Unverified Commit a39a57cb authored by Zac Liu's avatar Zac Liu Committed by GitHub

Merge pull request #1 from 920232796/master

Add AltDiffusion
parents 4b3c5bc2 0831ab47
model:
base_learning_rate: 1.0e-04
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false # Note: different from the one we trained before
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 10000 ]
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
f_start: [ 1.e-6 ]
f_max: [ 1. ]
f_min: [ 1. ]
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
image_size: 32 # unused
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_heads: 8
use_spatial_transformer: True
transformer_depth: 1
context_dim: 768
use_checkpoint: True
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.xlmr.BertSeriesModelWithTransformation
params:
name: "XLMR-Large"
\ No newline at end of file
from abc import abstractmethod
from torch.utils.data import Dataset, ConcatDataset, ChainDataset, IterableDataset
class Txt2ImgIterableBaseDataset(IterableDataset):
'''
Define an interface to make the IterableDatasets for text2img data chainable
'''
def __init__(self, num_records=0, valid_ids=None, size=256):
super().__init__()
self.num_records = num_records
self.valid_ids = valid_ids
self.sample_ids = valid_ids
self.size = size
print(f'{self.__class__.__name__} dataset contains {self.__len__()} examples.')
def __len__(self):
return self.num_records
@abstractmethod
def __iter__(self):
pass
\ No newline at end of file
This diff is collapsed.
import os
import numpy as np
import PIL
from PIL import Image
from torch.utils.data import Dataset
from torchvision import transforms
class LSUNBase(Dataset):
def __init__(self,
txt_file,
data_root,
size=None,
interpolation="bicubic",
flip_p=0.5
):
self.data_paths = txt_file
self.data_root = data_root
with open(self.data_paths, "r") as f:
self.image_paths = f.read().splitlines()
self._length = len(self.image_paths)
self.labels = {
"relative_file_path_": [l for l in self.image_paths],
"file_path_": [os.path.join(self.data_root, l)
for l in self.image_paths],
}
self.size = size
self.interpolation = {"linear": PIL.Image.LINEAR,
"bilinear": PIL.Image.BILINEAR,
"bicubic": PIL.Image.BICUBIC,
"lanczos": PIL.Image.LANCZOS,
}[interpolation]
self.flip = transforms.RandomHorizontalFlip(p=flip_p)
def __len__(self):
return self._length
def __getitem__(self, i):
example = dict((k, self.labels[k][i]) for k in self.labels)
image = Image.open(example["file_path_"])
if not image.mode == "RGB":
image = image.convert("RGB")
# default to score-sde preprocessing
img = np.array(image).astype(np.uint8)
crop = min(img.shape[0], img.shape[1])
h, w, = img.shape[0], img.shape[1]
img = img[(h - crop) // 2:(h + crop) // 2,
(w - crop) // 2:(w + crop) // 2]
image = Image.fromarray(img)
if self.size is not None:
image = image.resize((self.size, self.size), resample=self.interpolation)
image = self.flip(image)
image = np.array(image).astype(np.uint8)
example["image"] = (image / 127.5 - 1.0).astype(np.float32)
return example
class LSUNChurchesTrain(LSUNBase):
def __init__(self, **kwargs):
super().__init__(txt_file="data/lsun/church_outdoor_train.txt", data_root="data/lsun/churches", **kwargs)
class LSUNChurchesValidation(LSUNBase):
def __init__(self, flip_p=0., **kwargs):
super().__init__(txt_file="data/lsun/church_outdoor_val.txt", data_root="data/lsun/churches",
flip_p=flip_p, **kwargs)
class LSUNBedroomsTrain(LSUNBase):
def __init__(self, **kwargs):
super().__init__(txt_file="data/lsun/bedrooms_train.txt", data_root="data/lsun/bedrooms", **kwargs)
class LSUNBedroomsValidation(LSUNBase):
def __init__(self, flip_p=0.0, **kwargs):
super().__init__(txt_file="data/lsun/bedrooms_val.txt", data_root="data/lsun/bedrooms",
flip_p=flip_p, **kwargs)
class LSUNCatsTrain(LSUNBase):
def __init__(self, **kwargs):
super().__init__(txt_file="data/lsun/cat_train.txt", data_root="data/lsun/cats", **kwargs)
class LSUNCatsValidation(LSUNBase):
def __init__(self, flip_p=0., **kwargs):
super().__init__(txt_file="data/lsun/cat_val.txt", data_root="data/lsun/cats",
flip_p=flip_p, **kwargs)
import numpy as np
class LambdaWarmUpCosineScheduler:
"""
note: use with a base_lr of 1.0
"""
def __init__(self, warm_up_steps, lr_min, lr_max, lr_start, max_decay_steps, verbosity_interval=0):
self.lr_warm_up_steps = warm_up_steps
self.lr_start = lr_start
self.lr_min = lr_min
self.lr_max = lr_max
self.lr_max_decay_steps = max_decay_steps
self.last_lr = 0.
self.verbosity_interval = verbosity_interval
def schedule(self, n, **kwargs):
if self.verbosity_interval > 0:
if n % self.verbosity_interval == 0: print(f"current step: {n}, recent lr-multiplier: {self.last_lr}")
if n < self.lr_warm_up_steps:
lr = (self.lr_max - self.lr_start) / self.lr_warm_up_steps * n + self.lr_start
self.last_lr = lr
return lr
else:
t = (n - self.lr_warm_up_steps) / (self.lr_max_decay_steps - self.lr_warm_up_steps)
t = min(t, 1.0)
lr = self.lr_min + 0.5 * (self.lr_max - self.lr_min) * (
1 + np.cos(t * np.pi))
self.last_lr = lr
return lr
def __call__(self, n, **kwargs):
return self.schedule(n,**kwargs)
class LambdaWarmUpCosineScheduler2:
"""
supports repeated iterations, configurable via lists
note: use with a base_lr of 1.0.
"""
def __init__(self, warm_up_steps, f_min, f_max, f_start, cycle_lengths, verbosity_interval=0):
assert len(warm_up_steps) == len(f_min) == len(f_max) == len(f_start) == len(cycle_lengths)
self.lr_warm_up_steps = warm_up_steps
self.f_start = f_start
self.f_min = f_min
self.f_max = f_max
self.cycle_lengths = cycle_lengths
self.cum_cycles = np.cumsum([0] + list(self.cycle_lengths))
self.last_f = 0.
self.verbosity_interval = verbosity_interval
def find_in_interval(self, n):
interval = 0
for cl in self.cum_cycles[1:]:
if n <= cl:
return interval
interval += 1
def schedule(self, n, **kwargs):
cycle = self.find_in_interval(n)
n = n - self.cum_cycles[cycle]
if self.verbosity_interval > 0:
if n % self.verbosity_interval == 0: print(f"current step: {n}, recent lr-multiplier: {self.last_f}, "
f"current cycle {cycle}")
if n < self.lr_warm_up_steps[cycle]:
f = (self.f_max[cycle] - self.f_start[cycle]) / self.lr_warm_up_steps[cycle] * n + self.f_start[cycle]
self.last_f = f
return f
else:
t = (n - self.lr_warm_up_steps[cycle]) / (self.cycle_lengths[cycle] - self.lr_warm_up_steps[cycle])
t = min(t, 1.0)
f = self.f_min[cycle] + 0.5 * (self.f_max[cycle] - self.f_min[cycle]) * (
1 + np.cos(t * np.pi))
self.last_f = f
return f
def __call__(self, n, **kwargs):
return self.schedule(n, **kwargs)
class LambdaLinearScheduler(LambdaWarmUpCosineScheduler2):
def schedule(self, n, **kwargs):
cycle = self.find_in_interval(n)
n = n - self.cum_cycles[cycle]
if self.verbosity_interval > 0:
if n % self.verbosity_interval == 0: print(f"current step: {n}, recent lr-multiplier: {self.last_f}, "
f"current cycle {cycle}")
if n < self.lr_warm_up_steps[cycle]:
f = (self.f_max[cycle] - self.f_start[cycle]) / self.lr_warm_up_steps[cycle] * n + self.f_start[cycle]
self.last_f = f
return f
else:
f = self.f_min[cycle] + (self.f_max[cycle] - self.f_min[cycle]) * (self.cycle_lengths[cycle] - n) / (self.cycle_lengths[cycle])
self.last_f = f
return f
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
from .sampler import DPMSolverSampler
\ No newline at end of file
This diff is collapsed.
"""SAMPLING ONLY."""
import torch
from .dpm_solver import NoiseScheduleVP, model_wrapper, DPM_Solver
class DPMSolverSampler(object):
def __init__(self, model, **kwargs):
super().__init__()
self.model = model
to_torch = lambda x: x.clone().detach().to(torch.float32).to(model.device)
self.register_buffer('alphas_cumprod', to_torch(model.alphas_cumprod))
def register_buffer(self, name, attr):
if type(attr) == torch.Tensor:
if attr.device != torch.device("cuda"):
attr = attr.to(torch.device("cuda"))
setattr(self, name, attr)
@torch.no_grad()
def sample(self,
S,
batch_size,
shape,
conditioning=None,
callback=None,
normals_sequence=None,
img_callback=None,
quantize_x0=False,
eta=0.,
mask=None,
x0=None,
temperature=1.,
noise_dropout=0.,
score_corrector=None,
corrector_kwargs=None,
verbose=True,
x_T=None,
log_every_t=100,
unconditional_guidance_scale=1.,
unconditional_conditioning=None,
# this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
**kwargs
):
if conditioning is not None:
if isinstance(conditioning, dict):
cbs = conditioning[list(conditioning.keys())[0]].shape[0]
if cbs != batch_size:
print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
else:
if conditioning.shape[0] != batch_size:
print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
# sampling
C, H, W = shape
size = (batch_size, C, H, W)
# print(f'Data shape for DPM-Solver sampling is {size}, sampling steps {S}')
device = self.model.betas.device
if x_T is None:
img = torch.randn(size, device=device)
else:
img = x_T
ns = NoiseScheduleVP('discrete', alphas_cumprod=self.alphas_cumprod)
model_fn = model_wrapper(
lambda x, t, c: self.model.apply_model(x, t, c),
ns,
model_type="noise",
guidance_type="classifier-free",
condition=conditioning,
unconditional_condition=unconditional_conditioning,
guidance_scale=unconditional_guidance_scale,
)
dpm_solver = DPM_Solver(model_fn, ns, predict_x0=True, thresholding=False)
x = dpm_solver.sample(img, steps=S, skip_type="time_uniform", method="multistep", order=2, lower_order_final=True)
return x.to(device), None
This diff is collapsed.
from inspect import isfunction
import math
import torch
import torch.nn.functional as F
from torch import nn, einsum
from einops import rearrange, repeat
from ldm.modules.diffusionmodules.util import checkpoint
def exists(val):
return val is not None
def uniq(arr):
return{el: True for el in arr}.keys()
def default(val, d):
if exists(val):
return val
return d() if isfunction(d) else d
def max_neg_value(t):
return -torch.finfo(t.dtype).max
def init_(tensor):
dim = tensor.shape[-1]
std = 1 / math.sqrt(dim)
tensor.uniform_(-std, std)
return tensor
# feedforward
class GEGLU(nn.Module):
def __init__(self, dim_in, dim_out):
super().__init__()
self.proj = nn.Linear(dim_in, dim_out * 2)
def forward(self, x):
x, gate = self.proj(x).chunk(2, dim=-1)
return x * F.gelu(gate)
class FeedForward(nn.Module):
def __init__(self, dim, dim_out=None, mult=4, glu=False, dropout=0.):
super().__init__()
inner_dim = int(dim * mult)
dim_out = default(dim_out, dim)
project_in = nn.Sequential(
nn.Linear(dim, inner_dim),
nn.GELU()
) if not glu else GEGLU(dim, inner_dim)
self.net = nn.Sequential(
project_in,
nn.Dropout(dropout),
nn.Linear(inner_dim, dim_out)
)
def forward(self, x):
return self.net(x)
def zero_module(module):
"""
Zero out the parameters of a module and return it.
"""
for p in module.parameters():
p.detach().zero_()
return module
def Normalize(in_channels):
return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)
class LinearAttention(nn.Module):
def __init__(self, dim, heads=4, dim_head=32):
super().__init__()
self.heads = heads
hidden_dim = dim_head * heads
self.to_qkv = nn.Conv2d(dim, hidden_dim * 3, 1, bias = False)
self.to_out = nn.Conv2d(hidden_dim, dim, 1)
def forward(self, x):
b, c, h, w = x.shape
qkv = self.to_qkv(x)
q, k, v = rearrange(qkv, 'b (qkv heads c) h w -> qkv b heads c (h w)', heads = self.heads, qkv=3)
k = k.softmax(dim=-1)
context = torch.einsum('bhdn,bhen->bhde', k, v)
out = torch.einsum('bhde,bhdn->bhen', context, q)
out = rearrange(out, 'b heads c (h w) -> b (heads c) h w', heads=self.heads, h=h, w=w)
return self.to_out(out)
class SpatialSelfAttention(nn.Module):
def __init__(self, in_channels):
super().__init__()
self.in_channels = in_channels
self.norm = Normalize(in_channels)
self.q = torch.nn.Conv2d(in_channels,
in_channels,
kernel_size=1,
stride=1,
padding=0)
self.k = torch.nn.Conv2d(in_channels,
in_channels,
kernel_size=1,
stride=1,
padding=0)
self.v = torch.nn.Conv2d(in_channels,
in_channels,
kernel_size=1,
stride=1,
padding=0)
self.proj_out = torch.nn.Conv2d(in_channels,
in_channels,
kernel_size=1,
stride=1,
padding=0)
def forward(self, x):
h_ = x
h_ = self.norm(h_)
q = self.q(h_)
k = self.k(h_)
v = self.v(h_)
# compute attention
b,c,h,w = q.shape
q = rearrange(q, 'b c h w -> b (h w) c')
k = rearrange(k, 'b c h w -> b c (h w)')
w_ = torch.einsum('bij,bjk->bik', q, k)
w_ = w_ * (int(c)**(-0.5))
w_ = torch.nn.functional.softmax(w_, dim=2)
# attend to values
v = rearrange(v, 'b c h w -> b c (h w)')
w_ = rearrange(w_, 'b i j -> b j i')
h_ = torch.einsum('bij,bjk->bik', v, w_)
h_ = rearrange(h_, 'b c (h w) -> b c h w', h=h)
h_ = self.proj_out(h_)
return x+h_
class CrossAttention(nn.Module):
def __init__(self, query_dim, context_dim=None, heads=8, dim_head=64, dropout=0.):
super().__init__()
inner_dim = dim_head * heads
context_dim = default(context_dim, query_dim)
self.scale = dim_head ** -0.5
self.heads = heads
self.to_q = nn.Linear(query_dim, inner_dim, bias=False)
self.to_k = nn.Linear(context_dim, inner_dim, bias=False)
self.to_v = nn.Linear(context_dim, inner_dim, bias=False)
self.to_out = nn.Sequential(
nn.Linear(inner_dim, query_dim),
nn.Dropout(dropout)
)
def forward(self, x, context=None, mask=None):
h = self.heads
q = self.to_q(x)
context = default(context, x)
k = self.to_k(context)
v = self.to_v(context)
q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v))
sim = einsum('b i d, b j d -> b i j', q, k) * self.scale
if exists(mask):
mask = rearrange(mask, 'b ... -> b (...)')
max_neg_value = -torch.finfo(sim.dtype).max
mask = repeat(mask, 'b j -> (b h) () j', h=h)
sim.masked_fill_(~mask, max_neg_value)
# attention, what we cannot get enough of
attn = sim.softmax(dim=-1)
out = einsum('b i j, b j d -> b i d', attn, v)
out = rearrange(out, '(b h) n d -> b n (h d)', h=h)
return self.to_out(out)
class BasicTransformerBlock(nn.Module):
def __init__(self, dim, n_heads, d_head, dropout=0., context_dim=None, gated_ff=True, checkpoint=True):
super().__init__()
self.attn1 = CrossAttention(query_dim=dim, heads=n_heads, dim_head=d_head, dropout=dropout) # is a self-attention
self.ff = FeedForward(dim, dropout=dropout, glu=gated_ff)
self.attn2 = CrossAttention(query_dim=dim, context_dim=context_dim,
heads=n_heads, dim_head=d_head, dropout=dropout) # is self-attn if context is none
self.norm1 = nn.LayerNorm(dim)
self.norm2 = nn.LayerNorm(dim)
self.norm3 = nn.LayerNorm(dim)
self.checkpoint = checkpoint
def forward(self, x, context=None):
return checkpoint(self._forward, (x, context), self.parameters(), self.checkpoint)
def _forward(self, x, context=None):
x = self.attn1(self.norm1(x)) + x
x = self.attn2(self.norm2(x), context=context) + x
x = self.ff(self.norm3(x)) + x
return x
class SpatialTransformer(nn.Module):
"""
Transformer block for image-like data.
First, project the input (aka embedding)
and reshape to b, t, d.
Then apply standard transformer action.
Finally, reshape to image
"""
def __init__(self, in_channels, n_heads, d_head,
depth=1, dropout=0., context_dim=None):
super().__init__()
self.in_channels = in_channels
inner_dim = n_heads * d_head
self.norm = Normalize(in_channels)
self.proj_in = nn.Conv2d(in_channels,
inner_dim,
kernel_size=1,
stride=1,
padding=0)
self.transformer_blocks = nn.ModuleList(
[BasicTransformerBlock(inner_dim, n_heads, d_head, dropout=dropout, context_dim=context_dim)
for d in range(depth)]
)
self.proj_out = zero_module(nn.Conv2d(inner_dim,
in_channels,
kernel_size=1,
stride=1,
padding=0))
def forward(self, x, context=None):
# note: if no context is given, cross-attention defaults to self-attention
b, c, h, w = x.shape
x_in = x
x = self.norm(x)
x = self.proj_in(x)
x = rearrange(x, 'b c h w -> b (h w) c')
for block in self.transformer_blocks:
x = block(x, context=context)
x = rearrange(x, 'b (h w) c -> b c h w', h=h, w=w)
x = self.proj_out(x)
return x + x_in
\ No newline at end of file
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
import torch
import numpy as np
class AbstractDistribution:
def sample(self):
raise NotImplementedError()
def mode(self):
raise NotImplementedError()
class DiracDistribution(AbstractDistribution):
def __init__(self, value):
self.value = value
def sample(self):
return self.value
def mode(self):
return self.value
class DiagonalGaussianDistribution(object):
def __init__(self, parameters, deterministic=False):
self.parameters = parameters
self.mean, self.logvar = torch.chunk(parameters, 2, dim=1)
self.logvar = torch.clamp(self.logvar, -30.0, 20.0)
self.deterministic = deterministic
self.std = torch.exp(0.5 * self.logvar)
self.var = torch.exp(self.logvar)
if self.deterministic:
self.var = self.std = torch.zeros_like(self.mean).to(device=self.parameters.device)
def sample(self):
x = self.mean + self.std * torch.randn(self.mean.shape).to(device=self.parameters.device)
return x
def kl(self, other=None):
if self.deterministic:
return torch.Tensor([0.])
else:
if other is None:
return 0.5 * torch.sum(torch.pow(self.mean, 2)
+ self.var - 1.0 - self.logvar,
dim=[1, 2, 3])
else:
return 0.5 * torch.sum(
torch.pow(self.mean - other.mean, 2) / other.var
+ self.var / other.var - 1.0 - self.logvar + other.logvar,
dim=[1, 2, 3])
def nll(self, sample, dims=[1,2,3]):
if self.deterministic:
return torch.Tensor([0.])
logtwopi = np.log(2.0 * np.pi)
return 0.5 * torch.sum(
logtwopi + self.logvar + torch.pow(sample - self.mean, 2) / self.var,
dim=dims)
def mode(self):
return self.mean
def normal_kl(mean1, logvar1, mean2, logvar2):
"""
source: https://github.com/openai/guided-diffusion/blob/27c20a8fab9cb472df5d6bdd6c8d11c8f430b924/guided_diffusion/losses.py#L12
Compute the KL divergence between two gaussians.
Shapes are automatically broadcasted, so batches can be compared to
scalars, among other use cases.
"""
tensor = None
for obj in (mean1, logvar1, mean2, logvar2):
if isinstance(obj, torch.Tensor):
tensor = obj
break
assert tensor is not None, "at least one argument must be a Tensor"
# Force variances to be Tensors. Broadcasting helps convert scalars to
# Tensors, but it does not work for torch.exp().
logvar1, logvar2 = [
x if isinstance(x, torch.Tensor) else torch.tensor(x).to(tensor)
for x in (logvar1, logvar2)
]
return 0.5 * (
-1.0
+ logvar2
- logvar1
+ torch.exp(logvar1 - logvar2)
+ ((mean1 - mean2) ** 2) * torch.exp(-logvar2)
)
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
from ldm.modules.image_degradation.bsrgan import degradation_bsrgan_variant as degradation_fn_bsr
from ldm.modules.image_degradation.bsrgan_light import degradation_bsrgan_variant as degradation_fn_bsr_light
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
from ldm.modules.losses.contperceptual import LPIPSWithDiscriminator
\ No newline at end of file
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
...@@ -38,8 +38,8 @@ def get_optimal_device(): ...@@ -38,8 +38,8 @@ def get_optimal_device():
if torch.cuda.is_available(): if torch.cuda.is_available():
return torch.device(get_cuda_device_string()) return torch.device(get_cuda_device_string())
if has_mps(): # if has_mps():
return torch.device("mps") # return torch.device("mps")
return cpu return cpu
......
...@@ -81,17 +81,23 @@ class StableDiffusionModelHijack: ...@@ -81,17 +81,23 @@ class StableDiffusionModelHijack:
embedding_db = modules.textual_inversion.textual_inversion.EmbeddingDatabase(cmd_opts.embeddings_dir) embedding_db = modules.textual_inversion.textual_inversion.EmbeddingDatabase(cmd_opts.embeddings_dir)
def hijack(self, m): def hijack(self, m):
if type(m.cond_stage_model) == ldm.modules.encoders.modules.FrozenCLIPEmbedder: if type(m.cond_stage_model) == ldm.modules.encoders.modules.FrozenCLIPEmbedder:
model_embeddings = m.cond_stage_model.transformer.text_model.embeddings model_embeddings = m.cond_stage_model.transformer.text_model.embeddings
model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.token_embedding, self) model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.token_embedding, self)
m.cond_stage_model = sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords(m.cond_stage_model, self) m.cond_stage_model = sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords(m.cond_stage_model, self)
apply_optimizations()
elif type(m.cond_stage_model) == ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder: elif type(m.cond_stage_model) == ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder:
m.cond_stage_model.model.token_embedding = EmbeddingsWithFixes(m.cond_stage_model.model.token_embedding, self) m.cond_stage_model.model.token_embedding = EmbeddingsWithFixes(m.cond_stage_model.model.token_embedding, self)
m.cond_stage_model = sd_hijack_open_clip.FrozenOpenCLIPEmbedderWithCustomWords(m.cond_stage_model, self) m.cond_stage_model = sd_hijack_open_clip.FrozenOpenCLIPEmbedderWithCustomWords(m.cond_stage_model, self)
apply_optimizations()
elif shared.text_model_name == "XLMR-Large":
model_embeddings = m.cond_stage_model.roberta.embeddings
model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.word_embeddings, self)
m.cond_stage_model = sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords(m.cond_stage_model, self)
self.clip = m.cond_stage_model self.clip = m.cond_stage_model
apply_optimizations()
fix_checkpoint() fix_checkpoint()
def flatten(el): def flatten(el):
...@@ -132,8 +138,8 @@ class StableDiffusionModelHijack: ...@@ -132,8 +138,8 @@ class StableDiffusionModelHijack:
def tokenize(self, text): def tokenize(self, text):
_, remade_batch_tokens, _, _, _, token_count = self.clip.process_text([text]) _, remade_batch_tokens, _, _, _, token_count = self.clip.process_text([text])
return remade_batch_tokens[0], token_count, sd_hijack_clip.get_target_prompt_token_count(token_count)
return remade_batch_tokens[0], token_count, sd_hijack_clip.get_target_prompt_token_count(token_count)
class EmbeddingsWithFixes(torch.nn.Module): class EmbeddingsWithFixes(torch.nn.Module):
......
This diff is collapsed.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment