diff options
41 files changed, 313 insertions, 308 deletions
diff --git a/extensions-builtin/LDSR/ldsr_model_arch.py b/extensions-builtin/LDSR/ldsr_model_arch.py index 2173de79..7f450086 100644 --- a/extensions-builtin/LDSR/ldsr_model_arch.py +++ b/extensions-builtin/LDSR/ldsr_model_arch.py @@ -130,11 +130,11 @@ class LDSR: im_og = im_og.resize((width_downsampled_pre, height_downsampled_pre), Image.LANCZOS) else: print(f"Down sample rate is 1 from {target_scale} / 4 (Not downsampling)") - + # pad width and height to multiples of 64, pads with the edge values of image to avoid artifacts pad_w, pad_h = np.max(((2, 2), np.ceil(np.array(im_og.size) / 64).astype(int)), axis=0) * 64 - im_og.size im_padded = Image.fromarray(np.pad(np.array(im_og), ((0, pad_h), (0, pad_w), (0, 0)), mode='edge')) - + logs = self.run(model["model"], im_padded, diffusion_steps, eta) sample = logs["sample"] diff --git a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py index 57c02d12..631a08ef 100644 --- a/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py +++ b/extensions-builtin/LDSR/sd_hijack_ddpm_v1.py @@ -460,7 +460,7 @@ class LatentDiffusionV1(DDPMV1): self.instantiate_cond_stage(cond_stage_config) self.cond_stage_forward = cond_stage_forward self.clip_denoised = False - self.bbox_tokenizer = None + self.bbox_tokenizer = None self.restarted_from_ckpt = False if ckpt_path is not None: @@ -792,7 +792,7 @@ class LatentDiffusionV1(DDPMV1): z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1])) # (bn, nc, ks[0], ks[1], L ) # 2. apply model loop over last dim - if isinstance(self.first_stage_model, VQModelInterface): + if isinstance(self.first_stage_model, VQModelInterface): output_list = [self.first_stage_model.decode(z[:, :, :, :, i], force_not_quantize=predict_cids or force_not_quantize) for i in range(z.shape[-1])] @@ -890,7 +890,7 @@ class LatentDiffusionV1(DDPMV1): if hasattr(self, "split_input_params"): assert len(cond) == 1 # todo can only deal with one conditioning atm - assert not return_ids + assert not return_ids ks = self.split_input_params["ks"] # eg. (128, 128) stride = self.split_input_params["stride"] # eg. (64, 64) diff --git a/extensions-builtin/ScuNET/scunet_model_arch.py b/extensions-builtin/ScuNET/scunet_model_arch.py index 8028918a..b51a8806 100644 --- a/extensions-builtin/ScuNET/scunet_model_arch.py +++ b/extensions-builtin/ScuNET/scunet_model_arch.py @@ -265,4 +265,4 @@ class SCUNet(nn.Module): nn.init.constant_(m.bias, 0) elif isinstance(m, nn.LayerNorm): nn.init.constant_(m.bias, 0) - nn.init.constant_(m.weight, 1.0)
\ No newline at end of file + nn.init.constant_(m.weight, 1.0) diff --git a/extensions-builtin/SwinIR/scripts/swinir_model.py b/extensions-builtin/SwinIR/scripts/swinir_model.py index 55dd94ab..0ba50487 100644 --- a/extensions-builtin/SwinIR/scripts/swinir_model.py +++ b/extensions-builtin/SwinIR/scripts/swinir_model.py @@ -150,7 +150,7 @@ def inference(img, model, tile, tile_overlap, window_size, scale): for w_idx in w_idx_list: if state.interrupted or state.skipped: break - + in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile] out_patch = model(in_patch) out_patch_mask = torch.ones_like(out_patch) diff --git a/extensions-builtin/SwinIR/swinir_model_arch.py b/extensions-builtin/SwinIR/swinir_model_arch.py index 73e37cfa..93b93274 100644 --- a/extensions-builtin/SwinIR/swinir_model_arch.py +++ b/extensions-builtin/SwinIR/swinir_model_arch.py @@ -805,7 +805,7 @@ class SwinIR(nn.Module): def forward(self, x): H, W = x.shape[2:] x = self.check_image_size(x) - + self.mean = self.mean.type_as(x) x = (x - self.mean) * self.img_range diff --git a/extensions-builtin/SwinIR/swinir_model_arch_v2.py b/extensions-builtin/SwinIR/swinir_model_arch_v2.py index 3ca9be78..dad22cca 100644 --- a/extensions-builtin/SwinIR/swinir_model_arch_v2.py +++ b/extensions-builtin/SwinIR/swinir_model_arch_v2.py @@ -241,7 +241,7 @@ class SwinTransformerBlock(nn.Module): attn_mask = None
self.register_buffer("attn_mask", attn_mask)
-
+
def calculate_mask(self, x_size):
# calculate attention mask for SW-MSA
H, W = x_size
@@ -263,7 +263,7 @@ class SwinTransformerBlock(nn.Module): attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
- return attn_mask
+ return attn_mask
def forward(self, x, x_size):
H, W = x_size
@@ -288,7 +288,7 @@ class SwinTransformerBlock(nn.Module): attn_windows = self.attn(x_windows, mask=self.attn_mask) # nW*B, window_size*window_size, C
else:
attn_windows = self.attn(x_windows, mask=self.calculate_mask(x_size).to(x.device))
-
+
# merge windows
attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
shifted_x = window_reverse(attn_windows, self.window_size, H, W) # B H' W' C
@@ -369,7 +369,7 @@ class PatchMerging(nn.Module): H, W = self.input_resolution
flops = (H // 2) * (W // 2) * 4 * self.dim * 2 * self.dim
flops += H * W * self.dim // 2
- return flops
+ return flops
class BasicLayer(nn.Module):
""" A basic Swin Transformer layer for one stage.
@@ -447,7 +447,7 @@ class BasicLayer(nn.Module): nn.init.constant_(blk.norm1.weight, 0)
nn.init.constant_(blk.norm2.bias, 0)
nn.init.constant_(blk.norm2.weight, 0)
-
+
class PatchEmbed(nn.Module):
r""" Image to Patch Embedding
Args:
@@ -492,7 +492,7 @@ class PatchEmbed(nn.Module): flops = Ho * Wo * self.embed_dim * self.in_chans * (self.patch_size[0] * self.patch_size[1])
if self.norm is not None:
flops += Ho * Wo * self.embed_dim
- return flops
+ return flops
class RSTB(nn.Module):
"""Residual Swin Transformer Block (RSTB).
@@ -531,7 +531,7 @@ class RSTB(nn.Module): num_heads=num_heads,
window_size=window_size,
mlp_ratio=mlp_ratio,
- qkv_bias=qkv_bias,
+ qkv_bias=qkv_bias,
drop=drop, attn_drop=attn_drop,
drop_path=drop_path,
norm_layer=norm_layer,
@@ -622,7 +622,7 @@ class Upsample(nn.Sequential): else:
raise ValueError(f'scale {scale} is not supported. ' 'Supported scales: 2^n and 3.')
super(Upsample, self).__init__(*m)
-
+
class Upsample_hf(nn.Sequential):
"""Upsample module.
@@ -642,7 +642,7 @@ class Upsample_hf(nn.Sequential): m.append(nn.PixelShuffle(3))
else:
raise ValueError(f'scale {scale} is not supported. ' 'Supported scales: 2^n and 3.')
- super(Upsample_hf, self).__init__(*m)
+ super(Upsample_hf, self).__init__(*m)
class UpsampleOneStep(nn.Sequential):
@@ -667,8 +667,8 @@ class UpsampleOneStep(nn.Sequential): H, W = self.input_resolution
flops = H * W * self.num_feat * 3 * 9
return flops
-
-
+
+
class Swin2SR(nn.Module):
r""" Swin2SR
@@ -699,7 +699,7 @@ class Swin2SR(nn.Module): def __init__(self, img_size=64, patch_size=1, in_chans=3,
embed_dim=96, depths=(6, 6, 6, 6), num_heads=(6, 6, 6, 6),
- window_size=7, mlp_ratio=4., qkv_bias=True,
+ window_size=7, mlp_ratio=4., qkv_bias=True,
drop_rate=0., attn_drop_rate=0., drop_path_rate=0.1,
norm_layer=nn.LayerNorm, ape=False, patch_norm=True,
use_checkpoint=False, upscale=2, img_range=1., upsampler='', resi_connection='1conv',
@@ -764,7 +764,7 @@ class Swin2SR(nn.Module): num_heads=num_heads[i_layer],
window_size=window_size,
mlp_ratio=self.mlp_ratio,
- qkv_bias=qkv_bias,
+ qkv_bias=qkv_bias,
drop=drop_rate, attn_drop=attn_drop_rate,
drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])], # no impact on SR results
norm_layer=norm_layer,
@@ -776,7 +776,7 @@ class Swin2SR(nn.Module): )
self.layers.append(layer)
-
+
if self.upsampler == 'pixelshuffle_hf':
self.layers_hf = nn.ModuleList()
for i_layer in range(self.num_layers):
@@ -787,7 +787,7 @@ class Swin2SR(nn.Module): num_heads=num_heads[i_layer],
window_size=window_size,
mlp_ratio=self.mlp_ratio,
- qkv_bias=qkv_bias,
+ qkv_bias=qkv_bias,
drop=drop_rate, attn_drop=attn_drop_rate,
drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])], # no impact on SR results
norm_layer=norm_layer,
@@ -799,7 +799,7 @@ class Swin2SR(nn.Module): )
self.layers_hf.append(layer)
-
+
self.norm = norm_layer(self.num_features)
# build the last conv layer in deep feature extraction
@@ -829,10 +829,10 @@ class Swin2SR(nn.Module): self.conv_aux = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
self.conv_after_aux = nn.Sequential(
nn.Conv2d(3, num_feat, 3, 1, 1),
- nn.LeakyReLU(inplace=True))
+ nn.LeakyReLU(inplace=True))
self.upsample = Upsample(upscale, num_feat)
self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
-
+
elif self.upsampler == 'pixelshuffle_hf':
self.conv_before_upsample = nn.Sequential(nn.Conv2d(embed_dim, num_feat, 3, 1, 1),
nn.LeakyReLU(inplace=True))
@@ -846,7 +846,7 @@ class Swin2SR(nn.Module): nn.Conv2d(embed_dim, num_feat, 3, 1, 1),
nn.LeakyReLU(inplace=True))
self.conv_last_hf = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1)
-
+
elif self.upsampler == 'pixelshuffledirect':
# for lightweight SR (to save parameters)
self.upsample = UpsampleOneStep(upscale, embed_dim, num_out_ch,
@@ -905,7 +905,7 @@ class Swin2SR(nn.Module): x = self.patch_unembed(x, x_size)
return x
-
+
def forward_features_hf(self, x):
x_size = (x.shape[2], x.shape[3])
x = self.patch_embed(x)
@@ -919,7 +919,7 @@ class Swin2SR(nn.Module): x = self.norm(x) # B L C
x = self.patch_unembed(x, x_size)
- return x
+ return x
def forward(self, x):
H, W = x.shape[2:]
@@ -951,7 +951,7 @@ class Swin2SR(nn.Module): x = self.conv_after_body(self.forward_features(x)) + x
x_before = self.conv_before_upsample(x)
x_out = self.conv_last(self.upsample(x_before))
-
+
x_hf = self.conv_first_hf(x_before)
x_hf = self.conv_after_body_hf(self.forward_features_hf(x_hf)) + x_hf
x_hf = self.conv_before_upsample_hf(x_hf)
@@ -977,15 +977,15 @@ class Swin2SR(nn.Module): x_first = self.conv_first(x)
res = self.conv_after_body(self.forward_features(x_first)) + x_first
x = x + self.conv_last(res)
-
+
x = x / self.img_range + self.mean
if self.upsampler == "pixelshuffle_aux":
return x[:, :, :H*self.upscale, :W*self.upscale], aux
-
+
elif self.upsampler == "pixelshuffle_hf":
x_out = x_out / self.img_range + self.mean
return x_out[:, :, :H*self.upscale, :W*self.upscale], x[:, :, :H*self.upscale, :W*self.upscale], x_hf[:, :, :H*self.upscale, :W*self.upscale]
-
+
else:
return x[:, :, :H*self.upscale, :W*self.upscale]
@@ -1014,4 +1014,4 @@ if __name__ == '__main__': x = torch.randn((1, 3, height, width))
x = model(x)
- print(x.shape)
\ No newline at end of file + print(x.shape)
@@ -327,7 +327,7 @@ def prepare_environment(): if args.update_all_extensions:
git_pull_recursive(extensions_dir)
-
+
if "--exit" in sys.argv:
print("Exiting because of --exit argument")
exit(0)
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
|