diff options
Diffstat (limited to 'modules')
26 files changed, 215 insertions, 213 deletions
diff --git a/modules/api/api.py b/modules/api/api.py index 594fa655..165985c3 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -227,7 +227,7 @@ class Api: script_idx = script_name_to_index(script_name, script_runner.selectable_scripts) script = script_runner.selectable_scripts[script_idx] return script, script_idx - + def get_scripts_list(self): t2ilist = [str(title.lower()) for title in scripts.scripts_txt2img.titles] i2ilist = [str(title.lower()) for title in scripts.scripts_img2img.titles] @@ -237,7 +237,7 @@ class Api: def get_script(self, script_name, script_runner): if script_name is None or script_name == "": return None, None - + script_idx = script_name_to_index(script_name, script_runner.scripts) return script_runner.scripts[script_idx] diff --git a/modules/api/models.py b/modules/api/models.py index 4d291076..006ccdb7 100644 --- a/modules/api/models.py +++ b/modules/api/models.py @@ -289,4 +289,4 @@ class MemoryResponse(BaseModel): class ScriptsList(BaseModel): txt2img: list = Field(default=None,title="Txt2img", description="Titles of scripts (txt2img)") - img2img: list = Field(default=None,title="Img2img", description="Titles of scripts (img2img)")
\ No newline at end of file + img2img: list = Field(default=None,title="Img2img", description="Titles of scripts (img2img)") diff --git a/modules/cmd_args.py b/modules/cmd_args.py index e01ca655..f4a4ab36 100644 --- a/modules/cmd_args.py +++ b/modules/cmd_args.py @@ -102,4 +102,4 @@ parser.add_argument("--no-gradio-queue", action='store_true', help="Disables gra parser.add_argument("--skip-version-check", action='store_true', help="Do not check versions of torch and xformers")
parser.add_argument("--no-hashing", action='store_true', help="disable sha256 hashing of checkpoints to help loading performance", default=False)
parser.add_argument("--no-download-sd-model", action='store_true', help="don't download SD1.5 model even if no model is found in --ckpt-dir", default=False)
-parser.add_argument('--subpath', type=str, help='customize the subpath for gradio, use with reverse proxy')
\ No newline at end of file +parser.add_argument('--subpath', type=str, help='customize the subpath for gradio, use with reverse proxy')
diff --git a/modules/codeformer/codeformer_arch.py b/modules/codeformer/codeformer_arch.py index 45c70f84..12db6814 100644 --- a/modules/codeformer/codeformer_arch.py +++ b/modules/codeformer/codeformer_arch.py @@ -119,7 +119,7 @@ class TransformerSALayer(nn.Module): tgt_mask: Optional[Tensor] = None, tgt_key_padding_mask: Optional[Tensor] = None, query_pos: Optional[Tensor] = None): - + # self attention tgt2 = self.norm1(tgt) q = k = self.with_pos_embed(tgt2, query_pos) @@ -159,7 +159,7 @@ class Fuse_sft_block(nn.Module): @ARCH_REGISTRY.register() class CodeFormer(VQAutoEncoder): - def __init__(self, dim_embd=512, n_head=8, n_layers=9, + def __init__(self, dim_embd=512, n_head=8, n_layers=9, codebook_size=1024, latent_size=256, connect_list=('32', '64', '128', '256'), fix_modules=('quantize', 'generator')): @@ -179,14 +179,14 @@ class CodeFormer(VQAutoEncoder): self.feat_emb = nn.Linear(256, self.dim_embd) # transformer - self.ft_layers = nn.Sequential(*[TransformerSALayer(embed_dim=dim_embd, nhead=n_head, dim_mlp=self.dim_mlp, dropout=0.0) + self.ft_layers = nn.Sequential(*[TransformerSALayer(embed_dim=dim_embd, nhead=n_head, dim_mlp=self.dim_mlp, dropout=0.0) for _ in range(self.n_layers)]) # logits_predict head self.idx_pred_layer = nn.Sequential( nn.LayerNorm(dim_embd), nn.Linear(dim_embd, codebook_size, bias=False)) - + self.channels = { '16': 512, '32': 256, @@ -221,7 +221,7 @@ class CodeFormer(VQAutoEncoder): enc_feat_dict = {} out_list = [self.fuse_encoder_block[f_size] for f_size in self.connect_list] for i, block in enumerate(self.encoder.blocks): - x = block(x) + x = block(x) if i in out_list: enc_feat_dict[str(x.shape[-1])] = x.clone() @@ -266,11 +266,11 @@ class CodeFormer(VQAutoEncoder): fuse_list = [self.fuse_generator_block[f_size] for f_size in self.connect_list] for i, block in enumerate(self.generator.blocks): - x = block(x) + x = block(x) if i in fuse_list: # fuse after i-th block f_size = str(x.shape[-1]) if w>0: x = self.fuse_convs_dict[f_size](enc_feat_dict[f_size].detach(), x, w) out = x # logits doesn't need softmax before cross_entropy loss - return out, logits, lq_feat
\ No newline at end of file + return out, logits, lq_feat diff --git a/modules/codeformer/vqgan_arch.py b/modules/codeformer/vqgan_arch.py index b24a0394..09ee6660 100644 --- a/modules/codeformer/vqgan_arch.py +++ b/modules/codeformer/vqgan_arch.py @@ -13,7 +13,7 @@ from basicsr.utils.registry import ARCH_REGISTRY def normalize(in_channels): return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True) - + @torch.jit.script def swish(x): @@ -210,15 +210,15 @@ class AttnBlock(nn.Module): # compute attention b, c, h, w = q.shape q = q.reshape(b, c, h*w) - q = q.permute(0, 2, 1) + q = q.permute(0, 2, 1) k = k.reshape(b, c, h*w) - w_ = torch.bmm(q, k) + w_ = torch.bmm(q, k) w_ = w_ * (int(c)**(-0.5)) w_ = F.softmax(w_, dim=2) # attend to values v = v.reshape(b, c, h*w) - w_ = w_.permute(0, 2, 1) + w_ = w_.permute(0, 2, 1) h_ = torch.bmm(v, w_) h_ = h_.reshape(b, c, h, w) @@ -270,18 +270,18 @@ class Encoder(nn.Module): def forward(self, x): for block in self.blocks: x = block(x) - + return x class Generator(nn.Module): def __init__(self, nf, emb_dim, ch_mult, res_blocks, img_size, attn_resolutions): super().__init__() - self.nf = nf - self.ch_mult = ch_mult + self.nf = nf + self.ch_mult = ch_mult self.num_resolutions = len(self.ch_mult) self.num_res_blocks = res_blocks - self.resolution = img_size + self.resolution = img_size self.attn_resolutions = attn_resolutions self.in_channels = emb_dim self.out_channels = 3 @@ -315,24 +315,24 @@ class Generator(nn.Module): blocks.append(nn.Conv2d(block_in_ch, self.out_channels, kernel_size=3, stride=1, padding=1)) self.blocks = nn.ModuleList(blocks) - + def forward(self, x): for block in self.blocks: x = block(x) - + return x - + @ARCH_REGISTRY.register() class VQAutoEncoder(nn.Module): def __init__(self, img_size, nf, ch_mult, quantizer="nearest", res_blocks=2, attn_resolutions=None, codebook_size=1024, emb_dim=256, beta=0.25, gumbel_straight_through=False, gumbel_kl_weight=1e-8, model_path=None): super().__init__() logger = get_root_logger() - self.in_channels = 3 - self.nf = nf - self.n_blocks = res_blocks + self.in_channels = 3 + self.nf = nf + self.n_blocks = res_blocks self.codebook_size = codebook_size self.embed_dim = emb_dim self.ch_mult = ch_mult @@ -363,11 +363,11 @@ class VQAutoEncoder(nn.Module): self.kl_weight ) self.generator = Generator( - self.nf, + self.nf, self.embed_dim, - self.ch_mult, - self.n_blocks, - self.resolution, + self.ch_mult, + self.n_blocks, + self.resolution, self.attn_resolutions ) @@ -432,4 +432,4 @@ class VQGANDiscriminator(nn.Module): raise ValueError('Wrong params!') def forward(self, x): - return self.main(x)
\ No newline at end of file + return self.main(x) diff --git a/modules/esrgan_model_arch.py b/modules/esrgan_model_arch.py index 4de9dd8d..2b9888ba 100644 --- a/modules/esrgan_model_arch.py +++ b/modules/esrgan_model_arch.py @@ -105,7 +105,7 @@ class ResidualDenseBlock_5C(nn.Module): Modified options that can be used:
- "Partial Convolution based Padding" arXiv:1811.11718
- "Spectral normalization" arXiv:1802.05957
- - "ICASSP 2020 - ESRGAN+ : Further Improving ESRGAN" N. C.
+ - "ICASSP 2020 - ESRGAN+ : Further Improving ESRGAN" N. C.
{Rakotonirina} and A. {Rasoanaivo}
"""
@@ -170,7 +170,7 @@ class GaussianNoise(nn.Module): scale = self.sigma * x.detach() if self.is_relative_detach else self.sigma * x
sampled_noise = self.noise.repeat(*x.size()).normal_() * scale
x = x + sampled_noise
- return x
+ return x
def conv1x1(in_planes, out_planes, stride=1):
return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
diff --git a/modules/extras.py b/modules/extras.py index eb4f0b42..bdf9b3b7 100644 --- a/modules/extras.py +++ b/modules/extras.py @@ -199,7 +199,7 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_ result_is_inpainting_model = True
else:
theta_0[key] = theta_func2(a, b, multiplier)
-
+
theta_0[key] = to_half(theta_0[key], save_as_half)
shared.state.sampling_step += 1
diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py index 38ef074f..570b5603 100644 --- a/modules/hypernetworks/hypernetwork.py +++ b/modules/hypernetworks/hypernetwork.py @@ -540,7 +540,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi return hypernetwork, filename
scheduler = LearnRateScheduler(learn_rate, steps, initial_step)
-
+
clip_grad = torch.nn.utils.clip_grad_value_ if clip_grad_mode == "value" else torch.nn.utils.clip_grad_norm_ if clip_grad_mode == "norm" else None
if clip_grad:
clip_grad_sched = LearnRateScheduler(clip_grad_value, steps, initial_step, verbose=False)
@@ -593,7 +593,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi print(e)
scaler = torch.cuda.amp.GradScaler()
-
+
batch_size = ds.batch_size
gradient_step = ds.gradient_step
# n steps = batch_size * gradient_step * n image processed
@@ -636,7 +636,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi if clip_grad:
clip_grad_sched.step(hypernetwork.step)
-
+
with devices.autocast():
x = batch.latent_sample.to(devices.device, non_blocking=pin_memory)
if use_weight:
@@ -657,14 +657,14 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi _loss_step += loss.item()
scaler.scale(loss).backward()
-
+
# go back until we reach gradient accumulation steps
if (j + 1) % gradient_step != 0:
continue
loss_logging.append(_loss_step)
if clip_grad:
clip_grad(weights, clip_grad_sched.learn_rate)
-
+
scaler.step(optimizer)
scaler.update()
hypernetwork.step += 1
@@ -674,7 +674,7 @@ def train_hypernetwork(id_task, hypernetwork_name, learn_rate, batch_size, gradi _loss_step = 0
steps_done = hypernetwork.step + 1
-
+
epoch_num = hypernetwork.step // steps_per_epoch
epoch_step = hypernetwork.step % steps_per_epoch
diff --git a/modules/images.py b/modules/images.py index 3b8b62d9..b2de3662 100644 --- a/modules/images.py +++ b/modules/images.py @@ -367,7 +367,7 @@ class FilenameGenerator: self.seed = seed
self.prompt = prompt
self.image = image
-
+
def hasprompt(self, *args):
lower = self.prompt.lower()
if self.p is None or self.prompt is None:
diff --git a/modules/mac_specific.py b/modules/mac_specific.py index 5c2f92a1..d74c6b95 100644 --- a/modules/mac_specific.py +++ b/modules/mac_specific.py @@ -42,7 +42,7 @@ if has_mps: # MPS workaround for https://github.com/pytorch/pytorch/issues/79383 CondFunc('torch.Tensor.to', lambda orig_func, self, *args, **kwargs: orig_func(self.contiguous(), *args, **kwargs), lambda _, self, *args, **kwargs: self.device.type != 'mps' and (args and isinstance(args[0], torch.device) and args[0].type == 'mps' or isinstance(kwargs.get('device'), torch.device) and kwargs['device'].type == 'mps')) - # MPS workaround for https://github.com/pytorch/pytorch/issues/80800 + # MPS workaround for https://github.com/pytorch/pytorch/issues/80800 CondFunc('torch.nn.functional.layer_norm', lambda orig_func, *args, **kwargs: orig_func(*([args[0].contiguous()] + list(args[1:])), **kwargs), lambda _, *args, **kwargs: args and isinstance(args[0], torch.Tensor) and args[0].device.type == 'mps') # MPS workaround for https://github.com/pytorch/pytorch/issues/90532 @@ -60,4 +60,4 @@ if has_mps: # MPS workaround for https://github.com/pytorch/pytorch/issues/92311 if platform.processor() == 'i386': for funcName in ['torch.argmax', 'torch.Tensor.argmax']: - CondFunc(funcName, lambda _, input, *args, **kwargs: torch.max(input.float() if input.dtype == torch.int64 else input, *args, **kwargs)[1], lambda _, input, *args, **kwargs: input.device.type == 'mps')
\ No newline at end of file + CondFunc(funcName, lambda _, input, *args, **kwargs: torch.max(input.float() if input.dtype == torch.int64 else input, *args, **kwargs)[1], lambda _, input, *args, **kwargs: input.device.type == 'mps') diff --git a/modules/masking.py b/modules/masking.py index a5c4d2da..be9f84c7 100644 --- a/modules/masking.py +++ b/modules/masking.py @@ -4,7 +4,7 @@ from PIL import Image, ImageFilter, ImageOps def get_crop_region(mask, pad=0):
"""finds a rectangular region that contains all masked ares in an image. Returns (x1, y1, x2, y2) coordinates of the rectangle.
For example, if a user has painted the top-right part of a 512x512 image", the result may be (256, 0, 512, 256)"""
-
+
h, w = mask.shape
crop_left = 0
diff --git a/modules/ngrok.py b/modules/ngrok.py index 7a7b4b26..67a74e85 100644 --- a/modules/ngrok.py +++ b/modules/ngrok.py @@ -13,7 +13,7 @@ def connect(token, port, region): config = conf.PyngrokConfig( auth_token=token, region=region ) - + # Guard for existing tunnels existing = ngrok.get_tunnels(pyngrok_config=config) if existing: @@ -24,7 +24,7 @@ def connect(token, port, region): print(f'ngrok has already been connected to localhost:{port}! URL: {public_url}\n' 'You can use this link after the launch is complete.') return - + try: if account is None: public_url = ngrok.connect(port, pyngrok_config=config, bind_tls=True).public_url diff --git a/modules/processing.py b/modules/processing.py index c3932d6b..f902b9df 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -164,7 +164,7 @@ class StableDiffusionProcessing: self.all_subseeds = None
self.iteration = 0
self.is_hr_pass = False
-
+
@property
def sd_model(self):
diff --git a/modules/script_callbacks.py b/modules/script_callbacks.py index 17109732..7d9dd736 100644 --- a/modules/script_callbacks.py +++ b/modules/script_callbacks.py @@ -32,22 +32,22 @@ class CFGDenoiserParams: def __init__(self, x, image_cond, sigma, sampling_step, total_sampling_steps, text_cond, text_uncond):
self.x = x
"""Latent image representation in the process of being denoised"""
-
+
self.image_cond = image_cond
"""Conditioning image"""
-
+
self.sigma = sigma
"""Current sigma noise step value"""
-
+
self.sampling_step = sampling_step
"""Current Sampling step number"""
-
+
self.total_sampling_steps = total_sampling_steps
"""Total number of sampling steps planned"""
-
+
self.text_cond = text_cond
""" Encoder hidden states of text conditioning from prompt"""
-
+
self.text_uncond = text_uncond
""" Encoder hidden states of text conditioning from negative prompt"""
@@ -240,7 +240,7 @@ def add_callback(callbacks, fun): callbacks.append(ScriptCallback(filename, fun))
-
+
def remove_current_script_callbacks():
stack = [x for x in inspect.stack() if x.filename != __file__]
filename = stack[0].filename if len(stack) > 0 else 'unknown file'
diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index e374aeb8..7e50f1ab 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -34,7 +34,7 @@ def apply_optimizations(): ldm.modules.diffusionmodules.model.nonlinearity = silu
ldm.modules.diffusionmodules.openaimodel.th = sd_hijack_unet.th
-
+
optimization_method = None
can_use_sdp = hasattr(torch.nn.functional, "scaled_dot_product_attention") and callable(torch.nn.functional.scaled_dot_product_attention) # not everyone has torch 2.x to use sdp
@@ -92,12 +92,12 @@ def fix_checkpoint(): def weighted_loss(sd_model, pred, target, mean=True):
#Calculate the weight normally, but ignore the mean
loss = sd_model._old_get_loss(pred, target, mean=False)
-
+
#Check if we have weights available
weight = getattr(sd_model, '_custom_loss_weight', None)
if weight is not None:
loss *= weight
-
+
#Return the loss, as mean if specified
return loss.mean() if mean else loss
@@ -105,7 +105,7 @@ def weighted_forward(sd_model, x, c, w, *args, **kwargs): try:
#Temporarily append weights to a place accessible during loss calc
sd_model._custom_loss_weight = w
-
+
#Replace 'get_loss' with a weight-aware one. Otherwise we need to reimplement 'forward' completely
#Keep 'get_loss', but don't overwrite the previous old_get_loss if it's already set
if not hasattr(sd_model, '_old_get_loss'):
@@ -120,7 +120,7 @@ def weighted_forward(sd_model, x, c, w, *args, **kwargs): del sd_model._custom_loss_weight
except AttributeError:
pass
-
+
#If we have an old loss function, reset the loss function to the original one
if hasattr(sd_model, '_old_get_loss'):
sd_model.get_loss = sd_model._old_get_loss
@@ -184,7 +184,7 @@ class StableDiffusionModelHijack: def undo_hijack(self, m):
if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
- m.cond_stage_model = m.cond_stage_model.wrapped
+ m.cond_stage_model = m.cond_stage_model.wrapped
elif type(m.cond_stage_model) == sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords:
m.cond_stage_model = m.cond_stage_model.wrapped
diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index a174bbe1..f00fe55c 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -62,10 +62,10 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None): end = i + 2
s1 = einsum('b i d, b j d -> b i j', q[i:end], k[i:end])
s1 *= self.scale
-
+
s2 = s1.softmax(dim=-1)
del s1
-
+
r1[i:end] = einsum('b i j, b j d -> b i d', s2, v[i:end])
del s2
del q, k, v
@@ -95,43 +95,43 @@ def split_cross_attention_forward(self, x, context=None, mask=None): with devices.without_autocast(disable=not shared.opts.upcast_attn):
k_in = k_in * self.scale
-
+
del context, x
-
+
q, k, v = (rearrange(t, 'b n (h d) -> (b h) n d', h=h) for t in (q_in, k_in, v_in))
del q_in, k_in, v_in
-
+
r1 = torch.zeros(q.shape[0], q.shape[1], v.shape[2], device=q.device, dtype=q.dtype)
-
+
mem_free_total = get_available_vram()
-
+
gb = 1024 ** 3
tensor_size = q.shape[0] * q.shape[1] * k.shape[1] * q.element_size()
modifier = 3 if q.element_size() == 2 else 2.5
mem_required = tensor_size * modifier
steps = 1
-
+
if mem_required > mem_free_total:
steps = 2 ** (math.ceil(math.log(mem_required / mem_free_total, 2)))
# print(f"Expected tensor size:{tensor_size/gb:0.1f}GB, cuda free:{mem_free_cuda/gb:0.1f}GB "
# f"torch free:{mem_free_torch/gb:0.1f} total:{mem_free_total/gb:0.1f} steps:{steps}")
-
+
if steps > 64:
max_res = math.floor(math.sqrt(math.sqrt(mem_free_total / 2.5)) / 8) * 64
raise RuntimeError(f'Not enough memory, use lower resolution (max approx. {max_res}x{max_res}). '
f'Need: {mem_required / 64 / gb:0.1f}GB free, Have:{mem_free_total / gb:0.1f}GB free')
-
+
slice_size = q.shape[1] // steps if (q.shape[1] % steps) == 0 else q.shape[1]
for i in range(0, q.shape[1], slice_size):
end = i + slice_size
s1 = einsum('b i d, b j d -> b i j', q[:, i:end], k)
-
+
s2 = s1.softmax(dim=-1, dtype=q.dtype)
del s1
-
+
r1[:, i:end] = einsum('b i j, b j d -> b i d', s2, v)
del s2
-
+
del q, k, v
r1 = r1.to(dtype)
@@ -228,7 +228,7 @@ def split_cross_attention_forward_invokeAI(self, x, context=None, mask=None): with devices.without_autocast(disable=not shared.opts.upcast_attn):
k = k * self.scale
-
+
q, k, v = (rearrange(t, 'b n (h d) -> (b h) n d', h=h) for t in (q, k, v))
r = einsum_op(q, k, v)
r = r.to(dtype)
@@ -369,7 +369,7 @@ def scaled_dot_product_attention_forward(self, x, context=None, mask=None): q = q_in.view(batch_size, -1, h, head_dim).transpose(1, 2)
k = k_in.view(batch_size, -1, h, head_dim).transpose(1, 2)
v = v_in.view(batch_size, -1, h, head_dim).transpose(1, 2)
-
+
del q_in, k_in, v_in
dtype = q.dtype
@@ -451,7 +451,7 @@ def cross_attention_attnblock_forward(self, x): h3 += x
return h3
-
+
def xformers_attnblock_forward(self, x):
try:
h_ = x
diff --git a/modules/sd_models.py b/modules/sd_models.py index d1e946a5..3316d021 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -165,7 +165,7 @@ def model_hash(filename): def select_checkpoint():
model_checkpoint = shared.opts.sd_model_checkpoint
-
+
checkpoint_info = checkpoint_alisases.get(model_checkpoint, None)
if checkpoint_info is not None:
return checkpoint_info
@@ -372,7 +372,7 @@ def enable_midas_autodownload(): if not os.path.exists(path):
if not os.path.exists(midas_path):
mkdir(midas_path)
-
+
print(f"Downloading midas model weights for {model_type} to {path}")
request.urlretrieve(midas_urls[model_type], path)
print(f"{model_type} downloaded")
diff --git a/modules/sd_samplers_kdiffusion.py b/modules/sd_samplers_kdiffusion.py index 2f733cf5..e9e41818 100644 --- a/modules/sd_samplers_kdiffusion.py +++ b/modules/sd_samplers_kdiffusion.py @@ -93,10 +93,10 @@ class CFGDenoiser(torch.nn.Module): if shared.sd_model.model.conditioning_key == "crossattn-adm":
image_uncond = torch.zeros_like(image_cond)
- make_condition_dict = lambda c_crossattn, c_adm: {"c_crossattn": c_crossattn, "c_adm": c_adm}
+ make_condition_dict = lambda c_crossattn, c_adm: {"c_crossattn": c_crossattn, "c_adm": c_adm}
else:
image_uncond = image_cond
- make_condition_dict = lambda c_crossattn, c_concat: {"c_crossattn": c_crossattn, "c_concat": [c_concat]}
+ make_condition_dict = lambda c_crossattn, c_concat: {"c_crossattn": c_crossattn, "c_concat": [c_concat]}
if not is_edit_model:
x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
@@ -316,7 +316,7 @@ class KDiffusionSampler: sigma_sched = sigmas[steps - t_enc - 1:]
xi = x + noise * sigma_sched[0]
-
+
extra_params_kwargs = self.initialize(p)
parameters = inspect.signature(self.func).parameters
@@ -339,9 +339,9 @@ class KDiffusionSampler: self.model_wrap_cfg.init_latent = x
self.last_latent = x
extra_args={
- 'cond': conditioning,
- 'image_cond': image_conditioning,
- 'uncond': unconditional_conditioning,
+ 'cond': conditioning,
+ 'image_cond': image_conditioning,
+ 'uncond': unconditional_conditioning,
'cond_scale': p.cfg_scale,
's_min_uncond': self.s_min_uncond
}
@@ -374,9 +374,9 @@ class KDiffusionSampler: self.last_latent = x
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
- 'cond': conditioning,
- 'image_cond': image_conditioning,
- 'uncond': unconditional_conditioning,
+ 'cond': conditioning,
+ 'image_cond': image_conditioning,
+ 'uncond': unconditional_conditioning,
'cond_scale': p.cfg_scale,
's_min_uncond': self.s_min_uncond
}, disable=False, callback=self.callback_state, **extra_params_kwargs))
diff --git a/modules/sub_quadratic_attention.py b/modules/sub_quadratic_attention.py index cc38debd..497568eb 100644 --- a/modules/sub_quadratic_attention.py +++ b/modules/sub_quadratic_attention.py @@ -179,7 +179,7 @@ def efficient_dot_product_attention( chunk_idx, min(query_chunk_size, q_tokens) ) - + summarize_chunk: SummarizeChunk = partial(_summarize_chunk, scale=scale) summarize_chunk: SummarizeChunk = partial(checkpoint, summarize_chunk) if use_checkpoint else summarize_chunk compute_query_chunk_attn: ComputeQueryChunkAttn = partial( diff --git a/modules/textual_inversion/autocrop.py b/modules/textual_inversion/autocrop.py index 7770d22f..8e667a4d 100644 --- a/modules/textual_inversion/autocrop.py +++ b/modules/textual_inversion/autocrop.py @@ -10,63 +10,64 @@ RED = "#F00" def crop_image(im, settings):
- """ Intelligently crop an image to the subject matter """
-
- scale_by = 1
- if is_landscape(im.width, im.height):
- scale_by = settings.crop_height / im.height
- elif is_portrait(im.width, im.height):
- scale_by = settings.crop_width / im.width
- elif is_square(im.width, im.height):
- if is_square(settings.crop_width, settings.crop_height):
- scale_by = settings.crop_width / im.width
- elif is_landscape(settings.crop_width, settings.crop_height):
- scale_by = settings.crop_width / im.width
- elif is_portrait(settings.crop_width, settings.crop_height):
- scale_by = settings.crop_height / im.height
-
- im = im.resize((int(im.width * scale_by), int(im.height * scale_by)))
- im_debug = im.copy()
-
- focus = focal_point(im_debug, settings)
-
- # take the focal point and turn it into crop coordinates that try to center over the focal
- # point but then get adjusted back into the frame
- y_half = int(settings.crop_height / 2)
- x_half = int(settings.crop_width / 2)
-
- x1 = focus.x - x_half
- if x1 < 0:
- x1 = 0
- elif x1 + settings.crop_width > im.width:
- x1 = im.width - settings.crop_width
-
- y1 = focus.y - y_half
- if y1 < 0:
- y1 = 0
- elif y1 + settings.crop_height > im.height:
- y1 = im.height - settings.crop_height
-
- x2 = x1 + settings.crop_width
- y2 = y1 + settings.crop_height
-
- crop = [x1, y1, x2, y2]
-
- results = []
-
- results.append(im.crop(tuple(crop)))
-
- if settings.annotate_image:
- d = ImageDraw.Draw(im_debug)
- rect = list(crop)
- rect[2] -= 1
- rect[3] -= 1
- d.rectangle(rect, outline=GREEN)
- results.append(im_debug)
- if settings.destop_view_image:
- im_debug.show()
-
- return results
+ """ Intelligently crop an image to the subject matter """
+
+ scale_by = 1
+ if is_landscape(im.width, im.height):
+ scale_by = settings.crop_height / im.height
+ elif is_portrait(im.width, im.height):
+ scale_by = settings.crop_width / im.width
+ elif is_square(im.width, im.height):
+ if is_square(settings.crop_width, settings.crop_height):
+ scale_by = settings.crop_width / im.width
+ elif is_landscape(settings.crop_width, settings.crop_height):
+ scale_by = settings.crop_width / im.width
+ elif is_portrait(settings.crop_width, settings.crop_height):
+ scale_by = settings.crop_height / im.height
+
+
+ im = im.resize((int(im.width * scale_by), int(im.height * scale_by)))
+ im_debug = im.copy()
+
+ focus = focal_point(im_debug, settings)
+
+ # take the focal point and turn it into crop coordinates that try to center over the focal
+ # point but then get adjusted back into the frame
+ y_half = int(settings.crop_height / 2)
+ x_half = int(settings.crop_width / 2)
+
+ x1 = focus.x - x_half
+ if x1 < 0:
+ x1 = 0
+ elif x1 + settings.crop_width > im.width:
+ x1 = im.width - settings.crop_width
+
+ y1 = focus.y - y_half
+ if y1 < 0:
+ y1 = 0
+ elif y1 + settings.crop_height > im.height:
+ y1 = im.height - settings.crop_height
+
+ x2 = x1 + settings.crop_width
+ y2 = y1 + settings.crop_height
+
+ crop = [x1, y1, x2, y2]
+
+ results = []
+
+ results.append(im.crop(tuple(crop)))
+
+ if settings.annotate_image:
+ d = ImageDraw.Draw(im_debug)
+ rect = list(crop)
+ rect[2] -= 1
+ rect[3] -= 1
+ d.rectangle(rect, outline=GREEN)
+ results.append(im_debug)
+ if settings.destop_view_image:
+ im_debug.show()
+
+ return results
def focal_point(im, settings):
corner_points = image_corner_points(im, settings) if settings.corner_points_weight > 0 else []
@@ -86,7 +87,7 @@ def focal_point(im, settings): corner_centroid = None
if len(corner_points) > 0:
corner_centroid = centroid(corner_points)
- corner_centroid.weight = settings.corner_points_weight / weight_pref_total
+ corner_centroid.weight = settings.corner_points_weight / weight_pref_total
pois.append(corner_centroid)
entropy_centroid = None
@@ -98,7 +99,7 @@ def focal_point(im, settings): face_centroid = None
if len(face_points) > 0:
face_centroid = centroid(face_points)
- face_centroid.weight = settings.face_points_weight / weight_pref_total
+ face_centroid.weight = settings.face_points_weight / weight_pref_total
pois.append(face_centroid)
average_point = poi_average(pois, settings)
@@ -132,7 +133,7 @@ def focal_point(im, settings): d.rectangle(f.bounding(4), outline=color)
d.ellipse(average_point.bounding(max_size), outline=GREEN)
-
+
return average_point
@@ -260,10 +261,11 @@ def image_entropy(im): hist = hist[hist > 0]
return -np.log2(hist / hist.sum()).sum()
+
def centroid(pois):
- x = [poi.x for poi in pois]
- y = [poi.y for poi in pois]
- return PointOfInterest(sum(x)/len(pois), sum(y)/len(pois))
+ x = [poi.x for poi in pois]
+ y = [poi.y for poi in pois]
+ return PointOfInterest(sum(x) / len(pois), sum(y) / len(pois))
def poi_average(pois, settings):
@@ -281,59 +283,59 @@ def poi_average(pois, settings): def is_landscape(w, h):
- return w > h
+ return w > h
def is_portrait(w, h):
- return h > w
+ return h > w
def is_square(w, h):
- return w == h
+ return w == h
def download_and_cache_models(dirname):
- download_url = 'https://github.com/opencv/opencv_zoo/blob/91fb0290f50896f38a0ab1e558b74b16bc009428/models/face_detection_yunet/face_detection_yunet_2022mar.onnx?raw=true'
- model_file_name = 'face_detection_yunet.onnx'
+ download_url = 'https://github.com/opencv/opencv_zoo/blob/91fb0290f50896f38a0ab1e558b74b16bc009428/models/face_detection_yunet/face_detection_yunet_2022mar.onnx?raw=true'
+ model_file_name = 'face_detection_yunet.onnx'
- if not os.path.exists(dirname):
- os.makedirs(dirname)
+ if not os.path.exists(dirname):
+ os.makedirs(dirname)
- cache_file = os.path.join(dirname, model_file_name)
- if not os.path.exists(cache_file):
- print(f"downloading face detection model from '{download_url}' to '{cache_file}'")
- response = requests.get(download_url)
- with open(cache_file, "wb") as f:
- f.write(response.content)
+ cache_file = os.path.join(dirname, model_file_name)
+ if not os.path.exists(cache_file):
+ print(f"downloading face detection model from '{download_url}' to '{cache_file}'")
+ response = requests.get(download_url)
+ with open(cache_file, "wb") as f:
+ f.write(response.content)
- if os.path.exists(cache_file):
- return cache_file
- return None
+ if os.path.exists(cache_file):
+ return cache_file
+ return None
class PointOfInterest:
- def __init__(self, x, y, weight=1.0, size=10):
- self.x = x
- self.y = y
- self.weight = weight
- self.size = size
+ def __init__(self, x, y, weight=1.0, size=10):
+ self.x = x
+ self.y = y
+ self.weight = weight
+ self.size = size
- def bounding(self, size):
- return [
- self.x - size//2,
- self.y - size//2,
- self.x + size//2,
- self.y + size//2
- ]
+ def bounding(self, size):
+ return [
+ self.x - size // 2,
+ self.y - size // 2,
+ self.x + size // 2,
+ self.y + size // 2
+ ]
class Settings:
- def __init__(self, crop_width=512, crop_height=512, corner_points_weight=0.5, entropy_points_weight=0.5, face_points_weight=0.5, annotate_image=False, dnn_model_path=None):
- self.crop_width = crop_width
- self.crop_height = crop_height
- self.corner_points_weight = corner_points_weight
- self.entropy_points_weight = entropy_points_weight
- self.face_points_weight = face_points_weight
- self.annotate_image = annotate_image
- self.destop_view_image = False
- self.dnn_model_path = dnn_model_path
+ def __init__(self, crop_width=512, crop_height=512, corner_points_weight=0.5, entropy_points_weight=0.5, face_points_weight=0.5, annotate_image=False, dnn_model_path=None):
+ self.crop_width = crop_width
+ self.crop_height = crop_height
+ self.corner_points_weight = corner_points_weight
+ self.entropy_points_weight = entropy_points_weight
+ self.face_points_weight = face_points_weight
+ self.annotate_image = annotate_image
+ self.destop_view_image = False
+ self.dnn_model_path = dnn_model_path
diff --git a/modules/textual_inversion/dataset.py b/modules/textual_inversion/dataset.py index 41610e03..b9621fc9 100644 --- a/modules/textual_inversion/dataset.py +++ b/modules/textual_inversion/dataset.py @@ -118,7 +118,7 @@ class PersonalizedBase(Dataset): weight = torch.ones(latent_sample.shape)
else:
weight = None
-
+
if latent_sampling_method == "random":
entry = DatasetEntry(filename=path, filename_text=filename_text, latent_dist=latent_dist, weight=weight)
else:
@@ -243,4 +243,4 @@ class BatchLoaderRandom(BatchLoader): return self
def collate_wrapper_random(batch):
- return BatchLoaderRandom(batch)
\ No newline at end of file + return BatchLoaderRandom(batch)
diff --git a/modules/textual_inversion/preprocess.py b/modules/textual_inversion/preprocess.py index d0cad09e..a009d8e8 100644 --- a/modules/textual_inversion/preprocess.py +++ b/modules/textual_inversion/preprocess.py @@ -125,7 +125,7 @@ def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, thr default=None
)
return wh and center_crop(image, *wh)
-
+
def preprocess_work(process_src, process_dst, process_width, process_height, preprocess_txt_action, process_keep_original_size, process_flip, process_split, process_caption, process_caption_deepbooru=False, split_threshold=0.5, overlap_ratio=0.2, process_focal_crop=False, process_focal_crop_face_weight=0.9, process_focal_crop_entropy_weight=0.3, process_focal_crop_edges_weight=0.5, process_focal_crop_debug=False, process_multicrop=None, process_multicrop_mindim=None, process_multicrop_maxdim=None, process_multicrop_minarea=None, process_multicrop_maxarea=None, process_multicrop_objective=None, process_multicrop_threshold=None):
width = process_width
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index 9e1b2b9a..d489ed1e 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -323,16 +323,16 @@ def tensorboard_add(tensorboard_writer, loss, global_step, step, learn_rate, epo tensorboard_add_scaler(tensorboard_writer, f"Learn rate/train/epoch-{epoch_num}", learn_rate, step)
def tensorboard_add_scaler(tensorboard_writer, tag, value, step):
- tensorboard_writer.add_scalar(tag=tag,
+ tensorboard_writer.add_scalar(tag=tag,
scalar_value=value, global_step=step)
def tensorboard_add_image(tensorboard_writer, tag, pil_image, step):
# Convert a pil image to a torch tensor
img_tensor = torch.as_tensor(np.array(pil_image, copy=True))
- img_tensor = img_tensor.view(pil_image.size[1], pil_image.size[0],
+ img_tensor = img_tensor.view(pil_image.size[1], pil_image.size[0],
len(pil_image.getbands()))
img_tensor = img_tensor.permute((2, 0, 1))
-
+
tensorboard_writer.add_image(tag, img_tensor, global_step=step)
def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, data_root, template_file, template_filename, steps, save_model_every, create_image_every, log_directory, name="embedding"):
@@ -402,7 +402,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st if initial_step >= steps:
shared.state.textinfo = "Model has already been trained beyond specified max steps"
return embedding, filename
-
+
scheduler = LearnRateScheduler(learn_rate, steps, initial_step)
clip_grad = torch.nn.utils.clip_grad_value_ if clip_grad_mode == "value" else \
torch.nn.utils.clip_grad_norm_ if clip_grad_mode == "norm" else \
@@ -412,7 +412,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st # dataset loading may take a while, so input validations and early returns should be done before this
shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
old_parallel_processing_allowed = shared.parallel_processing_allowed
-
+
if shared.opts.training_enable_tensorboard:
tensorboard_writer = tensorboard_setup(log_directory)
@@ -439,7 +439,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st optimizer_saved_dict = torch.load(f"{filename}.optim", map_location='cpu')
if embedding.checksum() == optimizer_saved_dict.get('hash', None):
optimizer_state_dict = optimizer_saved_dict.get('optimizer_state_dict', None)
-
+
if optimizer_state_dict is not None:
optimizer.load_state_dict(optimizer_state_dict)
print("Loaded existing optimizer from checkpoint")
@@ -485,7 +485,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st if clip_grad:
clip_grad_sched.step(embedding.step)
-
+
with devices.autocast():
x = batch.latent_sample.to(devices.device, non_blocking=pin_memory)
if use_weight:
@@ -513,7 +513,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st # go back until we reach gradient accumulation steps
if (j + 1) % gradient_step != 0:
continue
-
+
if clip_grad:
clip_grad(embedding.vec, clip_grad_sched.learn_rate)
diff --git a/modules/ui.py b/modules/ui.py index 1efb656a..ff82fff6 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -1171,7 +1171,7 @@ def create_ui(): process_focal_crop_entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_entropy_weight")
process_focal_crop_edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="train_process_focal_crop_edges_weight")
process_focal_crop_debug = gr.Checkbox(label='Create debug image', elem_id="train_process_focal_crop_debug")
-
+
with gr.Column(visible=False) as process_multicrop_col:
gr.Markdown('Each image is center-cropped with an automatically chosen width and height.')
with gr.Row():
@@ -1183,7 +1183,7 @@ def create_ui(): with gr.Row():
process_multicrop_objective = gr.Radio(["Maximize area", "Minimize error"], value="Maximize area", label="Resizing objective", elem_id="train_process_multicrop_objective")
process_multicrop_threshold = gr.Slider(minimum=0, maximum=1, step=0.01, label="Error threshold", value=0.1, elem_id="train_process_multicrop_threshold")
-
+
with gr.Row():
with gr.Column(scale=3):
gr.HTML(value="")
@@ -1226,7 +1226,7 @@ def create_ui(): with FormRow():
embedding_learn_rate = gr.Textbox(label='Embedding Learning rate', placeholder="Embedding Learning rate", value="0.005", elem_id="train_embedding_learn_rate")
hypernetwork_learn_rate = gr.Textbox(label='Hypernetwork Learning rate', placeholder="Hypernetwork Learning rate", value="0.00001", elem_id="train_hypernetwork_learn_rate")
-
+
with FormRow():
clip_grad_mode = gr.Dropdown(value="disabled", label="Gradient Clipping", choices=["disabled", "value", "norm"])
clip_grad_value = gr.Textbox(placeholder="Gradient clip value", value="0.1", show_label=False)
@@ -1565,7 +1565,7 @@ def create_ui(): gr.HTML(shared.html("licenses.html"), elem_id="licenses")
gr.Button(value="Show all pages", elem_id="settings_show_all_pages")
-
+
def unload_sd_weights():
modules.sd_models.unload_model_weights()
@@ -1841,15 +1841,15 @@ def versions_html(): return f"""
version: <a href="https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/{commit}">{tag}</a>
- •
+ •
python: <span title="{sys.version}">{python_version}</span>
- •
+ •
torch: {getattr(torch, '__long_version__',torch.__version__)}
- •
+ •
xformers: {xformers_version}
- •
+ •
gradio: {gr.__version__}
- •
+ •
checkpoint: <a id="sd_checkpoint_hash">N/A</a>
"""
diff --git a/modules/ui_extensions.py b/modules/ui_extensions.py index ed70abe5..af497733 100644 --- a/modules/ui_extensions.py +++ b/modules/ui_extensions.py @@ -467,7 +467,7 @@ def refresh_available_extensions_from_data(hide_tags, sort_column, filter_text=" <td>{html.escape(description)}<p class="info"><span class="date_added">Added: {html.escape(added)}</span></p></td>
<td>{install_code}</td>
</tr>
-
+
"""
for tag in [x for x in extension_tags if x not in tags]:
@@ -535,9 +535,9 @@ def create_ui(): hide_tags = gr.CheckboxGroup(value=["ads", "localization", "installed"], label="Hide extensions with tags", choices=["script", "ads", "localization", "installed"])
sort_column = gr.Radio(value="newest first", label="Order", choices=["newest first", "oldest first", "a-z", "z-a", "internal order", ], type="index")
- with gr.Row():
+ with gr.Row():
search_extensions_text = gr.Text(label="Search").style(container=False)
-
+
install_result = gr.HTML()
available_extensions_table = gr.HTML()
diff --git a/modules/xlmr.py b/modules/xlmr.py index e056c3f6..a407a3ca 100644 --- a/modules/xlmr.py +++ b/modules/xlmr.py @@ -28,7 +28,7 @@ class BertSeriesModelWithTransformation(BertPreTrainedModel): config_class = BertSeriesConfig def __init__(self, config=None, **kargs): - # modify initialization for autoloading + # modify initialization for autoloading if config is None: config = XLMRobertaConfig() config.attention_probs_dropout_prob= 0.1 @@ -74,7 +74,7 @@ class BertSeriesModelWithTransformation(BertPreTrainedModel): text["attention_mask"] = torch.tensor( text['attention_mask']).to(device) features = self(**text) - return features['projection_state'] + return features['projection_state'] def forward( self, @@ -134,4 +134,4 @@ class BertSeriesModelWithTransformation(BertPreTrainedModel): class RobertaSeriesModelWithTransformation(BertSeriesModelWithTransformation): base_model_prefix = 'roberta' - config_class= RobertaSeriesConfig
\ No newline at end of file + config_class= RobertaSeriesConfig |