sd-webui-controlnet/scripts/adapter.py

250 lines
7.7 KiB
Python

import torch
import torch.nn as nn
from omegaconf import OmegaConf
from copy import deepcopy
from modules import devices, lowvram, shared, scripts
from ldm.modules.diffusionmodules.util import timestep_embedding
from ldm.modules.diffusionmodules.openaimodel import UNetModel
class TorchHijackForUnet:
"""
This is torch, but with cat that resizes tensors to appropriate dimensions if they do not match;
this makes it possible to create pictures with dimensions that are multiples of 8 rather than 64
"""
def __getattr__(self, item):
if item == 'cat':
return self.cat
if hasattr(torch, item):
return getattr(torch, item)
raise AttributeError("'{}' object has no attribute '{}'".format(type(self).__name__, item))
def cat(self, tensors, *args, **kwargs):
if len(tensors) == 2:
a, b = tensors
if a.shape[-2:] != b.shape[-2:]:
a = torch.nn.functional.interpolate(a, b.shape[-2:], mode="nearest")
tensors = (a, b)
return torch.cat(tensors, *args, **kwargs)
th = TorchHijackForUnet()
def align(hint, size):
b, c, h1, w1 = hint.shape
h, w = size
if h != h1 or w != w1:
hint = th.nn.functional.interpolate(hint, size=size, mode="nearest")
return hint
def get_node_name(name, parent_name):
if len(name) <= len(parent_name):
return False, ''
p = name[:len(parent_name)]
if p != parent_name:
return False, ''
return True, name[len(parent_name):]
class PlugableAdapter(nn.Module):
def __init__(self, state_dict, config_path, lowvram=False, base_model=None) -> None:
super().__init__()
config = OmegaConf.load(config_path)
self.control_model = Adapter(**config.model.params)
self.control_model.load_state_dict(state_dict)
self.lowvram = lowvram
self.control = None
self.hint_cond = None
if not self.lowvram:
self.control_model.to(devices.get_device_for("controlnet"))
def reset(self):
self.control = None
self.hint_cond = None
def forward(self, hint=None, *args, **kwargs):
if self.control is not None:
return deepcopy(self.control)
self.hint_cond = hint
hint_in = hint
if self.control_model.conv_in.in_channels == 64:
hint_in = hint_in[0].unsqueeze(0).unsqueeze(0)
else:
hint_in = hint_in.unsqueeze(0)
self.control = self.control_model(hint_in)
return deepcopy(self.control)
def conv_nd(dims, *args, **kwargs):
"""
Create a 1D, 2D, or 3D convolution module.
"""
if dims == 1:
return nn.Conv1d(*args, **kwargs)
elif dims == 2:
return nn.Conv2d(*args, **kwargs)
elif dims == 3:
return nn.Conv3d(*args, **kwargs)
raise ValueError(f"unsupported dimensions: {dims}")
def avg_pool_nd(dims, *args, **kwargs):
"""
Create a 1D, 2D, or 3D average pooling module.
"""
if dims == 1:
return nn.AvgPool1d(*args, **kwargs)
elif dims == 2:
return nn.AvgPool2d(*args, **kwargs)
elif dims == 3:
return nn.AvgPool3d(*args, **kwargs)
raise ValueError(f"unsupported dimensions: {dims}")
class Downsample(nn.Module):
"""
A downsampling layer with an optional convolution.
:param channels: channels in the inputs and outputs.
:param use_conv: a bool determining if a convolution is applied.
:param dims: determines if the signal is 1D, 2D, or 3D. If 3D, then
downsampling occurs in the inner-two dimensions.
"""
def __init__(self, channels, use_conv, dims=2, out_channels=None,padding=1):
super().__init__()
self.channels = channels
self.out_channels = out_channels or channels
self.use_conv = use_conv
self.dims = dims
stride = 2 if dims != 3 else (1, 2, 2)
if use_conv:
self.op = conv_nd(
dims, self.channels, self.out_channels, 3, stride=stride, padding=padding
)
else:
assert self.channels == self.out_channels
self.op = avg_pool_nd(dims, kernel_size=stride, stride=stride)
def forward(self, x):
assert x.shape[1] == self.channels
return self.op(x)
class ResnetBlock(nn.Module):
def __init__(self, in_c, out_c, down, ksize=3, sk=False, use_conv=True):
super().__init__()
ps = ksize//2
if in_c != out_c or sk==False:
self.in_conv = nn.Conv2d(in_c, out_c, ksize, 1, ps)
else:
# print('n_in')
self.in_conv = None
self.block1 = nn.Conv2d(out_c, out_c, 3, 1, 1)
self.act = nn.ReLU()
self.block2 = nn.Conv2d(out_c, out_c, ksize, 1, ps)
if sk==False:
self.skep = nn.Conv2d(in_c, out_c, ksize, 1, ps)
else:
# print('n_sk')
self.skep = None
self.down = down
if self.down == True:
self.down_opt = Downsample(in_c, use_conv=use_conv)
def forward(self, x):
if self.down == True:
x = self.down_opt(x)
if self.in_conv is not None: # edit
h = self.in_conv(x)
# x = self.in_conv(x)
# else:
# x = x
h = self.block1(h)
h = self.act(h)
h = self.block2(h)
if self.skep is not None:
return h + self.skep(x)
else:
return h + x
class ResnetBlock(nn.Module):
def __init__(self, in_c, out_c, down, ksize=3, sk=False, use_conv=True):
super().__init__()
ps = ksize//2
if in_c != out_c or sk==False:
self.in_conv = nn.Conv2d(in_c, out_c, ksize, 1, ps)
else:
# print('n_in')
self.in_conv = None
self.block1 = nn.Conv2d(out_c, out_c, 3, 1, 1)
self.act = nn.ReLU()
self.block2 = nn.Conv2d(out_c, out_c, ksize, 1, ps)
if sk==False:
self.skep = nn.Conv2d(in_c, out_c, ksize, 1, ps)
else:
self.skep = None
self.down = down
if self.down == True:
self.down_opt = Downsample(in_c, use_conv=use_conv)
def forward(self, x):
if self.down == True:
x = self.down_opt(x)
if self.in_conv is not None: # edit
x = self.in_conv(x)
h = self.block1(x)
h = self.act(h)
h = self.block2(h)
if self.skep is not None:
return h + self.skep(x)
else:
return h + x
class Adapter(nn.Module):
def __init__(self, channels=[320, 640, 1280, 1280], nums_rb=3, cin=64, ksize=3, sk=False, use_conv=True):
super(Adapter, self).__init__()
self.unshuffle = nn.PixelUnshuffle(8)
self.channels = channels
self.nums_rb = nums_rb
self.body = []
for i in range(len(channels)):
for j in range(nums_rb):
if (i!=0) and (j==0):
self.body.append(ResnetBlock(channels[i-1], channels[i], down=True, ksize=ksize, sk=sk, use_conv=use_conv))
else:
self.body.append(ResnetBlock(channels[i], channels[i], down=False, ksize=ksize, sk=sk, use_conv=use_conv))
self.body = nn.ModuleList(self.body)
self.conv_in = nn.Conv2d(cin, channels[0], 3, 1, 1)
def forward(self, x):
# unshuffle
x = self.unshuffle(x)
# extract features
features = []
x = self.conv_in(x)
for i in range(len(self.channels)):
for j in range(self.nums_rb):
idx = i*self.nums_rb +j
x = self.body[idx](x)
features.append(x)
return features