File size: 10,335 Bytes
40440d6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 | # Flux project: https://github.com/black-forest-labs/flux/blob/main/src/flux/modules/autoencoder.py
from dataclasses import dataclass
import torch
from einops import rearrange
from torch import Tensor, nn
@dataclass
class AutoEncoderParams:
resolution: int
in_channels: int
ch: int
out_ch: int
ch_mult: list[int]
num_res_blocks: int
z_channels: int
scale_factor: float
shift_factor: float
def swish(x: Tensor) -> Tensor:
return x * torch.sigmoid(x)
class AttnBlock(nn.Module):
def __init__(self, in_channels: int):
super().__init__()
self.in_channels = in_channels
self.norm = nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)
self.q = nn.Conv2d(in_channels, in_channels, kernel_size=1)
self.k = nn.Conv2d(in_channels, in_channels, kernel_size=1)
self.v = nn.Conv2d(in_channels, in_channels, kernel_size=1)
self.proj_out = nn.Conv2d(in_channels, in_channels, kernel_size=1)
def attention(self, h_: Tensor) -> Tensor:
h_ = self.norm(h_)
q = self.q(h_)
k = self.k(h_)
v = self.v(h_)
b, c, h, w = q.shape
q = rearrange(q, "b c h w -> b 1 (h w) c").contiguous()
k = rearrange(k, "b c h w -> b 1 (h w) c").contiguous()
v = rearrange(v, "b c h w -> b 1 (h w) c").contiguous()
h_ = nn.functional.scaled_dot_product_attention(q, k, v)
return rearrange(h_, "b 1 (h w) c -> b c h w", h=h, w=w, c=c, b=b)
def forward(self, x: Tensor) -> Tensor:
return x + self.proj_out(self.attention(x))
class ResnetBlock(nn.Module):
def __init__(self, in_channels: int, out_channels: int):
super().__init__()
self.in_channels = in_channels
out_channels = in_channels if out_channels is None else out_channels
self.out_channels = out_channels
self.norm1 = nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)
self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=1, padding=1)
self.norm2 = nn.GroupNorm(num_groups=32, num_channels=out_channels, eps=1e-6, affine=True)
self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1)
if self.in_channels != self.out_channels:
self.nin_shortcut = nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=1, padding=0)
def forward(self, x):
h = x
h = self.norm1(h)
h = swish(h)
h = self.conv1(h)
h = self.norm2(h)
h = swish(h)
h = self.conv2(h)
if self.in_channels != self.out_channels:
x = self.nin_shortcut(x)
return x + h
class Downsample(nn.Module):
def __init__(self, in_channels: int):
super().__init__()
self.conv = nn.Conv2d(in_channels, in_channels, kernel_size=3, stride=2, padding=0)
def forward(self, x: Tensor):
pad = (0, 1, 0, 1)
x = nn.functional.pad(x, pad, mode="constant", value=0)
x = self.conv(x)
return x
class Upsample(nn.Module):
def __init__(self, in_channels: int):
super().__init__()
self.conv = nn.Conv2d(in_channels, in_channels, kernel_size=3, stride=1, padding=1)
def forward(self, x: Tensor):
x = nn.functional.interpolate(x, scale_factor=2.0, mode="nearest")
x = self.conv(x)
return x
class Encoder(nn.Module):
def __init__(self, resolution: int, in_channels: int, ch: int, ch_mult: list[int], num_res_blocks: int, z_channels: int):
super().__init__()
self.ch = ch
self.num_resolutions = len(ch_mult)
self.num_res_blocks = num_res_blocks
self.resolution = resolution
self.in_channels = in_channels
self.conv_in = nn.Conv2d(in_channels, self.ch, kernel_size=3, stride=1, padding=1)
curr_res = resolution
in_ch_mult = (1,) + tuple(ch_mult)
self.in_ch_mult = in_ch_mult
self.down = nn.ModuleList()
block_in = self.ch
for i_level in range(self.num_resolutions):
block = nn.ModuleList()
attn = nn.ModuleList()
block_in = ch * in_ch_mult[i_level]
block_out = ch * ch_mult[i_level]
for _ in range(self.num_res_blocks):
block.append(ResnetBlock(in_channels=block_in, out_channels=block_out))
block_in = block_out
down = nn.Module()
down.block = block
down.attn = attn
if i_level != self.num_resolutions - 1:
down.downsample = Downsample(block_in)
curr_res = curr_res // 2
self.down.append(down)
self.mid = nn.Module()
self.mid.block_1 = ResnetBlock(in_channels=block_in, out_channels=block_in)
self.mid.attn_1 = AttnBlock(block_in)
self.mid.block_2 = ResnetBlock(in_channels=block_in, out_channels=block_in)
self.norm_out = nn.GroupNorm(num_groups=32, num_channels=block_in, eps=1e-6, affine=True)
self.conv_out = nn.Conv2d(block_in, 2 * z_channels, kernel_size=3, stride=1, padding=1)
def forward(self, x: Tensor) -> Tensor:
hs = [self.conv_in(x)]
for i_level in range(self.num_resolutions):
for i_block in range(self.num_res_blocks):
h = self.down[i_level].block[i_block](hs[-1])
if len(self.down[i_level].attn) > 0:
h = self.down[i_level].attn[i_block](h)
hs.append(h)
if i_level != self.num_resolutions - 1:
hs.append(self.down[i_level].downsample(hs[-1]))
h = hs[-1]
h = self.mid.block_1(h)
h = self.mid.attn_1(h)
h = self.mid.block_2(h)
h = self.norm_out(h)
h = swish(h)
h = self.conv_out(h)
return h
class Decoder(nn.Module):
def __init__(self, ch: int, out_ch: int, ch_mult: list[int], num_res_blocks: int, in_channels: int, resolution: int, z_channels: int):
super().__init__()
self.ch = ch
self.num_resolutions = len(ch_mult)
self.num_res_blocks = num_res_blocks
self.resolution = resolution
self.in_channels = in_channels
self.ffactor = 2 ** (self.num_resolutions - 1)
block_in = ch * ch_mult[self.num_resolutions - 1]
curr_res = resolution // 2 ** (self.num_resolutions - 1)
self.z_shape = (1, z_channels, curr_res, curr_res)
self.conv_in = nn.Conv2d(z_channels, block_in, kernel_size=3, stride=1, padding=1)
self.mid = nn.Module()
self.mid.block_1 = ResnetBlock(in_channels=block_in, out_channels=block_in)
self.mid.attn_1 = AttnBlock(block_in)
self.mid.block_2 = ResnetBlock(in_channels=block_in, out_channels=block_in)
self.up = nn.ModuleList()
for i_level in reversed(range(self.num_resolutions)):
block = nn.ModuleList()
attn = nn.ModuleList()
block_out = ch * ch_mult[i_level]
for _ in range(self.num_res_blocks + 1):
block.append(ResnetBlock(in_channels=block_in, out_channels=block_out))
block_in = block_out
up = nn.Module()
up.block = block
up.attn = attn
if i_level != 0:
up.upsample = Upsample(block_in)
curr_res = curr_res * 2
self.up.insert(0, up)
self.norm_out = nn.GroupNorm(num_groups=32, num_channels=block_in, eps=1e-6, affine=True)
self.conv_out = nn.Conv2d(block_in, out_ch, kernel_size=3, stride=1, padding=1)
def forward(self, z: Tensor) -> Tensor:
upscale_dtype = next(self.up.parameters()).dtype
h = self.conv_in(z)
h = self.mid.block_1(h)
h = self.mid.attn_1(h)
h = self.mid.block_2(h)
h = h.to(upscale_dtype)
for i_level in reversed(range(self.num_resolutions)):
for i_block in range(self.num_res_blocks + 1):
h = self.up[i_level].block[i_block](h)
if len(self.up[i_level].attn) > 0:
h = self.up[i_level].attn[i_block](h)
if i_level != 0:
h = self.up[i_level].upsample(h)
h = self.norm_out(h)
h = swish(h)
h = self.conv_out(h)
return h
class DiagonalGaussian(nn.Module):
def __init__(self, sample: bool = True, chunk_dim: int = 1):
super().__init__()
self.sample = sample
self.chunk_dim = chunk_dim
def forward(self, z: Tensor) -> Tensor:
mean, logvar = torch.chunk(z, 2, dim=self.chunk_dim)
if self.sample:
std = torch.exp(0.5 * logvar)
return mean + std * torch.randn_like(mean)
else:
return mean
class AutoEncoder(nn.Module):
def __init__(self, params: AutoEncoderParams, sample_z: bool = False):
super().__init__()
self.params = params
self.encoder = Encoder(
resolution=params.resolution,
in_channels=params.in_channels,
ch=params.ch,
ch_mult=params.ch_mult,
num_res_blocks=params.num_res_blocks,
z_channels=params.z_channels,
)
self.decoder = Decoder(
resolution=params.resolution,
in_channels=params.in_channels,
ch=params.ch,
out_ch=params.out_ch,
ch_mult=params.ch_mult,
num_res_blocks=params.num_res_blocks,
z_channels=params.z_channels,
)
self.reg = DiagonalGaussian(sample=sample_z)
self.scale_factor = params.scale_factor
self.shift_factor = params.shift_factor
def encode(self, x: Tensor) -> Tensor:
z = self.reg(self.encoder(x))
z = self.scale_factor * (z - self.shift_factor)
return z
def decode(self, z: Tensor) -> Tensor:
z = z / self.scale_factor + self.shift_factor
return self.decoder(z)
def forward(self, x: Tensor) -> Tensor:
return self.decode(self.encode(x)) |