|
|
|
""" |
|
Tiny AutoEncoder for Stable Diffusion |
|
(DNN for encoding / decoding SD's latent space) |
|
""" |
|
import torch |
|
import torch.nn as nn |
|
|
|
def conv(n_in, n_out, **kwargs): |
|
return nn.Conv2d(n_in, n_out, 3, padding=1, **kwargs) |
|
|
|
class Clamp(nn.Module): |
|
def forward(self, x): |
|
return torch.tanh(x / 3) * 3 |
|
|
|
class Block(nn.Module): |
|
def __init__(self, n_in, n_out): |
|
super().__init__() |
|
self.conv = nn.Sequential(conv(n_in, n_out), nn.ReLU(), conv(n_out, n_out), nn.ReLU(), conv(n_out, n_out)) |
|
self.skip = nn.Conv2d(n_in, n_out, 1, bias=False) if n_in != n_out else nn.Identity() |
|
self.fuse = nn.ReLU() |
|
def forward(self, x): |
|
return self.fuse(self.conv(x) + self.skip(x)) |
|
|
|
def Encoder(): |
|
return nn.Sequential( |
|
conv(3, 64), Block(64, 64), |
|
conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64), |
|
conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64), |
|
conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64), |
|
conv(64, 4), |
|
) |
|
|
|
def Decoder(): |
|
return nn.Sequential( |
|
Clamp(), conv(4, 64), nn.ReLU(), |
|
Block(64, 64), Block(64, 64), Block(64, 64), nn.Upsample(scale_factor=2), conv(64, 64, bias=False), |
|
Block(64, 64), Block(64, 64), Block(64, 64), nn.Upsample(scale_factor=2), conv(64, 64, bias=False), |
|
Block(64, 64), Block(64, 64), Block(64, 64), nn.Upsample(scale_factor=2), conv(64, 64, bias=False), |
|
Block(64, 64), conv(64, 3), |
|
) |
|
|
|
class TAESD(nn.Module): |
|
latent_magnitude = 3 |
|
latent_shift = 0.5 |
|
|
|
def __init__(self, encoder_path="taesd_encoder.pth", decoder_path="taesd_decoder.pth"): |
|
"""Initialize pretrained TAESD on the given device from the given checkpoints.""" |
|
super().__init__() |
|
self.encoder = Encoder() |
|
self.decoder = Decoder() |
|
if encoder_path is not None: |
|
self.encoder.load_state_dict(torch.load(encoder_path, map_location="cpu", weights_only=True)) |
|
if decoder_path is not None: |
|
self.decoder.load_state_dict(torch.load(decoder_path, map_location="cpu", weights_only=True)) |
|
|
|
@staticmethod |
|
def scale_latents(x): |
|
"""raw latents -> [0, 1]""" |
|
return x.div(2 * TAESD.latent_magnitude).add(TAESD.latent_shift).clamp(0, 1) |
|
|
|
@staticmethod |
|
def unscale_latents(x): |
|
"""[0, 1] -> raw latents""" |
|
return x.sub(TAESD.latent_shift).mul(2 * TAESD.latent_magnitude) |
|
|
