0])),
interpolation=random.choice([1, 2, 3]),
)
else:
k = fspecial("gaussian", 25, random.uniform(0.1, 0.6 * sf))
k_shifted = shift_pixel(k, sf)
k_shifted = k_shifted / k_shifted.sum() # blur with shifted kernel
img = ndimage.filters.convolve(img, np.expand_dims(k_shifted, axis=2), mode="mirror")
img = img[0::sf, 0::sf, ...] # nearest downsampling
img = np.clip(img, 0.0, 1.0)
elif i == 3:
# downsample3
img = cv2.resize(
img,
(int(1 / sf * a), int(1 / sf * b)),
interpolation=random.choice([1, 2, 3]),
)
img = np.clip(img, 0.0, 1.0)
elif i == 4:
# add Gaussian noise
img = add_Gaussian_noise(img, noise_level1=2, noise_level2=8)
elif i == 5:
# add JPEG noise
if random.random() < jpeg_prob:
img = add_JPEG_noise(img)
elif i == 6:
# add processed camera sensor noise
if random.random() < isp_prob and isp_model is not None:
with torch.no_grad():
img, hq = isp_model.forward(img.copy(), hq)
# add final JPEG compression noise
img = add_JPEG_noise(img)
# random crop
img, hq = random_crop(img, hq, sf_ori, lq_patchsize)
return img, hq
# todo no isp_model?
def degradation_bsrgan_variant(image, sf=4, isp_model=None):
"""
This is the degradation model of BSRGAN from the paper
"Designing a Practical Degradation Model for Deep Blind Image Super-Resolution"
----------
sf: scale factor
isp_model: camera ISP model
Returns
-------
img: low-quality patch, size: lq_patchsizeXlq_patchsizeXC, range: [0, 1]
hq: corresponding high-quality patch, size: (lq_patchsizexsf)X(lq_patchsizexsf)XC, range: [0, 1]
"""
image = util.uint2single(image)
jpeg_prob, scale2_prob = 0.9, 0.25
# isp_prob = 0.25 # uncomment with `if i== 6` block below
# sf_ori = sf # uncomment with `if i== 6` block below
h1, w1 = image.shape[:2]
image = image.copy()[: w1 - w1 % sf, : h1 - h1 % sf, ...] # mod crop
h, w = image.shape[:2]
# hq = image.copy() # uncomment with `if i== 6` block below
if sf == 4 and random.random() < scale2_prob: # downsample1
if np.random.rand() < 0.5:
image = cv2.resize(
image,
(int(1 / 2 * image.shape[1]), int(1 / 2 * image.shape[0])),
interpolation=random.choice([1, 2, 3]),
)
else:
image = util.imresize_np(image, 1 / 2, True)
image = np.clip(image, 0.0, 1.0)
sf = 2
shuffle_order = random.sample(range(7), 7)
idx1, idx2 = shuffle_order.index(2), shuffle_order.index(3)
if idx1 > idx2: # keep downsample3 last
shuffle_order[idx1], shuffle_order[idx2] = (
shuffle_order[idx2],
shuffle_order[idx1],
)
for i in shuffle_order:
if i == 0:
image = add_blur(image, sf=sf)
# elif i == 1:
# image = add_blur(image, sf=sf)
if i == 0:
pass
elif i == 2:
a, b = image.shape[1], image.shape[0]
# downsample2
if random.random() < 0.8:
sf1 = random.uniform(1, 2 * sf)
image = cv2.resize(
image,
(
int(1 / sf1 * image.shape[1]),
int(1 / sf1 * image.shape[0]),
),
interpolation=random.choice([1, 2, 3]),
)
else:
k = fspecial("gaussian", 25, random.uniform(0.1, 0.6 * sf))
k_shifted = shift_pixel(k, sf)
k_shifted = k_shifted / k_shifted.sum() # blur with shifted kernel
image = ndimage.filters.convolve(image, np.expand_dims(k_shifted, axis=2), mode="mirror")
image = image[0::sf, 0::sf, ...] # nearest downsampling
image = np.clip(image, 0.0, 1.0)
elif i == 3:
# downsample3
image = cv2.resize(
image,
(int(1 / sf * a), int(1 / sf * b)),
interpolation=random.choice([1, 2, 3]),
)
image = np.clip(image, 0.0, 1.0)
elif i == 4:
# add Gaussian noise
image = add_Gaussian_noise(image, noise_level1=1, noise_level2=2)
elif i == 5:
# add JPEG noise
if random.random() < jpeg_prob:
image = add_JPEG_noise(image)
#
# elif i == 6:
# # add processed camera sensor noise
# if random.random() < isp_prob and isp_model is not None:
# with torch.no_grad():
# img, hq = isp_model.forward(img.copy(), hq)
# add final JPEG compression noise
image = add_JPEG_noise(image)
image = util.single2uint(image)
example = {"image": image}
return example
if __name__ == "__main__":
print("hey")
img = util.imread_uint("utils/test.png", 3)
img = img[:448, :448]
h = img.shape[0] // 4
print("resizing to", h)
sf = 4
deg_fn = partial(degradation_bsrgan_variant, sf=sf)
for i in range(20):
print(i)
img_hq = img
img_lq = deg_fn(img)["image"]
img_hq, img_lq = util.uint2single(img_hq), util.uint2single(img_lq)
print(img_lq)
img_lq_bicubic = albumentations.SmallestMaxSize(max_size=h, interpolation=cv2.INTER_CUBIC)(image=img_hq)[
"image"
]
print(img_lq.shape)
print("bicubic", img_lq_bicubic.shape)
print(img_hq.shape)
lq_nearest = cv2.resize(
util.single2uint(img_lq),
(int(sf * img_lq.shape[1]), int(sf * img_lq.shape[0])),
interpolation=0,
)
lq_bicubic_nearest = cv2.resize(
util.single2uint(img_lq_bicubic),
(int(sf * img_lq.shape[1]), int(sf * img_lq.shape[0])),
interpolation=0,
)
img_concat = np.concatenate([lq_bicubic_nearest, lq_nearest, util.single2uint(img_hq)], axis=1)
util.imsave(img_concat, str(i) + ".png")

BIN
invokeai/backend/stable_diffusion/image_degradation/utils/test.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 431 KiB

968
invokeai/backend/stable_diffusion/image_degradation/utils_image.py
View File

@ -1,968 +0,0 @@
import math
import os
import random
from datetime import datetime
import cv2
import numpy as np
import torch
from torchvision.utils import make_grid
import invokeai.backend.util.logging as logger
os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"
"""
# --------------------------------------------
# Kai Zhang (github: https://github.com/cszn)
# 03/Mar/2019
# --------------------------------------------
# https://github.com/twhui/SRGAN-pyTorch
# https://github.com/xinntao/BasicSR
# --------------------------------------------
"""
IMG_EXTENSIONS = [
".jpg",
".JPG",
".jpeg",
".JPEG",
".png",
".PNG",
".ppm",
".PPM",
".bmp",
".BMP",
".tif",
]
def is_image_file(filename):
return any(filename.endswith(extension) for extension in IMG_EXTENSIONS)
def get_timestamp():
return datetime.now().strftime("%y%m%d-%H%M%S")
def imshow(x, title=None, cbar=False, figsize=None):
import matplotlib.pyplot as plt
plt.figure(figsize=figsize)
plt.imshow(np.squeeze(x), interpolation="nearest", cmap="gray")
if title:
plt.title(title)
if cbar:
plt.colorbar()
plt.show()
def surf(Z, cmap="rainbow", figsize=None):
import matplotlib.pyplot as plt
plt.figure(figsize=figsize)
ax3 = plt.axes(projection="3d")
w, h = Z.shape[:2]
xx = np.arange(0, w, 1)
yy = np.arange(0, h, 1)
X, Y = np.meshgrid(xx, yy)
ax3.plot_surface(X, Y, Z, cmap=cmap)
# ax3.contour(X,Y,Z, zdim='z',offset=-2，cmap=cmap)
plt.show()
"""
# --------------------------------------------
# get image pathes
# --------------------------------------------
"""
def get_image_paths(dataroot):
paths = None # return None if dataroot is None
if dataroot is not None:
paths = sorted(_get_paths_from_images(dataroot))
return paths
def _get_paths_from_images(path):
assert os.path.isdir(path), "{:s} is not a valid directory".format(path)
images = []
for dirpath, _, fnames in sorted(os.walk(path, followlinks=True)):
for fname in sorted(fnames):
if is_image_file(fname):
img_path = os.path.join(dirpath, fname)
images.append(img_path)
assert images, "{:s} has no valid image file".format(path)
return images
"""
# --------------------------------------------
# split large images into small images
# --------------------------------------------
"""
def patches_from_image(img, p_size=512, p_overlap=64, p_max=800):
w, h = img.shape[:2]
patches = []
if w > p_max and h > p_max:
w1 = list(np.arange(0, w - p_size, p_size - p_overlap, dtype=np.int))
h1 = list(np.arange(0, h - p_size, p_size - p_overlap, dtype=np.int))
w1.append(w - p_size)
h1.append(h - p_size)
# print(w1)
# print(h1)
for i in w1:
for j in h1:
patches.append(img[i : i + p_size, j : j + p_size, :])
else:
patches.append(img)
return patches
def imssave(imgs, img_path):
"""
imgs: list, N images of size WxHxC
"""
img_name, ext = os.path.splitext(os.path.basename(img_path))
for i, img in enumerate(imgs):
if img.ndim == 3:
img = img[:, :, [2, 1, 0]]
new_path = os.path.join(
os.path.dirname(img_path),
img_name + str("_s{:04d}".format(i)) + ".png",
)
cv2.imwrite(new_path, img)
def split_imageset(
original_dataroot,
taget_dataroot,
n_channels=3,
p_size=800,
p_overlap=96,
p_max=1000,
):
"""
split the large images from original_dataroot into small overlapped images with size (p_size)x(p_size),
and save them into taget_dataroot; only the images with larger size than (p_max)x(p_max)
will be splitted.
Args:
original_dataroot:
taget_dataroot:
p_size: size of small images
p_overlap: patch size in training is a good choice
p_max: images with smaller size than (p_max)x(p_max) keep unchanged.
"""
paths = get_image_paths(original_dataroot)
for img_path in paths:
# img_name, ext = os.path.splitext(os.path.basename(img_path))
img = imread_uint(img_path, n_channels=n_channels)
patches = patches_from_image(img, p_size, p_overlap, p_max)
imssave(patches, os.path.join(taget_dataroot, os.path.basename(img_path)))
# if original_dataroot == taget_dataroot:
# del img_path
"""
# --------------------------------------------
# makedir
# --------------------------------------------
"""
def mkdir(path):
if not os.path.exists(path):
os.makedirs(path)
def mkdirs(paths):
if isinstance(paths, str):
mkdir(paths)
else:
for path in paths:
mkdir(path)
def mkdir_and_rename(path):
if os.path.exists(path):
new_name = path + "_archived_" + get_timestamp()
logger.error("Path already exists. Rename it to [{:s}]".format(new_name))
os.replace(path, new_name)
os.makedirs(path)
"""
# --------------------------------------------
# read image from path
# opencv is fast, but read BGR numpy image
# --------------------------------------------
"""
# --------------------------------------------
# get uint8 image of size HxWxn_channles (RGB)
# --------------------------------------------
def imread_uint(path, n_channels=3):
# input: path
# output: HxWx3(RGB or GGG), or HxWx1 (G)
if n_channels == 1:
img = cv2.imread(path, 0) # cv2.IMREAD_GRAYSCALE
img = np.expand_dims(img, axis=2) # HxWx1
elif n_channels == 3:
img = cv2.imread(path, cv2.IMREAD_UNCHANGED) # BGR or G
if img.ndim == 2:
img = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB) # GGG
else:
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) # RGB
return img
# --------------------------------------------
# matlab's imwrite
# --------------------------------------------
def imsave(img, img_path):
img = np.squeeze(img)
if img.ndim == 3:
img = img[:, :, [2, 1, 0]]
cv2.imwrite(img_path, img)
def imwrite(img, img_path):
img = np.squeeze(img)
if img.ndim == 3:
img = img[:, :, [2, 1, 0]]
cv2.imwrite(img_path, img)
# --------------------------------------------
# get single image of size HxWxn_channles (BGR)
# --------------------------------------------
def read_img(path):
# read image by cv2
# return: Numpy float32, HWC, BGR, [0,1]
img = cv2.imread(path, cv2.IMREAD_UNCHANGED) # cv2.IMREAD_GRAYSCALE
img = img.astype(np.float32) / 255.0
if img.ndim == 2:
img = np.expand_dims(img, axis=2)
# some images have 4 channels
if img.shape[2] > 3:
img = img[:, :, :3]
return img
"""
# --------------------------------------------
# image format conversion
# --------------------------------------------
# numpy(single) <---> numpy(unit)
# numpy(single) <---> tensor
# numpy(unit) <---> tensor
# --------------------------------------------
"""
# --------------------------------------------
# numpy(single) [0, 1] <---> numpy(unit)
# --------------------------------------------
def uint2single(img):
return np.float32(img / 255.0)
def single2uint(img):
return np.uint8((img.clip(0, 1) * 255.0).round())
def uint162single(img):
return np.float32(img / 65535.0)
def single2uint16(img):
return np.uint16((img.clip(0, 1) * 65535.0).round())
# --------------------------------------------
# numpy(unit) (HxWxC or HxW) <---> tensor
# --------------------------------------------
# convert uint to 4-dimensional torch tensor
def uint2tensor4(img):
if img.ndim == 2:
img = np.expand_dims(img, axis=2)
return torch.from_numpy(np.ascontiguousarray(img)).permute(2, 0, 1).float().div(255.0).unsqueeze(0)
# convert uint to 3-dimensional torch tensor
def uint2tensor3(img):
if img.ndim == 2:
img = np.expand_dims(img, axis=2)
return torch.from_numpy(np.ascontiguousarray(img)).permute(2, 0, 1).float().div(255.0)
# convert 2/3/4-dimensional torch tensor to uint
def tensor2uint(img):
img = img.data.squeeze().float().clamp_(0, 1).cpu().numpy()
if img.ndim == 3:
img = np.transpose(img, (1, 2, 0))
return np.uint8((img * 255.0).round())
# --------------------------------------------
# numpy(single) (HxWxC) <---> tensor
# --------------------------------------------
# convert single (HxWxC) to 3-dimensional torch tensor
def single2tensor3(img):
return torch.from_numpy(np.ascontiguousarray(img)).permute(2, 0, 1).float()
# convert single (HxWxC) to 4-dimensional torch tensor
def single2tensor4(img):
return torch.from_numpy(np.ascontiguousarray(img)).permute(2, 0, 1).float().unsqueeze(0)
# convert torch tensor to single
def tensor2single(img):
img = img.data.squeeze().float().cpu().numpy()
if img.ndim == 3:
img = np.transpose(img, (1, 2, 0))
return img
# convert torch tensor to single
def tensor2single3(img):
img = img.data.squeeze().float().cpu().numpy()
if img.ndim == 3:
img = np.transpose(img, (1, 2, 0))
elif img.ndim == 2:
img = np.expand_dims(img, axis=2)
return img
def single2tensor5(img):
return torch.from_numpy(np.ascontiguousarray(img)).permute(2, 0, 1, 3).float().unsqueeze(0)
def single32tensor5(img):
return torch.from_numpy(np.ascontiguousarray(img)).float().unsqueeze(0).unsqueeze(0)
def single42tensor4(img):
return torch.from_numpy(np.ascontiguousarray(img)).permute(2, 0, 1, 3).float()
# from skimage.io import imread, imsave
def tensor2img(tensor, out_type=np.uint8, min_max=(0, 1)):
"""
Converts a torch Tensor into an image Numpy array of BGR channel order
Input: 4D(B,(3/1),H,W), 3D(C,H,W), or 2D(H,W), any range, RGB channel order
Output: 3D(H,W,C) or 2D(H,W), [0,255], np.uint8 (default)
"""
tensor = tensor.squeeze().float().cpu().clamp_(*min_max) # squeeze first, then clamp
tensor = (tensor - min_max[0]) / (min_max[1] - min_max[0]) # to range [0,1]
n_dim = tensor.dim()
if n_dim == 4:
n_img = len(tensor)
img_np = make_grid(tensor, nrow=int(math.sqrt(n_img)), normalize=False).numpy()
img_np = np.transpose(img_np[[2, 1, 0], :, :], (1, 2, 0)) # HWC, BGR
elif n_dim == 3:
img_np = tensor.numpy()
img_np = np.transpose(img_np[[2, 1, 0], :, :], (1, 2, 0)) # HWC, BGR
elif n_dim == 2:
img_np = tensor.numpy()
else:
raise TypeError("Only support 4D, 3D and 2D tensor. But received with dimension: {:d}".format(n_dim))
if out_type == np.uint8:
img_np = (img_np * 255.0).round()
# Important. Unlike matlab, numpy.unit8() WILL NOT round by default.
return img_np.astype(out_type)
"""
# --------------------------------------------
# Augmentation, flipe and/or rotate
# --------------------------------------------
# The following two are enough.
# (1) augmet_img: numpy image of WxHxC or WxH
# (2) augment_img_tensor4: tensor image 1xCxWxH
# --------------------------------------------
"""
def augment_img(img, mode=0):
"""Kai Zhang (github: https://github.com/cszn)"""
if mode == 0:
return img
elif mode == 1:
return np.flipud(np.rot90(img))
elif mode == 2:
return np.flipud(img)
elif mode == 3:
return np.rot90(img, k=3)
elif mode == 4:
return np.flipud(np.rot90(img, k=2))
elif mode == 5:
return np.rot90(img)
elif mode == 6:
return np.rot90(img, k=2)
elif mode == 7:
return np.flipud(np.rot90(img, k=3))
def augment_img_tensor4(img, mode=0):
"""Kai Zhang (github: https://github.com/cszn)"""
if mode == 0:
return img
elif mode == 1:
return img.rot90(1, [2, 3]).flip([2])
elif mode == 2:
return img.flip([2])
elif mode == 3:
return img.rot90(3, [2, 3])
elif mode == 4:
return img.rot90(2, [2, 3]).flip([2])
elif mode == 5:
return img.rot90(1, [2, 3])
elif mode == 6:
return img.rot90(2, [2, 3])
elif mode == 7:
return img.rot90(3, [2, 3]).flip([2])
def augment_img_tensor(img, mode=0):
"""Kai Zhang (github: https://github.com/cszn)"""
img_size = img.size()
img_np = img.data.cpu().numpy()
if len(img_size) == 3:
img_np = np.transpose(img_np, (1, 2, 0))
elif len(img_size) == 4:
img_np = np.transpose(img_np, (2, 3, 1, 0))
img_np = augment_img(img_np, mode=mode)
img_tensor = torch.from_numpy(np.ascontiguousarray(img_np))
if len(img_size) == 3:
img_tensor = img_tensor.permute(2, 0, 1)
elif len(img_size) == 4:
img_tensor = img_tensor.permute(3, 2, 0, 1)
return img_tensor.type_as(img)
def augment_img_np3(img, mode=0):
if mode == 0:
return img
elif mode == 1:
return img.transpose(1, 0, 2)
elif mode == 2:
return img[::-1, :, :]
elif mode == 3:
img = img[::-1, :, :]
img = img.transpose(1, 0, 2)
return img
elif mode == 4:
return img[:, ::-1, :]
elif mode == 5:
img = img[:, ::-1, :]
img = img.transpose(1, 0, 2)
return img
elif mode == 6:
img = img[:, ::-1, :]
img = img[::-1, :, :]
return img
elif mode == 7:
img = img[:, ::-1, :]
img = img[::-1, :, :]
img = img.transpose(1, 0, 2)
return img
def augment_imgs(img_list, hflip=True, rot=True):
# horizontal flip OR rotate
hflip = hflip and random.random() < 0.5
vflip = rot and random.random() < 0.5
rot90 = rot and random.random() < 0.5
def _augment(img):
if hflip:
img = img[:, ::-1, :]
if vflip:
img = img[::-1, :, :]
if rot90:
img = img.transpose(1, 0, 2)
return img
return [_augment(img) for img in img_list]
"""
# --------------------------------------------
# modcrop and shave
# --------------------------------------------
"""
def modcrop(img_in, scale):
# img_in: Numpy, HWC or HW
img = np.copy(img_in)
if img.ndim == 2:
H, W = img.shape
H_r, W_r = H % scale, W % scale
img = img[: H - H_r, : W - W_r]
elif img.ndim == 3:
H, W, C = img.shape
H_r, W_r = H % scale, W % scale
img = img[: H - H_r, : W - W_r, :]
else:
raise ValueError("Wrong img ndim: [{:d}].".format(img.ndim))
return img
def shave(img_in, border=0):
# img_in: Numpy, HWC or HW
img = np.copy(img_in)
h, w = img.shape[:2]
img = img[border : h - border, border : w - border]
return img
"""
# --------------------------------------------
# image processing process on numpy image
# channel_convert(in_c, tar_type, img_list):
# rgb2ycbcr(img, only_y=True):
# bgr2ycbcr(img, only_y=True):
# ycbcr2rgb(img):
# --------------------------------------------
"""
def rgb2ycbcr(img, only_y=True):
"""same as matlab rgb2ycbcr
only_y: only return Y channel
Input:
uint8, [0, 255]
float, [0, 1]
"""
in_img_type = img.dtype
img.astype(np.float32)
if in_img_type != np.uint8:
img *= 255.0
# convert
if only_y:
rlt = np.dot(img, [65.481, 128.553, 24.966]) / 255.0 + 16.0
else:
rlt = np.matmul(
img,
[
[65.481, -37.797, 112.0],
[128.553, -74.203, -93.786],
[24.966, 112.0, -18.214],
],
) / 255.0 + [16, 128, 128]
if in_img_type == np.uint8:
rlt = rlt.round()
else:
rlt /= 255.0
return rlt.astype(in_img_type)
def ycbcr2rgb(img):
"""same as matlab ycbcr2rgb
Input:
uint8, [0, 255]
float, [0, 1]
"""
in_img_type = img.dtype
img.astype(np.float32)
if in_img_type != np.uint8:
img *= 255.0
# convert
rlt = np.matmul(
img,
[
[0.00456621, 0.00456621, 0.00456621],
[0, -0.00153632, 0.00791071],
[0.00625893, -0.00318811, 0],
],
) * 255.0 + [-222.921, 135.576, -276.836]
if in_img_type == np.uint8:
rlt = rlt.round()
else:
rlt /= 255.0
return rlt.astype(in_img_type)
def bgr2ycbcr(img, only_y=True):
"""bgr version of rgb2ycbcr
only_y: only return Y channel
Input:
uint8, [0, 255]
float, [0, 1]
"""
in_img_type = img.dtype
img.astype(np.float32)
if in_img_type != np.uint8:
img *= 255.0
# convert
if only_y:
rlt = np.dot(img, [24.966, 128.553, 65.481]) / 255.0 + 16.0
else:
rlt = np.matmul(
img,
[
[24.966, 112.0, -18.214],
[128.553, -74.203, -93.786],
[65.481, -37.797, 112.0],
],
) / 255.0 + [16, 128, 128]
if in_img_type == np.uint8:
rlt = rlt.round()
else:
rlt /= 255.0
return rlt.astype(in_img_type)
def channel_convert(in_c, tar_type, img_list):
# conversion among BGR, gray and y
if in_c == 3 and tar_type == "gray": # BGR to gray
gray_list = [cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) for img in img_list]
return [np.expand_dims(img, axis=2) for img in gray_list]
elif in_c == 3 and tar_type == "y": # BGR to y
y_list = [bgr2ycbcr(img, only_y=True) for img in img_list]
return [np.expand_dims(img, axis=2) for img in y_list]
elif in_c == 1 and tar_type == "RGB": # gray/y to BGR
return [cv2.cvtColor(img, cv2.COLOR_GRAY2BGR) for img in img_list]
else:
return img_list
"""
# --------------------------------------------
# metric, PSNR and SSIM
# --------------------------------------------
"""
# --------------------------------------------
# PSNR
# --------------------------------------------
def calculate_psnr(img1, img2, border=0):
# img1 and img2 have range [0, 255]
# img1 = img1.squeeze()
# img2 = img2.squeeze()
if not img1.shape == img2.shape:
raise ValueError("Input images must have the same dimensions.")
h, w = img1.shape[:2]
img1 = img1[border : h - border, border : w - border]
img2 = img2[border : h - border, border : w - border]
img1 = img1.astype(np.float64)
img2 = img2.astype(np.float64)
mse = np.mean((img1 - img2) ** 2)
if mse == 0:
return float("inf")
return 20 * math.log10(255.0 / math.sqrt(mse))
# --------------------------------------------
# SSIM
# --------------------------------------------
def calculate_ssim(img1, img2, border=0):
"""calculate SSIM
the same outputs as MATLAB's
img1, img2: [0, 255]
"""
# img1 = img1.squeeze()
# img2 = img2.squeeze()
if not img1.shape == img2.shape:
raise ValueError("Input images must have the same dimensions.")
h, w = img1.shape[:2]
img1 = img1[border : h - border, border : w - border]
img2 = img2[border : h - border, border : w - border]
if img1.ndim == 2:
return ssim(img1, img2)
elif img1.ndim == 3:
if img1.shape[2] == 3:
ssims = []
for i in range(3):
ssims.append(ssim(img1[:, :, i], img2[:, :, i]))
return np.array(ssims).mean()
elif img1.shape[2] == 1:
return ssim(np.squeeze(img1), np.squeeze(img2))
else:
raise ValueError("Wrong input image dimensions.")
def ssim(img1, img2):
C1 = (0.01 * 255) ** 2
C2 = (0.03 * 255) ** 2
img1 = img1.astype(np.float64)
img2 = img2.astype(np.float64)
kernel = cv2.getGaussianKernel(11, 1.5)
window = np.outer(kernel, kernel.transpose())
mu1 = cv2.filter2D(img1, -1, window)[5:-5, 5:-5] # valid
mu2 = cv2.filter2D(img2, -1, window)[5:-5, 5:-5]
mu1_sq = mu1**2
mu2_sq = mu2**2
mu1_mu2 = mu1 * mu2
sigma1_sq = cv2.filter2D(img1**2, -1, window)[5:-5, 5:-5] - mu1_sq
sigma2_sq = cv2.filter2D(img2**2, -1, window)[5:-5, 5:-5] - mu2_sq
sigma12 = cv2.filter2D(img1 * img2, -1, window)[5:-5, 5:-5] - mu1_mu2
ssim_map = ((2 * mu1_mu2 + C1) * (2 * sigma12 + C2)) / ((mu1_sq + mu2_sq + C1) * (sigma1_sq + sigma2_sq + C2))
return ssim_map.mean()
"""
# --------------------------------------------
# matlab's bicubic imresize (numpy and torch) [0, 1]
# --------------------------------------------
"""
# matlab 'imresize' function, now only support 'bicubic'
def cubic(x):
absx = torch.abs(x)
absx2 = absx**2
absx3 = absx**3
return (1.5 * absx3 - 2.5 * absx2 + 1) * ((absx <= 1).type_as(absx)) + (
-0.5 * absx3 + 2.5 * absx2 - 4 * absx + 2
) * (((absx > 1) * (absx <= 2)).type_as(absx))
def calculate_weights_indices(in_length, out_length, scale, kernel, kernel_width, antialiasing):
if (scale < 1) and (antialiasing):
# Use a modified kernel to simultaneously interpolate and antialias- larger kernel width
kernel_width = kernel_width / scale
# Output-space coordinates
x = torch.linspace(1, out_length, out_length)
# Input-space coordinates. Calculate the inverse mapping such that 0.5
# in output space maps to 0.5 in input space, and 0.5+scale in output
# space maps to 1.5 in input space.
u = x / scale + 0.5 * (1 - 1 / scale)
# What is the left-most pixel that can be involved in the computation?
left = torch.floor(u - kernel_width / 2)
# What is the maximum number of pixels that can be involved in the
# computation? Note: it's OK to use an extra pixel here; if the
# corresponding weights are all zero, it will be eliminated at the end
# of this function.
P = math.ceil(kernel_width) + 2
# The indices of the input pixels involved in computing the k-th output
# pixel are in row k of the indices matrix.
indices = left.view(out_length, 1).expand(out_length, P) + torch.linspace(0, P - 1, P).view(1, P).expand(
out_length, P
)
# The weights used to compute the k-th output pixel are in row k of the
# weights matrix.
distance_to_center = u.view(out_length, 1).expand(out_length, P) - indices
# apply cubic kernel
if (scale < 1) and (antialiasing):
weights = scale * cubic(distance_to_center * scale)
else:
weights = cubic(distance_to_center)
# Normalize the weights matrix so that each row sums to 1.
weights_sum = torch.sum(weights, 1).view(out_length, 1)
weights = weights / weights_sum.expand(out_length, P)
# If a column in weights is all zero, get rid of it. only consider the first and last column.
weights_zero_tmp = torch.sum((weights == 0), 0)
if not math.isclose(weights_zero_tmp[0], 0, rel_tol=1e-6):
indices = indices.narrow(1, 1, P - 2)
weights = weights.narrow(1, 1, P - 2)
if not math.isclose(weights_zero_tmp[-1], 0, rel_tol=1e-6):
indices = indices.narrow(1, 0, P - 2)
weights = weights.narrow(1, 0, P - 2)
weights = weights.contiguous()
indices = indices.contiguous()
sym_len_s = -indices.min() + 1
sym_len_e = indices.max() - in_length
indices = indices + sym_len_s - 1
return weights, indices, int(sym_len_s), int(sym_len_e)
# --------------------------------------------
# imresize for tensor image [0, 1]
# --------------------------------------------
def imresize(img, scale, antialiasing=True):
# Now the scale should be the same for H and W
# input: img: pytorch tensor, CHW or HW [0,1]
# output: CHW or HW [0,1] w/o round
need_squeeze = True if img.dim() == 2 else False
if need_squeeze:
img.unsqueeze_(0)
in_C, in_H, in_W = img.size()
out_C, out_H, out_W = (
in_C,
math.ceil(in_H * scale),
math.ceil(in_W * scale),
)
kernel_width = 4
kernel = "cubic"
# Return the desired dimension order for performing the resize. The
# strategy is to perform the resize first along the dimension with the
# smallest scale factor.
# Now we do not support this.
# get weights and indices
weights_H, indices_H, sym_len_Hs, sym_len_He = calculate_weights_indices(
in_H, out_H, scale, kernel, kernel_width, antialiasing
)
weights_W, indices_W, sym_len_Ws, sym_len_We = calculate_weights_indices(
in_W, out_W, scale, kernel, kernel_width, antialiasing
)
# process H dimension
# symmetric copying
img_aug = torch.FloatTensor(in_C, in_H + sym_len_Hs + sym_len_He, in_W)
img_aug.narrow(1, sym_len_Hs, in_H).copy_(img)
sym_patch = img[:, :sym_len_Hs, :]
inv_idx = torch.arange(sym_patch.size(1) - 1, -1, -1).long()
sym_patch_inv = sym_patch.index_select(1, inv_idx)
img_aug.narrow(1, 0, sym_len_Hs).copy_(sym_patch_inv)
sym_patch = img[:, -sym_len_He:, :]
inv_idx = torch.arange(sym_patch.size(1) - 1, -1, -1).long()
sym_patch_inv = sym_patch.index_select(1, inv_idx)
img_aug.narrow(1, sym_len_Hs + in_H, sym_len_He).copy_(sym_patch_inv)
out_1 = torch.FloatTensor(in_C, out_H, in_W)
kernel_width = weights_H.size(1)
for i in range(out_H):
idx = int(indices_H[i][0])
for j in range(out_C):
out_1[j, i, :] = img_aug[j, idx : idx + kernel_width, :].transpose(0, 1).mv(weights_H[i])
# process W dimension
# symmetric copying
out_1_aug = torch.FloatTensor(in_C, out_H, in_W + sym_len_Ws + sym_len_We)
out_1_aug.narrow(2, sym_len_Ws, in_W).copy_(out_1)
sym_patch = out_1[:, :, :sym_len_Ws]
inv_idx = torch.arange(sym_patch.size(2) - 1, -1, -1).long()
sym_patch_inv = sym_patch.index_select(2, inv_idx)
out_1_aug.narrow(2, 0, sym_len_Ws).copy_(sym_patch_inv)
sym_patch = out_1[:, :, -sym_len_We:]
inv_idx = torch.arange(sym_patch.size(2) - 1, -1, -1).long()
sym_patch_inv = sym_patch.index_select(2, inv_idx)
out_1_aug.narrow(2, sym_len_Ws + in_W, sym_len_We).copy_(sym_patch_inv)
out_2 = torch.FloatTensor(in_C, out_H, out_W)
kernel_width = weights_W.size(1)
for i in range(out_W):
idx = int(indices_W[i][0])
for j in range(out_C):
out_2[j, :, i] = out_1_aug[j, :, idx : idx + kernel_width].mv(weights_W[i])
if need_squeeze:
out_2.squeeze_()
return out_2
# --------------------------------------------
# imresize for numpy image [0, 1]
# --------------------------------------------
def imresize_np(img, scale, antialiasing=True):
# Now the scale should be the same for H and W
# input: img: Numpy, HWC or HW [0,1]
# output: HWC or HW [0,1] w/o round
img = torch.from_numpy(img)
need_squeeze = True if img.dim() == 2 else False
if need_squeeze:
img.unsqueeze_(2)
in_H, in_W, in_C = img.size()
out_C, out_H, out_W = (
in_C,
math.ceil(in_H * scale),
math.ceil(in_W * scale),
)
kernel_width = 4
kernel = "cubic"
# Return the desired dimension order for performing the resize. The
# strategy is to perform the resize first along the dimension with the
# smallest scale factor.
# Now we do not support this.
# get weights and indices
weights_H, indices_H, sym_len_Hs, sym_len_He = calculate_weights_indices(
in_H, out_H, scale, kernel, kernel_width, antialiasing
)
weights_W, indices_W, sym_len_Ws, sym_len_We = calculate_weights_indices(
in_W, out_W, scale, kernel, kernel_width, antialiasing
)
# process H dimension
# symmetric copying
img_aug = torch.FloatTensor(in_H + sym_len_Hs + sym_len_He, in_W, in_C)
img_aug.narrow(0, sym_len_Hs, in_H).copy_(img)
sym_patch = img[:sym_len_Hs, :, :]
inv_idx = torch.arange(sym_patch.size(0) - 1, -1, -1).long()
sym_patch_inv = sym_patch.index_select(0, inv_idx)
img_aug.narrow(0, 0, sym_len_Hs).copy_(sym_patch_inv)
sym_patch = img[-sym_len_He:, :, :]
inv_idx = torch.arange(sym_patch.size(0) - 1, -1, -1).long()
sym_patch_inv = sym_patch.index_select(0, inv_idx)
img_aug.narrow(0, sym_len_Hs + in_H, sym_len_He).copy_(sym_patch_inv)
out_1 = torch.FloatTensor(out_H, in_W, in_C)
kernel_width = weights_H.size(1)
for i in range(out_H):
idx = int(indices_H[i][0])
for j in range(out_C):
out_1[i, :, j] = img_aug[idx : idx + kernel_width, :, j].transpose(0, 1).mv(weights_H[i])
# process W dimension
# symmetric copying
out_1_aug = torch.FloatTensor(out_H, in_W + sym_len_Ws + sym_len_We, in_C)
out_1_aug.narrow(1, sym_len_Ws, in_W).copy_(out_1)
sym_patch = out_1[:, :sym_len_Ws, :]
inv_idx = torch.arange(sym_patch.size(1) - 1, -1, -1).long()
sym_patch_inv = sym_patch.index_select(1, inv_idx)
out_1_aug.narrow(1, 0, sym_len_Ws).copy_(sym_patch_inv)
sym_patch = out_1[:, -sym_len_We:, :]
inv_idx = torch.arange(sym_patch.size(1) - 1, -1, -1).long()
sym_patch_inv = sym_patch.index_select(1, inv_idx)
out_1_aug.narrow(1, sym_len_Ws + in_W, sym_len_We).copy_(sym_patch_inv)
out_2 = torch.FloatTensor(out_H, out_W, in_C)
kernel_width = weights_W.size(1)
for i in range(out_W):
idx = int(indices_W[i][0])
for j in range(out_C):
out_2[:, i, j] = out_1_aug[:, idx : idx + kernel_width, j].mv(weights_W[i])
if need_squeeze:
out_2.squeeze_()
return out_2.numpy()
if __name__ == "__main__":
print("---")
# img = imread_uint('test.bmp', 3)
# img = uint2single(img)
# img_bicubic = imresize_np(img, 1/4)

1
invokeai/backend/util/__init__.py
View File

@ -10,7 +10,6 @@ from .devices import ( # noqa: F401
normalize_device,
torch_dtype,
)
from .log import write_log # noqa: F401
from .util import ( # noqa: F401
ask_user,
download_with_resume,

107
invokeai/backend/util/hotfixes.py
View File

@ -1,11 +1,11 @@
from typing import Any, Dict, List, Optional, Tuple, Union
import diffusers
import torch
from torch import nn
from diffusers.configuration_utils import ConfigMixin, register_to_config
from diffusers.loaders import FromOriginalControlnetMixin
from diffusers.models.attention_processor import AttentionProcessor, AttnProcessor
from diffusers.models.controlnet import ControlNetConditioningEmbedding, ControlNetOutput, zero_module
from diffusers.models.embeddings import (
TextImageProjection,
TextImageTimeEmbedding,
@ -14,16 +14,9 @@ from diffusers.models.embeddings import (
Timesteps,
)
from diffusers.models.modeling_utils import ModelMixin
from diffusers.models.unet_2d_blocks import (
CrossAttnDownBlock2D,
DownBlock2D,
UNetMidBlock2DCrossAttn,
get_down_block,
)
from diffusers.models.unet_2d_blocks import CrossAttnDownBlock2D, DownBlock2D, UNetMidBlock2DCrossAttn, get_down_block
from diffusers.models.unet_2d_condition import UNet2DConditionModel
import diffusers
from diffusers.models.controlnet import ControlNetConditioningEmbedding, ControlNetOutput, zero_module
from torch import nn
from invokeai.backend.util.logging import InvokeAILogger
@ -45,7 +38,8 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlnetMixin):
Whether to flip the sin to cos in the time embedding.
freq_shift (`int`, defaults to 0):
The frequency shift to apply to the time embedding.
down_block_types (`tuple[str]`, defaults to `("CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "DownBlock2D")`):
down_block_types (`tuple[str]`, defaults to `("CrossAttnDownBlock2D", "CrossAttnDownBlock2D", \
"CrossAttnDownBlock2D", "DownBlock2D")`):
The tuple of downsample blocks to use.
only_cross_attention (`Union[bool, Tuple[bool]]`, defaults to `False`):
block_out_channels (`tuple[int]`, defaults to `(320, 640, 1280, 1280)`):
@ -147,7 +141,9 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlnetMixin):
# If `num_attention_heads` is not defined (which is the case for most models)
# it will default to `attention_head_dim`. This looks weird upon first reading it and it is.
# The reason for this behavior is to correct for incorrectly named variables that were introduced
# when this library was created. The incorrect naming was only discovered much later in https://github.com/huggingface/diffusers/issues/2011#issuecomment-1547958131
# when this library was created...
# The incorrect naming was only discovered much ...
# later in https://github.com/huggingface/diffusers/issues/2011#issuecomment-1547958131
# Changing `attention_head_dim` to `num_attention_heads` for 40,000+ configurations is too backwards breaking
# which is why we correct for the naming here.
num_attention_heads = num_attention_heads or attention_head_dim
@ -155,17 +151,20 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlnetMixin):
# Check inputs
if len(block_out_channels) != len(down_block_types):
raise ValueError(
f"Must provide the same number of `block_out_channels` as `down_block_types`. `block_out_channels`: {block_out_channels}. `down_block_types`: {down_block_types}."
f"Must provide the same number of `block_out_channels` as `down_block_types`. \
`block_out_channels`: {block_out_channels}. `down_block_types`: {down_block_types}."
)
if not isinstance(only_cross_attention, bool) and len(only_cross_attention) != len(down_block_types):
raise ValueError(
f"Must provide the same number of `only_cross_attention` as `down_block_types`. `only_cross_attention`: {only_cross_attention}. `down_block_types`: {down_block_types}."
f"Must provide the same number of `only_cross_attention` as `down_block_types`. \
`only_cross_attention`: {only_cross_attention}. `down_block_types`: {down_block_types}."
)
if not isinstance(num_attention_heads, int) and len(num_attention_heads) != len(down_block_types):
raise ValueError(
f"Must provide the same number of `num_attention_heads` as `down_block_types`. `num_attention_heads`: {num_attention_heads}. `down_block_types`: {down_block_types}."
f"Must provide the same number of `num_attention_heads` as `down_block_types`. \
`num_attention_heads`: {num_attention_heads}. `down_block_types`: {down_block_types}."
)
if isinstance(transformer_layers_per_block, int):
@ -202,7 +201,8 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlnetMixin):
self.encoder_hid_proj = nn.Linear(encoder_hid_dim, cross_attention_dim)
elif encoder_hid_dim_type == "text_image_proj":
# image_embed_dim DOESN'T have to be `cross_attention_dim`. To not clutter the __init__ too much
# they are set to `cross_attention_dim` here as this is exactly the required dimension for the currently only use
# they are set to `cross_attention_dim` here as this is exactly the required dimension ...
# for the currently only use
# case when `addition_embed_type == "text_image_proj"` (Kadinsky 2.1)`
self.encoder_hid_proj = TextImageProjection(
text_embed_dim=encoder_hid_dim,
@ -250,8 +250,10 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlnetMixin):
text_time_embedding_from_dim, time_embed_dim, num_heads=addition_embed_type_num_heads
)
elif addition_embed_type == "text_image":
# text_embed_dim and image_embed_dim DON'T have to be `cross_attention_dim`. To not clutter the __init__ too much
# they are set to `cross_attention_dim` here as this is exactly the required dimension for the currently only use
# text_embed_dim and image_embed_dim DON'T have to be `cross_attention_dim`.
# To not clutter the __init__ too much
# they are set to `cross_attention_dim` here as this is exactly the required dimension...
# for the currently only use
# case when `addition_embed_type == "text_image"` (Kadinsky 2.1)`
self.add_embedding = TextImageTimeEmbedding(
text_embed_dim=cross_attention_dim, image_embed_dim=cross_attention_dim, time_embed_dim=time_embed_dim
@ -673,12 +675,14 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlnetMixin):
elif self.config.addition_embed_type == "text_time":
if "text_embeds" not in added_cond_kwargs:
raise ValueError(
f"{self.__class__} has the config param `addition_embed_type` set to 'text_time' which requires the keyword argument `text_embeds` to be passed in `added_cond_kwargs`"
f"{self.__class__} has the config param `addition_embed_type` set to 'text_time' which \
requires the keyword argument `text_embeds` to be passed in `added_cond_kwargs`"
)
text_embeds = added_cond_kwargs.get("text_embeds")
if "time_ids" not in added_cond_kwargs:
raise ValueError(
f"{self.__class__} has the config param `addition_embed_type` set to 'text_time' which requires the keyword argument `time_ids` to be passed in `added_cond_kwargs`"
f"{self.__class__} has the config param `addition_embed_type` set to 'text_time' which \
requires the keyword argument `time_ids` to be passed in `added_cond_kwargs`"
)
time_ids = added_cond_kwargs.get("time_ids")
time_embeds = self.add_time_proj(time_ids.flatten())
@ -761,3 +765,64 @@ class ControlNetModel(ModelMixin, ConfigMixin, FromOriginalControlnetMixin):
diffusers.ControlNetModel = ControlNetModel
diffusers.models.controlnet.ControlNetModel = ControlNetModel
# patch LoRACompatibleConv to use original Conv2D forward function
# this needed to make work seamless patch
# NOTE: with this patch, torch.compile crashes on 2.0 torch(already fixed in nightly)
# https://github.com/huggingface/diffusers/pull/4315
# https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/lora.py#L96C18-L96C18
def new_LoRACompatibleConv_forward(self, x):
if self.lora_layer is None:
return super(diffusers.models.lora.LoRACompatibleConv, self).forward(x)
else:
return super(diffusers.models.lora.LoRACompatibleConv, self).forward(x) + self.lora_layer(x)
diffusers.models.lora.LoRACompatibleConv.forward = new_LoRACompatibleConv_forward
try:
import xformers
xformers_available = True
except Exception:
xformers_available = False
if xformers_available:
# TODO: remove when fixed in diffusers
_xformers_memory_efficient_attention = xformers.ops.memory_efficient_attention
def new_memory_efficient_attention(
query: torch.Tensor,
key: torch.Tensor,
value: torch.Tensor,
attn_bias=None,
p: float = 0.0,
scale: Optional[float] = None,
*,
op=None,
):
# diffusers not align shape to 8, which is required by xformers
if attn_bias is not None and type(attn_bias) is torch.Tensor:
orig_size = attn_bias.shape[-1]
new_size = ((orig_size + 7) // 8) * 8
aligned_attn_bias = torch.zeros(
(attn_bias.shape[0], attn_bias.shape[1], new_size),
device=attn_bias.device,
dtype=attn_bias.dtype,
)
aligned_attn_bias[:, :, :orig_size] = attn_bias
attn_bias = aligned_attn_bias[:, :, :orig_size]
return _xformers_memory_efficient_attention(
query=query,
key=key,
value=value,
attn_bias=attn_bias,
p=p,
scale=scale,
op=op,
)
xformers.ops.memory_efficient_attention = new_memory_efficient_attention

4
invokeai/backend/util/mps_fixes.py
View File

@ -1,7 +1,7 @@
import math
import torch
import diffusers
import diffusers
import torch
if torch.backends.mps.is_available():
torch.empty = torch.zeros