diff options
Diffstat (limited to 'modules')
| -rw-r--r-- | modules/bsrgan_model.py | 2 | ||||
| -rw-r--r-- | modules/deepbooru.py | 73 | ||||
| -rw-r--r-- | modules/esrgan_model.py | 6 | ||||
| -rw-r--r-- | modules/esrgan_model_arch.py (renamed from modules/esrgam_model_arch.py) | 0 | ||||
| -rw-r--r-- | modules/extras.py | 12 | ||||
| -rw-r--r-- | modules/hypernetwork.py | 98 | ||||
| -rw-r--r-- | modules/images.py | 39 | ||||
| -rw-r--r-- | modules/img2img.py | 2 | ||||
| -rw-r--r-- | modules/interrogate.py | 4 | ||||
| -rw-r--r-- | modules/ldsr_model.py | 2 | ||||
| -rw-r--r-- | modules/paths.py | 2 | ||||
| -rw-r--r-- | modules/processing.py | 31 | ||||
| -rw-r--r-- | modules/prompt_parser.py | 18 | ||||
| -rw-r--r-- | modules/realesrgan_model.py | 2 | ||||
| -rw-r--r-- | modules/safe.py | 93 | ||||
| -rw-r--r-- | modules/scunet_model.py | 2 | ||||
| -rw-r--r-- | modules/scunet_model_arch.py | 4 | ||||
| -rw-r--r-- | modules/sd_hijack.py | 72 | ||||
| -rw-r--r-- | modules/sd_hijack_optimizations.py | 80 | ||||
| -rw-r--r-- | modules/sd_models.py | 54 | ||||
| -rw-r--r-- | modules/sd_samplers.py | 43 | ||||
| -rw-r--r-- | modules/shared.py | 33 | ||||
| -rw-r--r-- | modules/swinir_model.py | 2 | ||||
| -rw-r--r-- | modules/swinir_model_arch.py | 2 | ||||
| -rw-r--r-- | modules/ui.py | 156 | ||||
| -rw-r--r-- | modules/upscaler.py | 7 |
26 files changed, 713 insertions, 126 deletions
diff --git a/modules/bsrgan_model.py b/modules/bsrgan_model.py index 3bd80791..737e1a76 100644 --- a/modules/bsrgan_model.py +++ b/modules/bsrgan_model.py @@ -10,13 +10,11 @@ from basicsr.utils.download_util import load_file_from_url import modules.upscaler from modules import devices, modelloader from modules.bsrgan_model_arch import RRDBNet -from modules.paths import models_path class UpscalerBSRGAN(modules.upscaler.Upscaler): def __init__(self, dirname): self.name = "BSRGAN" - self.model_path = os.path.join(models_path, self.name) self.model_name = "BSRGAN 4x" self.model_url = "https://github.com/cszn/KAIR/releases/download/v1.0/BSRGAN.pth" self.user_path = dirname diff --git a/modules/deepbooru.py b/modules/deepbooru.py new file mode 100644 index 00000000..7e3c0618 --- /dev/null +++ b/modules/deepbooru.py @@ -0,0 +1,73 @@ +import os.path +from concurrent.futures import ProcessPoolExecutor +from multiprocessing import get_context + + +def _load_tf_and_return_tags(pil_image, threshold): + import deepdanbooru as dd + import tensorflow as tf + import numpy as np + + this_folder = os.path.dirname(__file__) + model_path = os.path.abspath(os.path.join(this_folder, '..', 'models', 'deepbooru')) + if not os.path.exists(os.path.join(model_path, 'project.json')): + # there is no point importing these every time + import zipfile + from basicsr.utils.download_util import load_file_from_url + load_file_from_url(r"https://github.com/KichangKim/DeepDanbooru/releases/download/v3-20211112-sgd-e28/deepdanbooru-v3-20211112-sgd-e28.zip", + model_path) + with zipfile.ZipFile(os.path.join(model_path, "deepdanbooru-v3-20211112-sgd-e28.zip"), "r") as zip_ref: + zip_ref.extractall(model_path) + os.remove(os.path.join(model_path, "deepdanbooru-v3-20211112-sgd-e28.zip")) + + tags = dd.project.load_tags_from_project(model_path) + model = dd.project.load_model_from_project( + model_path, compile_model=True + ) + + width = model.input_shape[2] + height = model.input_shape[1] + image = np.array(pil_image) + image = tf.image.resize( + image, + size=(height, width), + method=tf.image.ResizeMethod.AREA, + preserve_aspect_ratio=True, + ) + image = image.numpy() # EagerTensor to np.array + image = dd.image.transform_and_pad_image(image, width, height) + image = image / 255.0 + image_shape = image.shape + image = image.reshape((1, image_shape[0], image_shape[1], image_shape[2])) + + y = model.predict(image)[0] + + result_dict = {} + + for i, tag in enumerate(tags): + result_dict[tag] = y[i] + result_tags_out = [] + result_tags_print = [] + for tag in tags: + if result_dict[tag] >= threshold: + if tag.startswith("rating:"): + continue + result_tags_out.append(tag) + result_tags_print.append(f'{result_dict[tag]} {tag}') + + print('\n'.join(sorted(result_tags_print, reverse=True))) + + return ', '.join(result_tags_out).replace('_', ' ').replace(':', ' ') + + +def subprocess_init_no_cuda(): + import os + os.environ["CUDA_VISIBLE_DEVICES"] = "-1" + + +def get_deepbooru_tags(pil_image, threshold=0.5): + context = get_context('spawn') + with ProcessPoolExecutor(initializer=subprocess_init_no_cuda, mp_context=context) as executor: + f = executor.submit(_load_tf_and_return_tags, pil_image, threshold, ) + ret = f.result() # will rethrow any exceptions + return ret
\ No newline at end of file diff --git a/modules/esrgan_model.py b/modules/esrgan_model.py index d17e730f..46ad0da3 100644 --- a/modules/esrgan_model.py +++ b/modules/esrgan_model.py @@ -5,9 +5,8 @@ import torch from PIL import Image
from basicsr.utils.download_util import load_file_from_url
-import modules.esrgam_model_arch as arch
+import modules.esrgan_model_arch as arch
from modules import shared, modelloader, images, devices
-from modules.paths import models_path
from modules.upscaler import Upscaler, UpscalerData
from modules.shared import opts
@@ -76,7 +75,6 @@ class UpscalerESRGAN(Upscaler): self.model_name = "ESRGAN_4x"
self.scalers = []
self.user_path = dirname
- self.model_path = os.path.join(models_path, self.name)
super().__init__()
model_paths = self.find_models(ext_filter=[".pt", ".pth"])
scalers = []
@@ -111,7 +109,7 @@ class UpscalerESRGAN(Upscaler): print("Unable to load %s from %s" % (self.model_path, filename))
return None
- pretrained_net = torch.load(filename, map_location='cpu' if shared.device.type == 'mps' else None)
+ pretrained_net = torch.load(filename, map_location='cpu' if devices.device_esrgan.type == 'mps' else None)
crt_model = arch.RRDBNet(3, 3, 64, 23, gc=32)
pretrained_net = fix_model_layers(crt_model, pretrained_net)
diff --git a/modules/esrgam_model_arch.py b/modules/esrgan_model_arch.py index e413d36e..e413d36e 100644 --- a/modules/esrgam_model_arch.py +++ b/modules/esrgan_model_arch.py diff --git a/modules/extras.py b/modules/extras.py index 1d9e64e5..41e8612c 100644 --- a/modules/extras.py +++ b/modules/extras.py @@ -29,7 +29,7 @@ def run_extras(extras_mode, image, image_folder, gfpgan_visibility, codeformer_v if extras_mode == 1:
#convert file to pillow image
for img in image_folder:
- image = Image.fromarray(np.array(Image.open(img)))
+ image = Image.open(img)
imageArr.append(image)
imageNameArr.append(os.path.splitext(img.orig_name)[0])
else:
@@ -98,6 +98,10 @@ def run_extras(extras_mode, image, image_folder, gfpgan_visibility, codeformer_v no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo,
forced_filename=image_name if opts.use_original_name_batch else None)
+ if opts.enable_pnginfo:
+ image.info = existing_pnginfo
+ image.info["extras"] = info
+
outputs.append(image)
devices.torch_gc()
@@ -169,9 +173,9 @@ def run_modelmerger(primary_model_name, secondary_model_name, interp_method, int print(f"Loading {secondary_model_info.filename}...")
secondary_model = torch.load(secondary_model_info.filename, map_location='cpu')
-
- theta_0 = primary_model['state_dict']
- theta_1 = secondary_model['state_dict']
+
+ theta_0 = sd_models.get_state_dict_from_checkpoint(primary_model)
+ theta_1 = sd_models.get_state_dict_from_checkpoint(secondary_model)
theta_funcs = {
"Weighted Sum": weighted_sum,
diff --git a/modules/hypernetwork.py b/modules/hypernetwork.py new file mode 100644 index 00000000..498bc9d8 --- /dev/null +++ b/modules/hypernetwork.py @@ -0,0 +1,98 @@ +import glob
+import os
+import sys
+import traceback
+
+import torch
+
+from ldm.util import default
+from modules import devices, shared
+import torch
+from torch import einsum
+from einops import rearrange, repeat
+
+
+class HypernetworkModule(torch.nn.Module):
+ def __init__(self, dim, state_dict):
+ super().__init__()
+
+ self.linear1 = torch.nn.Linear(dim, dim * 2)
+ self.linear2 = torch.nn.Linear(dim * 2, dim)
+
+ self.load_state_dict(state_dict, strict=True)
+ self.to(devices.device)
+
+ def forward(self, x):
+ return x + (self.linear2(self.linear1(x)))
+
+
+class Hypernetwork:
+ filename = None
+ name = None
+
+ def __init__(self, filename):
+ self.filename = filename
+ self.name = os.path.splitext(os.path.basename(filename))[0]
+ self.layers = {}
+
+ state_dict = torch.load(filename, map_location='cpu')
+ for size, sd in state_dict.items():
+ self.layers[size] = (HypernetworkModule(size, sd[0]), HypernetworkModule(size, sd[1]))
+
+
+def list_hypernetworks(path):
+ res = {}
+ for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True):
+ name = os.path.splitext(os.path.basename(filename))[0]
+ res[name] = filename
+ return res
+
+
+def load_hypernetwork(filename):
+ path = shared.hypernetworks.get(filename, None)
+ if path is not None:
+ print(f"Loading hypernetwork {filename}")
+ try:
+ shared.loaded_hypernetwork = Hypernetwork(path)
+ except Exception:
+ print(f"Error loading hypernetwork {path}", file=sys.stderr)
+ print(traceback.format_exc(), file=sys.stderr)
+ else:
+ if shared.loaded_hypernetwork is not None:
+ print(f"Unloading hypernetwork")
+
+ shared.loaded_hypernetwork = None
+
+
+def attention_CrossAttention_forward(self, x, context=None, mask=None):
+ h = self.heads
+
+ q = self.to_q(x)
+ context = default(context, x)
+
+ hypernetwork = shared.loaded_hypernetwork
+ hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
+
+ if hypernetwork_layers is not None:
+ k = self.to_k(hypernetwork_layers[0](context))
+ v = self.to_v(hypernetwork_layers[1](context))
+ else:
+ 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 mask is not None:
+ 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)
diff --git a/modules/images.py b/modules/images.py index 29c5ee24..c0a90676 100644 --- a/modules/images.py +++ b/modules/images.py @@ -349,6 +349,38 @@ def get_next_sequence_number(path, basename): def save_image(image, path, basename, seed=None, prompt=None, extension='png', info=None, short_filename=False, no_prompt=False, grid=False, pnginfo_section_name='parameters', p=None, existing_info=None, forced_filename=None, suffix="", save_to_dirs=None):
+ '''Save an image.
+
+ Args:
+ image (`PIL.Image`):
+ The image to be saved.
+ path (`str`):
+ The directory to save the image. Note, the option `save_to_dirs` will make the image to be saved into a sub directory.
+ basename (`str`):
+ The base filename which will be applied to `filename pattern`.
+ seed, prompt, short_filename,
+ extension (`str`):
+ Image file extension, default is `png`.
+ pngsectionname (`str`):
+ Specify the name of the section which `info` will be saved in.
+ info (`str` or `PngImagePlugin.iTXt`):
+ PNG info chunks.
+ existing_info (`dict`):
+ Additional PNG info. `existing_info == {pngsectionname: info, ...}`
+ no_prompt:
+ TODO I don't know its meaning.
+ p (`StableDiffusionProcessing`)
+ forced_filename (`str`):
+ If specified, `basename` and filename pattern will be ignored.
+ save_to_dirs (bool):
+ If true, the image will be saved into a subdirectory of `path`.
+
+ Returns: (fullfn, txt_fullfn)
+ fullfn (`str`):
+ The full path of the saved imaged.
+ txt_fullfn (`str` or None):
+ If a text file is saved for this image, this will be its full path. Otherwise None.
+ '''
if short_filename or prompt is None or seed is None:
file_decoration = ""
elif opts.save_to_dirs:
@@ -424,7 +456,10 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i piexif.insert(exif_bytes(), fullfn_without_extension + ".jpg")
if opts.save_txt and info is not None:
- with open(f"{fullfn_without_extension}.txt", "w", encoding="utf8") as file:
+ txt_fullfn = f"{fullfn_without_extension}.txt"
+ with open(txt_fullfn, "w", encoding="utf8") as file:
file.write(info + "\n")
+ else:
+ txt_fullfn = None
- return fullfn
+ return fullfn, txt_fullfn
diff --git a/modules/img2img.py b/modules/img2img.py index da212d72..24126774 100644 --- a/modules/img2img.py +++ b/modules/img2img.py @@ -32,6 +32,8 @@ def process_batch(p, input_dir, output_dir, args): for i, image in enumerate(images):
state.job = f"{i+1} out of {len(images)}"
+ if state.skipped:
+ state.skipped = False
if state.interrupted:
break
diff --git a/modules/interrogate.py b/modules/interrogate.py index eed87144..635e266e 100644 --- a/modules/interrogate.py +++ b/modules/interrogate.py @@ -140,11 +140,11 @@ class InterrogateModels: res = caption
- cilp_image = self.clip_preprocess(pil_image).unsqueeze(0).type(self.dtype).to(shared.device)
+ clip_image = self.clip_preprocess(pil_image).unsqueeze(0).type(self.dtype).to(shared.device)
precision_scope = torch.autocast if shared.cmd_opts.precision == "autocast" else contextlib.nullcontext
with torch.no_grad(), precision_scope("cuda"):
- image_features = self.clip_model.encode_image(cilp_image).type(self.dtype)
+ image_features = self.clip_model.encode_image(clip_image).type(self.dtype)
image_features /= image_features.norm(dim=-1, keepdim=True)
diff --git a/modules/ldsr_model.py b/modules/ldsr_model.py index 1c1070fc..8c4db44a 100644 --- a/modules/ldsr_model.py +++ b/modules/ldsr_model.py @@ -7,13 +7,11 @@ from basicsr.utils.download_util import load_file_from_url from modules.upscaler import Upscaler, UpscalerData from modules.ldsr_model_arch import LDSR from modules import shared -from modules.paths import models_path class UpscalerLDSR(Upscaler): def __init__(self, user_path): self.name = "LDSR" - self.model_path = os.path.join(models_path, self.name) self.user_path = user_path self.model_url = "https://heibox.uni-heidelberg.de/f/578df07c8fc04ffbadf3/?dl=1" self.yaml_url = "https://heibox.uni-heidelberg.de/f/31a76b13ea27482981b4/?dl=1" diff --git a/modules/paths.py b/modules/paths.py index 606f7d66..1e7a2fbc 100644 --- a/modules/paths.py +++ b/modules/paths.py @@ -1,6 +1,7 @@ import argparse
import os
import sys
+import modules.safe
script_path = os.path.dirname(os.path.dirname(os.path.realpath(__file__)))
models_path = os.path.join(script_path, "models")
@@ -12,6 +13,7 @@ possible_sd_paths = [os.path.join(script_path, 'repositories/stable-diffusion'), for possible_sd_path in possible_sd_paths:
if os.path.exists(os.path.join(possible_sd_path, 'ldm/models/diffusion/ddpm.py')):
sd_path = os.path.abspath(possible_sd_path)
+ break
assert sd_path is not None, "Couldn't find Stable Diffusion in any of: " + str(possible_sd_paths)
diff --git a/modules/processing.py b/modules/processing.py index f773a30e..94d2dd62 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -46,6 +46,12 @@ def apply_color_correction(correction, image): return image
+def get_correct_sampler(p):
+ if isinstance(p, modules.processing.StableDiffusionProcessingTxt2Img):
+ return sd_samplers.samplers
+ elif isinstance(p, modules.processing.StableDiffusionProcessingImg2Img):
+ return sd_samplers.samplers_for_img2img
+
class StableDiffusionProcessing:
def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt="", styles=None, seed=-1, subseed=-1, subseed_strength=0, seed_resize_from_h=-1, seed_resize_from_w=-1, seed_enable_extras=True, sampler_index=0, batch_size=1, n_iter=1, steps=50, cfg_scale=7.0, width=512, height=512, restore_faces=False, tiling=False, do_not_save_samples=False, do_not_save_grid=False, extra_generation_params=None, overlay_images=None, negative_prompt=None, eta=None):
self.sd_model = sd_model
@@ -123,6 +129,7 @@ class Processed: self.index_of_first_image = index_of_first_image
self.styles = p.styles
self.job_timestamp = state.job_timestamp
+ self.clip_skip = opts.CLIP_stop_at_last_layers
self.eta = p.eta
self.ddim_discretize = p.ddim_discretize
@@ -169,6 +176,7 @@ class Processed: "infotexts": self.infotexts,
"styles": self.styles,
"job_timestamp": self.job_timestamp,
+ "clip_skip": self.clip_skip,
}
return json.dumps(obj)
@@ -266,14 +274,18 @@ def fix_seed(p): def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration=0, position_in_batch=0):
index = position_in_batch + iteration * p.batch_size
+ clip_skip = getattr(p, 'clip_skip', opts.CLIP_stop_at_last_layers)
+
generation_params = {
"Steps": p.steps,
- "Sampler": sd_samplers.samplers[p.sampler_index].name,
+ "Sampler": get_correct_sampler(p)[p.sampler_index].name,
"CFG scale": p.cfg_scale,
"Seed": all_seeds[index],
"Face restoration": (opts.face_restoration_model if p.restore_faces else None),
"Size": f"{p.width}x{p.height}",
"Model hash": getattr(p, 'sd_model_hash', None if not opts.add_model_hash_to_info or not shared.sd_model.sd_model_hash else shared.sd_model.sd_model_hash),
+ "Model": (None if not opts.add_model_name_to_info or not shared.sd_model.sd_checkpoint_info.model_name else shared.sd_model.sd_checkpoint_info.model_name.replace(',', '').replace(':', '')),
+ "Hypernet": (None if shared.loaded_hypernetwork is None else shared.loaded_hypernetwork.name.replace(',', '').replace(':', '')),
"Batch size": (None if p.batch_size < 2 else p.batch_size),
"Batch pos": (None if p.batch_size < 2 else position_in_batch),
"Variation seed": (None if p.subseed_strength == 0 else all_subseeds[index]),
@@ -281,6 +293,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration "Seed resize from": (None if p.seed_resize_from_w == 0 or p.seed_resize_from_h == 0 else f"{p.seed_resize_from_w}x{p.seed_resize_from_h}"),
"Denoising strength": getattr(p, 'denoising_strength', None),
"Eta": (None if p.sampler is None or p.sampler.eta == p.sampler.default_eta else p.sampler.eta),
+ "Clip skip": None if clip_skip <= 1 else clip_skip,
}
generation_params.update(p.extra_generation_params)
@@ -312,6 +325,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed: os.makedirs(p.outpath_grids, exist_ok=True)
modules.sd_hijack.model_hijack.apply_circular(p.tiling)
+ modules.sd_hijack.model_hijack.clear_comments()
comments = {}
@@ -341,7 +355,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed: infotexts = []
output_images = []
- with torch.no_grad():
+ with torch.no_grad(), p.sd_model.ema_scope():
with devices.autocast():
p.init(all_prompts, all_seeds, all_subseeds)
@@ -349,6 +363,9 @@ def process_images(p: StableDiffusionProcessing) -> Processed: state.job_count = p.n_iter
for n in range(p.n_iter):
+ if state.skipped:
+ state.skipped = False
+
if state.interrupted:
break
@@ -375,9 +392,9 @@ def process_images(p: StableDiffusionProcessing) -> Processed: with devices.autocast():
samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength)
- if state.interrupted:
+ if state.interrupted or state.skipped:
- # if we are interruped, sample returns just noise
+ # if we are interrupted, sample returns just noise
# use the image collected previously in sampler loop
samples_ddim = shared.state.current_latent
@@ -436,7 +453,8 @@ def process_images(p: StableDiffusionProcessing) -> Processed: text = infotext(n, i)
infotexts.append(text)
- image.info["parameters"] = text
+ if opts.enable_pnginfo:
+ image.info["parameters"] = text
output_images.append(image)
del x_samples_ddim
@@ -455,7 +473,8 @@ def process_images(p: StableDiffusionProcessing) -> Processed: if opts.return_grid:
text = infotext()
infotexts.insert(0, text)
- grid.info["parameters"] = text
+ if opts.enable_pnginfo:
+ grid.info["parameters"] = text
output_images.insert(0, grid)
index_of_first_image = 1
diff --git a/modules/prompt_parser.py b/modules/prompt_parser.py index f00256f2..919d5d31 100644 --- a/modules/prompt_parser.py +++ b/modules/prompt_parser.py @@ -13,13 +13,14 @@ import lark schedule_parser = lark.Lark(r"""
!start: (prompt | /[][():]/+)*
-prompt: (emphasized | scheduled | plain | WHITESPACE)*
+prompt: (emphasized | scheduled | alternate | plain | WHITESPACE)*
!emphasized: "(" prompt ")"
| "(" prompt ":" prompt ")"
| "[" prompt "]"
scheduled: "[" [prompt ":"] prompt ":" [WHITESPACE] NUMBER "]"
+alternate: "[" prompt ("|" prompt)+ "]"
WHITESPACE: /\s+/
-plain: /([^\\\[\]():]|\\.)+/
+plain: /([^\\\[\]():|]|\\.)+/
%import common.SIGNED_NUMBER -> NUMBER
""")
@@ -59,6 +60,8 @@ def get_learned_conditioning_prompt_schedules(prompts, steps): tree.children[-1] *= steps
tree.children[-1] = min(steps, int(tree.children[-1]))
l.append(tree.children[-1])
+ def alternate(self, tree):
+ l.extend(range(1, steps+1))
CollectSteps().visit(tree)
return sorted(set(l))
@@ -67,6 +70,8 @@ def get_learned_conditioning_prompt_schedules(prompts, steps): def scheduled(self, args):
before, after, _, when = args
yield before or () if step <= when else after
+ def alternate(self, args):
+ yield next(args[(step - 1)%len(args)])
def start(self, args):
def flatten(x):
if type(x) == str:
@@ -239,6 +244,15 @@ def reconstruct_multicond_batch(c: MulticondLearnedConditioning, current_step): conds_list.append(conds_for_batch)
+ # if prompts have wildly different lengths above the limit we'll get tensors fo different shapes
+ # and won't be able to torch.stack them. So this fixes that.
+ token_count = max([x.shape[0] for x in tensors])
+ for i in range(len(tensors)):
+ if tensors[i].shape[0] != token_count:
+ last_vector = tensors[i][-1:]
+ last_vector_repeated = last_vector.repeat([token_count - tensors[i].shape[0], 1])
+ tensors[i] = torch.vstack([tensors[i], last_vector_repeated])
+
return conds_list, torch.stack(tensors).to(device=param.device, dtype=param.dtype)
diff --git a/modules/realesrgan_model.py b/modules/realesrgan_model.py index dc0123e0..3ac0b97a 100644 --- a/modules/realesrgan_model.py +++ b/modules/realesrgan_model.py @@ -8,14 +8,12 @@ from basicsr.utils.download_util import load_file_from_url from realesrgan import RealESRGANer
from modules.upscaler import Upscaler, UpscalerData
-from modules.paths import models_path
from modules.shared import cmd_opts, opts
class UpscalerRealESRGAN(Upscaler):
def __init__(self, path):
self.name = "RealESRGAN"
- self.model_path = os.path.join(models_path, self.name)
self.user_path = path
super().__init__()
try:
diff --git a/modules/safe.py b/modules/safe.py new file mode 100644 index 00000000..05917463 --- /dev/null +++ b/modules/safe.py @@ -0,0 +1,93 @@ +# this code is adapted from the script contributed by anon from /h/
+
+import io
+import pickle
+import collections
+import sys
+import traceback
+
+import torch
+import numpy
+import _codecs
+import zipfile
+
+
+# PyTorch 1.13 and later have _TypedStorage renamed to TypedStorage
+TypedStorage = torch.storage.TypedStorage if hasattr(torch.storage, 'TypedStorage') else torch.storage._TypedStorage
+
+
+def encode(*args):
+ out = _codecs.encode(*args)
+ return out
+
+
+class RestrictedUnpickler(pickle.Unpickler):
+ def persistent_load(self, saved_id):
+ assert saved_id[0] == 'storage'
+ return TypedStorage()
+
+ def find_class(self, module, name):
+ if module == 'collections' and name == 'OrderedDict':
+ return getattr(collections, name)
+ if module == 'torch._utils' and name in ['_rebuild_tensor_v2', '_rebuild_parameter']:
+ return getattr(torch._utils, name)
+ if module == 'torch' and name in ['FloatStorage', 'HalfStorage', 'IntStorage', 'LongStorage', 'DoubleStorage']:
+ return getattr(torch, name)
+ if module == 'torch.nn.modules.container' and name in ['ParameterDict']:
+ return getattr(torch.nn.modules.container, name)
+ if module == 'numpy.core.multiarray' and name == 'scalar':
+ return numpy.core.multiarray.scalar
+ if module == 'numpy' and name == 'dtype':
+ return numpy.dtype
+ if module == '_codecs' and name == 'encode':
+ return encode
+ if module == "pytorch_lightning.callbacks" and name == 'model_checkpoint':
+ import pytorch_lightning.callbacks
+ return pytorch_lightning.callbacks.model_checkpoint
+ if module == "pytorch_lightning.callbacks.model_checkpoint" and name == 'ModelCheckpoint':
+ import pytorch_lightning.callbacks.model_checkpoint
+ return pytorch_lightning.callbacks.model_checkpoint.ModelCheckpoint
+ if module == "__builtin__" and name == 'set':
+ return set
+
+ # Forbid everything else.
+ raise pickle.UnpicklingError(f"global '{module}/{name}' is forbidden")
+
+
+def check_pt(filename):
+ try:
+
+ # new pytorch format is a zip file
+ with zipfile.ZipFile(filename) as z:
+ with z.open('archive/data.pkl') as file:
+ unpickler = RestrictedUnpickler(file)
+ unpickler.load()
+
+ except zipfile.BadZipfile:
+
+ # if it's not a zip file, it's an olf pytorch format, with five objects written to pickle
+ with open(filename, "rb") as file:
+ unpickler = RestrictedUnpickler(file)
+ for i in range(5):
+ unpickler.load()
+
+
+def load(filename, *args, **kwargs):
+ from modules import shared
+
+ try:
+ if not shared.cmd_opts.disable_safe_unpickle:
+ check_pt(filename)
+
+ except Exception:
+ print(f"Error verifying pickled file from {filename}:", file=sys.stderr)
+ print(traceback.format_exc(), file=sys.stderr)
+ print(f"\nThe file may be malicious, so the program is not going to read it.", file=sys.stderr)
+ print(f"You can skip this check with --disable-safe-unpickle commandline argument.", file=sys.stderr)
+ return None
+
+ return unsafe_torch_load(filename, *args, **kwargs)
+
+
+unsafe_torch_load = torch.load
+torch.load = load
diff --git a/modules/scunet_model.py b/modules/scunet_model.py index fb64b740..36a996bf 100644 --- a/modules/scunet_model.py +++ b/modules/scunet_model.py @@ -9,14 +9,12 @@ from basicsr.utils.download_util import load_file_from_url import modules.upscaler from modules import devices, modelloader -from modules.paths import models_path from modules.scunet_model_arch import SCUNet as net class UpscalerScuNET(modules.upscaler.Upscaler): def __init__(self, dirname): self.name = "ScuNET" - self.model_path = os.path.join(models_path, self.name) self.model_name = "ScuNET GAN" self.model_name2 = "ScuNET PSNR" self.model_url = "https://github.com/cszn/KAIR/releases/download/v1.0/scunet_color_real_gan.pth" diff --git a/modules/scunet_model_arch.py b/modules/scunet_model_arch.py index 972a2639..43ca8d36 100644 --- a/modules/scunet_model_arch.py +++ b/modules/scunet_model_arch.py @@ -40,7 +40,7 @@ class WMSA(nn.Module): Returns: attn_mask: should be (1 1 w p p), """ - # supporting sqaure. + # supporting square. attn_mask = torch.zeros(h, w, p, p, p, p, dtype=torch.bool, device=self.relative_position_params.device) if self.type == 'W': return attn_mask @@ -65,7 +65,7 @@ class WMSA(nn.Module): x = rearrange(x, 'b (w1 p1) (w2 p2) c -> b w1 w2 p1 p2 c', p1=self.window_size, p2=self.window_size) h_windows = x.size(1) w_windows = x.size(2) - # sqaure validation + # square validation # assert h_windows == w_windows x = rearrange(x, 'b w1 w2 p1 p2 c -> b (w1 w2) (p1 p2) c', p1=self.window_size, p2=self.window_size) diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index a6fa890c..437acce4 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -8,7 +8,7 @@ from torch import einsum from torch.nn.functional import silu
import modules.textual_inversion.textual_inversion
-from modules import prompt_parser, devices, sd_hijack_optimizations, shared
+from modules import prompt_parser, devices, sd_hijack_optimizations, shared, hypernetwork
from modules.shared import opts, device, cmd_opts
import ldm.modules.attention
@@ -18,23 +18,37 @@ attention_CrossAttention_forward = ldm.modules.attention.CrossAttention.forward diffusionmodules_model_nonlinearity = ldm.modules.diffusionmodules.model.nonlinearity
diffusionmodules_model_AttnBlock_forward = ldm.modules.diffusionmodules.model.AttnBlock.forward
-
def apply_optimizations():
+ undo_optimizations()
+
ldm.modules.diffusionmodules.model.nonlinearity = silu
- if cmd_opts.opt_split_attention_v1:
+ if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and torch.cuda.get_device_capability(shared.device) == (8, 6)):
+ print("Applying xformers cross attention optimization.")
+ ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.xformers_attention_forward
+ ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.xformers_attnblock_forward
+ elif cmd_opts.opt_split_attention_v1:
+ print("Applying v1 cross attention optimization.")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_v1
elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention or torch.cuda.is_available()):
+ print("Applying cross attention optimization.")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.cross_attention_attnblock_forward
def undo_optimizations():
- ldm.modules.attention.CrossAttention.forward = attention_CrossAttention_forward
+ ldm.modules.attention.CrossAttention.forward = hypernetwork.attention_CrossAttention_forward
ldm.modules.diffusionmodules.model.nonlinearity = diffusionmodules_model_nonlinearity
ldm.modules.diffusionmodules.model.AttnBlock.forward = diffusionmodules_model_AttnBlock_forward
+def get_target_prompt_token_count(token_count):
+ if token_count < 75:
+ return 75
+
+ return math.ceil(token_count / 10) * 10
+
+
class StableDiffusionModelHijack:
fixes = None
comments = []
@@ -80,10 +94,12 @@ class StableDiffusionModelHijack: for layer in [layer for layer in self.layers if type(layer) == torch.nn.Conv2d]:
layer.padding_mode = 'circular' if enable else 'zeros'
+ def clear_comments(self):
+ self.comments = []
+
def tokenize(self, text):
- max_length = self.clip.max_length - 2
_, remade_batch_tokens, _, _, _, token_count = self.clip.process_text([text])
- return remade_batch_tokens[0], token_count, max_length
+ return remade_batch_tokens[0], token_count, get_target_prompt_token_count(token_count)
class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
@@ -92,7 +108,6 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): self.wrapped = wrapped
self.hijack: StableDiffusionModelHijack = hijack
self.tokenizer = wrapped.tokenizer
- self.max_length = wrapped.max_length
self.token_mults = {}
tokens_with_parens = [(k, v) for k, v in self.tokenizer.get_vocab().items() if '(' in k or ')' in k or '[' in k or ']' in k]
@@ -114,7 +129,6 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): def tokenize_line(self, line, used_custom_terms, hijack_comments):
id_start = self.wrapped.tokenizer.bos_token_id
id_end = self.wrapped.tokenizer.eos_token_id
- maxlen = self.wrapped.max_length
if opts.enable_emphasis:
parsed = prompt_parser.parse_prompt_attention(line)
@@ -146,19 +160,12 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): used_custom_terms.append((embedding.name, embedding.checksum()))
i += embedding_length_in_tokens
- if len(remade_tokens) > maxlen - 2:
- vocab = {v: k for k, v in self.wrapped.tokenizer.get_vocab().items()}
- ovf = remade_tokens[maxlen - 2:]
- overflowing_words = [vocab.get(int(x), "") for x in ovf]
- overflowing_text = self.wrapped.tokenizer.convert_tokens_to_string(''.join(overflowing_words))
- hijack_comments.append(f"Warning: too many input tokens; some ({len(overflowing_words)}) have been truncated:\n{overflowing_text}\n")
-
token_count = len(remade_tokens)
- remade_tokens = remade_tokens + [id_end] * (maxlen - 2 - len(remade_tokens))
- remade_tokens = [id_start] + remade_tokens[0:maxlen - 2] + [id_end]
+ prompt_target_length = get_target_prompt_token_count(token_count)
+ tokens_to_add = prompt_target_length - len(remade_tokens) + 1
- multipliers = multipliers + [1.0] * (maxlen - 2 - len(multipliers))
- multipliers = [1.0] + multipliers[0:maxlen - 2] + [1.0]
+ remade_tokens = [id_start] + remade_tokens + [id_end] * tokens_to_add
+ multipliers = [1.0] + multipliers + [1.0] * tokens_to_add
return remade_tokens, fixes, multipliers, token_count
@@ -175,7 +182,8 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): if line in cache:
remade_tokens, fixes, multipliers = cache[line]
else:
- remade_tokens, fixes, multipliers, token_count = self.tokenize_line(line, used_custom_terms, hijack_comments)
+ remade_tokens, fixes, multipliers, current_token_count = self.tokenize_line(line, used_custom_terms, hijack_comments)
+ token_count = max(current_token_count, token_count)
cache[line] = (remade_tokens, fixes, multipliers)
@@ -189,7 +197,7 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): def process_text_old(self, text):
id_start = self.wrapped.tokenizer.bos_token_id
id_end = self.wrapped.tokenizer.eos_token_id
- maxlen = self.wrapped.max_length
+ maxlen = self.wrapped.max_length # you get to stay at 77
used_custom_terms = []
remade_batch_tokens = []
overflowing_words = []
@@ -261,17 +269,29 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module): batch_multipliers, remade_batch_tokens, used_custom_terms, hijack_comments, hijack_fixes, token_count = self.process_text(text)
self.hijack.fixes = hijack_fixes
- self.hijack.comments = hijack_comments
+ self.hijack.comments += hijack_comments
if len(used_custom_terms) > 0:
self.hijack.comments.append("Used embeddings: " + ", ".join([f'{word} [{checksum}]' for word, checksum in used_custom_terms]))
- tokens = torch.asarray(remade_batch_tokens).to(device)
- outputs = self.wrapped.transformer(input_ids=tokens)
- z = outputs.last_hidden_state
+ target_token_count = get_target_prompt_token_count(token_count) + 2
+
+ position_ids_array = [min(x, 75) for x in range(target_token_count-1)] + [76]
+ position_ids = torch.asarray(position_ids_array, device=devices.device).expand((1, -1))
+
+ remade_batch_tokens_of_same_length = [x + [self.wrapped.tokenizer.eos_token_id] * (target_token_count - len(x)) for x in remade_batch_tokens]
+ tokens = torch.asarray(remade_batch_tokens_of_same_length).to(device)
+
+ outputs = self.wrapped.transformer(input_ids=tokens, position_ids=position_ids, output_hidden_states=-opts.CLIP_stop_at_last_layers)
+ if opts.CLIP_stop_at_last_layers > 1:
+ z = outputs.hidden_states[-opts.CLIP_stop_at_last_layers]
+ z = self.wrapped.transformer.text_model.final_layer_norm(z)
+ else:
+ z = outputs.last_hidden_state
# restoring original mean is likely not correct, but it seems to work well to prevent artifacts that happen otherwise
- batch_multipliers = torch.asarray(batch_multipliers).to(device)
+ batch_multipliers_of_same_length = [x + [1.0] * (target_token_count - len(x)) for x in batch_multipliers]
+ batch_multipliers = torch.asarray(batch_multipliers_of_same_length).to(device)
original_mean = z.mean()
z *= batch_multipliers.reshape(batch_multipliers.shape + (1,)).expand(z.shape)
new_mean = z.mean()
diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py index ea4cfdfc..634fb4b2 100644 --- a/modules/sd_hijack_optimizations.py +++ b/modules/sd_hijack_optimizations.py @@ -1,22 +1,46 @@ import math
+import sys
+import traceback
+
import torch
from torch import einsum
from ldm.util import default
from einops import rearrange
+from modules import shared
+
+if shared.cmd_opts.xformers or shared.cmd_opts.force_enable_xformers:
+ try:
+ import xformers.ops
+ import functorch
+ xformers._is_functorch_available = True
+ shared.xformers_available = True
+ except Exception:
+ print("Cannot import xformers", file=sys.stderr)
+ print(traceback.format_exc(), file=sys.stderr)
+
# see https://github.com/basujindal/stable-diffusion/pull/117 for discussion
def split_cross_attention_forward_v1(self, x, context=None, mask=None):
h = self.heads
- q = self.to_q(x)
+ q_in = self.to_q(x)
context = default(context, x)
- k = self.to_k(context)
- v = self.to_v(context)
+
+ hypernetwork = shared.loaded_hypernetwork
+ hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
+
+ if hypernetwork_layers is not None:
+ k_in = self.to_k(hypernetwork_layers[0](context))
+ v_in = self.to_v(hypernetwork_layers[1](context))
+ else:
+ k_in = self.to_k(context)
+ v_in = self.to_v(context)
del context, x
- q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v))
+ q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (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)
for i in range(0, q.shape[0], 2):
@@ -29,6 +53,7 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None): r1[i:end] = einsum('b i j, b j d -> b i d', s2, v[i:end])
del s2
+ del q, k, v
r2 = rearrange(r1, '(b h) n d -> b n (h d)', h=h)
del r1
@@ -42,8 +67,19 @@ def split_cross_attention_forward(self, x, context=None, mask=None): q_in = self.to_q(x)
context = default(context, x)
- k_in = self.to_k(context) * self.scale
- v_in = self.to_v(context)
+
+ hypernetwork = shared.loaded_hypernetwork
+ hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
+
+ if hypernetwork_layers is not None:
+ k_in = self.to_k(hypernetwork_layers[0](context))
+ v_in = self.to_v(hypernetwork_layers[1](context))
+ else:
+ k_in = self.to_k(context)
+ v_in = self.to_v(context)
+
+ k_in *= self.scale
+
del context, x
q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q_in, k_in, v_in))
@@ -92,6 +128,25 @@ def split_cross_attention_forward(self, x, context=None, mask=None): return self.to_out(r2)
+def xformers_attention_forward(self, x, context=None, mask=None):
+ h = self.heads
+ q_in = self.to_q(x)
+ context = default(context, x)
+ hypernetwork = shared.loaded_hypernetwork
+ hypernetwork_layers = (hypernetwork.layers if hypernetwork is not None else {}).get(context.shape[2], None)
+ if hypernetwork_layers is not None:
+ k_in = self.to_k(hypernetwork_layers[0](context))
+ v_in = self.to_v(hypernetwork_layers[1](context))
+ else:
+ k_in = self.to_k(context)
+ v_in = self.to_v(context)
+ q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b n h d', h=h), (q_in, k_in, v_in))
+ del q_in, k_in, v_in
+ out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None)
+
+ out = rearrange(out, 'b n h d -> b n (h d)', h=h)
+ return self.to_out(out)
+
def cross_attention_attnblock_forward(self, x):
h_ = x
h_ = self.norm(h_)
@@ -154,3 +209,16 @@ def cross_attention_attnblock_forward(self, x): h3 += x
return h3
+
+def xformers_attnblock_forward(self, x):
+ try:
+ h_ = x
+ h_ = self.norm(h_)
+ q1 = self.q(h_).contiguous()
+ k1 = self.k(h_).contiguous()
+ v = self.v(h_).contiguous()
+ out = xformers.ops.memory_efficient_attention(q1, k1, v)
+ out = self.proj_out(out)
+ return x + out
+ except NotImplementedError:
+ return cross_attention_attnblock_forward(self, x)
diff --git a/modules/sd_models.py b/modules/sd_models.py index 5f992064..e63d3c29 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -5,7 +5,6 @@ from collections import namedtuple import torch
from omegaconf import OmegaConf
-
from ldm.util import instantiate_from_config
from modules import shared, modelloader, devices
@@ -14,7 +13,7 @@ from modules.paths import models_path model_dir = "Stable-diffusion"
model_path = os.path.abspath(os.path.join(models_path, model_dir))
-CheckpointInfo = namedtuple("CheckpointInfo", ['filename', 'title', 'hash', 'model_name'])
+CheckpointInfo = namedtuple("CheckpointInfo", ['filename', 'title', 'hash', 'model_name', 'config'])
checkpoints_list = {}
try:
@@ -63,14 +62,20 @@ def list_models(): if os.path.exists(cmd_ckpt):
h = model_hash(cmd_ckpt)
title, short_model_name = modeltitle(cmd_ckpt, h)
- checkpoints_list[title] = CheckpointInfo(cmd_ckpt, title, h, short_model_name)
+ checkpoints_list[title] = CheckpointInfo(cmd_ckpt, title, h, short_model_name, shared.cmd_opts.config)
shared.opts.data['sd_model_checkpoint'] = title
elif cmd_ckpt is not None and cmd_ckpt != shared.default_sd_model_file:
print(f"Checkpoint in --ckpt argument not found (Possible it was moved to {model_path}: {cmd_ckpt}", file=sys.stderr)
for filename in model_list:
h = model_hash(filename)
title, short_model_name = modeltitle(filename, h)
- checkpoints_list[title] = CheckpointInfo(filename, title, h, short_model_name)
+
+ basename, _ = os.path.splitext(filename)
+ config = basename + ".yaml"
+ if not os.path.exists(config):
+ config = shared.cmd_opts.config
+
+ checkpoints_list[title] = CheckpointInfo(filename, title, h, short_model_name, config)
def get_closet_checkpoint_match(searchString):
@@ -116,13 +121,24 @@ def select_checkpoint(): return checkpoint_info
-def load_model_weights(model, checkpoint_file, sd_model_hash):
+def get_state_dict_from_checkpoint(pl_sd):
+ if "state_dict" in pl_sd:
+ return pl_sd["state_dict"]
+
+ return pl_sd
+
+
+def load_model_weights(model, checkpoint_info):
+ checkpoint_file = checkpoint_info.filename
+ sd_model_hash = checkpoint_info.hash
+
print(f"Loading weights [{sd_model_hash}] from {checkpoint_file}")
pl_sd = torch.load(checkpoint_file, map_location="cpu")
if "global_step" in pl_sd:
print(f"Global Step: {pl_sd['global_step']}")
- sd = pl_sd["state_dict"]
+
+ sd = get_state_dict_from_checkpoint(pl_sd)
model.load_state_dict(sd, strict=False)
@@ -134,17 +150,29 @@ def load_model_weights(model, checkpoint_file, sd_model_hash): devices.dtype = torch.float32 if shared.cmd_opts.no_half else torch.float16
+ vae_file = os.path.splitext(checkpoint_file)[0] + ".vae.pt"
+ if os.path.exists(vae_file):
+ print(f"Loading VAE weights from: {vae_file}")
+ vae_ckpt = torch.load(vae_file, map_location="cpu")
+ vae_dict = {k: v for k, v in vae_ckpt["state_dict"].items() if k[0:4] != "loss"}
+
+ model.first_stage_model.load_state_dict(vae_dict)
+
model.sd_model_hash = sd_model_hash
- model.sd_model_checkpint = checkpoint_file
+ model.sd_model_checkpoint = checkpoint_file
+ model.sd_checkpoint_info = checkpoint_info
def load_model():
from modules import lowvram, sd_hijack
checkpoint_info = select_checkpoint()
- sd_config = OmegaConf.load(shared.cmd_opts.config)
+ if checkpoint_info.config != shared.cmd_opts.config:
+ print(f"Loading config from: {checkpoint_info.config}")
+
+ sd_config = OmegaConf.load(checkpoint_info.config)
sd_model = instantiate_from_config(sd_config.model)
- load_model_weights(sd_model, checkpoint_info.filename, checkpoint_info.hash)
+ load_model_weights(sd_model, checkpoint_info)
if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
lowvram.setup_for_low_vram(sd_model, shared.cmd_opts.medvram)
@@ -163,9 +191,13 @@ def reload_model_weights(sd_model, info=None): from modules import lowvram, devices, sd_hijack
checkpoint_info = info or select_checkpoint()
- if sd_model.sd_model_checkpint == checkpoint_info.filename:
+ if sd_model.sd_model_checkpoint == checkpoint_info.filename:
return
+ if sd_model.sd_checkpoint_info.config != checkpoint_info.config:
+ shared.sd_model = load_model()
+ return shared.sd_model
+
if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
lowvram.send_everything_to_cpu()
else:
@@ -173,7 +205,7 @@ def reload_model_weights(sd_model, info=None): sd_hijack.model_hijack.undo_hijack(sd_model)
- load_model_weights(sd_model, checkpoint_info.filename, checkpoint_info.hash)
+ load_model_weights(sd_model, checkpoint_info)
sd_hijack.model_hijack.hijack(sd_model)
diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index df17e93c..6e743f7e 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -106,7 +106,7 @@ def extended_tdqm(sequence, *args, desc=None, **kwargs): seq = sequence if cmd_opts.disable_console_progressbars else tqdm.tqdm(sequence, *args, desc=state.job, file=shared.progress_print_out, **kwargs)
for x in seq:
- if state.interrupted:
+ if state.interrupted or state.skipped:
break
yield x
@@ -142,6 +142,16 @@ class VanillaStableDiffusionSampler: assert all([len(conds) == 1 for conds in conds_list]), 'composition via AND is not supported for DDIM/PLMS samplers'
cond = tensor
+ # for DDIM, shapes must match, we can't just process cond and uncond independently;
+ # filling unconditional_conditioning with repeats of the last vector to match length is
+ # not 100% correct but should work well enough
+ if unconditional_conditioning.shape[1] < cond.shape[1]:
+ last_vector = unconditional_conditioning[:, -1:]
+ last_vector_repeated = last_vector.repeat([1, cond.shape[1] - unconditional_conditioning.shape[1], 1])
+ unconditional_conditioning = torch.hstack([unconditional_conditioning, last_vector_repeated])
+ elif unconditional_conditioning.shape[1] > cond.shape[1]:
+ unconditional_conditioning = unconditional_conditioning[:, :cond.shape[1]]
+
if self.mask is not None:
img_orig = self.sampler.model.q_sample(self.init_latent, ts)
x_dec = img_orig * self.mask + self.nmask * x_dec
@@ -171,7 +181,7 @@ class VanillaStableDiffusionSampler: self.initialize(p)
- # existing code fails with cetain step counts, like 9
+ # existing code fails with certain step counts, like 9
try:
self.sampler.make_schedule(ddim_num_steps=steps, ddim_eta=self.eta, ddim_discretize=p.ddim_discretize, verbose=False)
except Exception:
@@ -194,7 +204,7 @@ class VanillaStableDiffusionSampler: steps = steps or p.steps
- # existing code fails with cetin step counts, like 9
+ # existing code fails with certain step counts, like 9
try:
samples_ddim, _ = self.sampler.sample(S=steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)
except Exception:
@@ -221,18 +231,29 @@ class CFGDenoiser(torch.nn.Module): x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma])
- cond_in = torch.cat([tensor, uncond])
- if shared.batch_cond_uncond:
- x_out = self.inner_model(x_in, sigma_in, cond=cond_in)
+ if tensor.shape[1] == uncond.shape[1]:
+ cond_in = torch.cat([tensor, uncond])
+
+ if shared.batch_cond_uncond:
+ x_out = self.inner_model(x_in, sigma_in, cond=cond_in)
+ else:
+ x_out = torch.zeros_like(x_in)
+ for batch_offset in range(0, x_out.shape[0], batch_size):
+ a = batch_offset
+ b = a + batch_size
+ x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=cond_in[a:b])
else:
x_out = torch.zeros_like(x_in)
- for batch_offset in range(0, x_out.shape[0], batch_size):
+ batch_size = batch_size*2 if shared.batch_cond_uncond else batch_size
+ for batch_offset in range(0, tensor.shape[0], batch_size):
a = batch_offset
- b = a + batch_size
- x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=cond_in[a:b])
+ b = min(a + batch_size, tensor.shape[0])
+ x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=tensor[a:b])
+
+ x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond=uncond)
- denoised_uncond = x_out[-batch_size:]
+ denoised_uncond = x_out[-uncond.shape[0]:]
denoised = torch.clone(denoised_uncond)
for i, conds in enumerate(conds_list):
@@ -254,7 +275,7 @@ def extended_trange(sampler, count, *args, **kwargs): seq = range(count) if cmd_opts.disable_console_progressbars else tqdm.trange(count, *args, desc=state.job, file=shared.progress_print_out, **kwargs)
for x in seq:
- if state.interrupted:
+ if state.interrupted or state.skipped:
break
if sampler.stop_at is not None and x > sampler.stop_at:
diff --git a/modules/shared.py b/modules/shared.py index 25bb6e6c..1995a99a 100644 --- a/modules/shared.py +++ b/modules/shared.py @@ -13,7 +13,7 @@ import modules.memmon import modules.sd_models
import modules.styles
import modules.devices as devices
-from modules import sd_samplers
+from modules import sd_samplers, hypernetwork
from modules.paths import models_path, script_path, sd_path
sd_model_file = os.path.join(script_path, 'model.ckpt')
@@ -43,6 +43,9 @@ parser.add_argument("--realesrgan-models-path", type=str, help="Path to director parser.add_argument("--scunet-models-path", type=str, help="Path to directory with ScuNET model file(s).", default=os.path.join(models_path, 'ScuNET'))
parser.add_argument("--swinir-models-path", type=str, help="Path to directory with SwinIR model file(s).", default=os.path.join(models_path, 'SwinIR'))
parser.add_argument("--ldsr-models-path", type=str, help="Path to directory with LDSR model file(s).", default=os.path.join(models_path, 'LDSR'))
+parser.add_argument("--xformers", action='store_true', help="enable xformers for cross attention layers")
+parser.add_argument("--force-enable-xformers", action='store_true', help="enable xformers for cross attention layers regardless of whether the checking code thinks you can run it; do not make bug reports if this fails to work")
+parser.add_argument("--deepdanbooru", action='store_true', help="enable deepdanbooru interrogator")
parser.add_argument("--opt-split-attention", action='store_true', help="force-enables cross-attention layer optimization. By default, it's on for torch.cuda and off for other torch devices.")
parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
parser.add_argument("--opt-split-attention-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find")
@@ -62,6 +65,7 @@ parser.add_argument("--autolaunch", action='store_true', help="open the webui UR parser.add_argument("--use-textbox-seed", action='store_true', help="use textbox for seeds in UI (no up/down, but possible to input long seeds)", default=False)
parser.add_argument("--disable-console-progressbars", action='store_true', help="do not output progressbars to console", default=False)
parser.add_argument("--enable-console-prompts", action='store_true', help="print prompts to console when generating with txt2img and img2img", default=False)
+parser.add_argument("--disable-safe-unpickle", action='store_true', help="disable checking pytorch models for malicious code", default=False)
cmd_opts = parser.parse_args()
@@ -73,11 +77,15 @@ device = devices.device batch_cond_uncond = cmd_opts.always_batch_cond_uncond or not (cmd_opts.lowvram or cmd_opts.medvram)
parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram
-
+xformers_available = False
config_filename = cmd_opts.ui_settings_file
+hypernetworks = hypernetwork.list_hypernetworks(os.path.join(models_path, 'hypernetworks'))
+loaded_hypernetwork = None
+
class State:
+ skipped = False
interrupted = False
job = ""
job_no = 0
@@ -90,6 +98,9 @@ class State: current_image_sampling_step = 0
textinfo = None
+ def skip(self):
+ self.skipped = True
+
def interrupt(self):
self.interrupted = True
@@ -112,8 +123,6 @@ prompt_styles = modules.styles.StyleDatabase(styles_filename) interrogator = modules.interrogate.InterrogateModels("interrogate")
face_restorers = []
-# This was moved to webui.py with the other model "setup" calls.
-# modules.sd_models.list_models()
def realesrgan_models_names():
@@ -122,18 +131,19 @@ def realesrgan_models_names(): class OptionInfo:
- def __init__(self, default=None, label="", component=None, component_args=None, onchange=None):
+ def __init__(self, default=None, label="", component=None, component_args=None, onchange=None, show_on_main_page=False):
self.default = default
self.label = label
self.component = component
self.component_args = component_args
self.onchange = onchange
self.section = None
+ self.show_on_main_page = show_on_main_page
-def options_section(section_identifer, options_dict):
+def options_section(section_identifier, options_dict):
for k, v in options_dict.items():
- v.section = section_identifer
+ v.section = section_identifier
return options_dict
@@ -205,7 +215,8 @@ options_templates.update(options_section(('system', "System"), { }))
options_templates.update(options_section(('sd', "Stable Diffusion"), {
- "sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": modules.sd_models.checkpoint_tiles()}),
+ "sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, show_on_main_page=True),
+ "sd_hypernetwork": OptionInfo("None", "Stable Diffusion finetune hypernetwork", gr.Dropdown, lambda: {"choices": ["None"] + [x for x in hypernetworks.keys()]}),
"img2img_color_correction": OptionInfo(False, "Apply color correction to img2img results to match original colors."),
"save_images_before_color_correction": OptionInfo(False, "Save a copy of image before applying color correction to img2img results"),
"img2img_fix_steps": OptionInfo(False, "With img2img, do exactly the amount of steps the slider specifies (normally you'd do less with less denoising)."),
@@ -214,6 +225,7 @@ options_templates.update(options_section(('sd', "Stable Diffusion"), { "use_old_emphasis_implementation": OptionInfo(False, "Use old emphasis implementation. Can be useful to reproduce old seeds."),
"enable_batch_seeds": OptionInfo(True, "Make K-diffusion samplers produce same images in a batch as when making a single image"),
"filter_nsfw": OptionInfo(False, "Filter NSFW content"),
+ 'CLIP_stop_at_last_layers': OptionInfo(1, "Stop At last layers of CLIP model", gr.Slider, {"minimum": 1, "maximum": 12, "step": 1}),
"random_artist_categories": OptionInfo([], "Allowed categories for random artists selection when using the Roll button", gr.CheckboxGroup, {"choices": artist_db.categories()}),
}))
@@ -228,13 +240,14 @@ options_templates.update(options_section(('interrogate', "Interrogate Options"), options_templates.update(options_section(('ui', "User interface"), {
"show_progressbar": OptionInfo(True, "Show progressbar"),
- "show_progress_every_n_steps": OptionInfo(0, "Show show image creation progress every N sampling steps. Set 0 to disable.", gr.Slider, {"minimum": 0, "maximum": 32, "step": 1}),
+ "show_progress_every_n_steps": OptionInfo(0, "Show image creation progress every N sampling steps. Set 0 to disable.", gr.Slider, {"minimum": 0, "maximum": 32, "step": 1}),
"return_grid": OptionInfo(True, "Show grid in results for web"),
"do_not_show_images": OptionInfo(False, "Do not show any images in results for web"),
"add_model_hash_to_info": OptionInfo(True, "Add model hash to generation information"),
+ "add_model_name_to_info": OptionInfo(False, "Add model name to generation information"),
"font": OptionInfo("", "Font for image grids that have text"),
"js_modal_lightbox": OptionInfo(True, "Enable full page image viewer"),
- "js_modal_lightbox_initialy_zoomed": OptionInfo(True, "Show images zoomed in by default in full page image viewer"),
+ "js_modal_lightbox_initially_zoomed": OptionInfo(True, "Show images zoomed in by default in full page image viewer"),
"show_progress_in_title": OptionInfo(True, "Show generation progress in window title."),
}))
diff --git a/modules/swinir_model.py b/modules/swinir_model.py index 9bd454c6..fbd11f84 100644 --- a/modules/swinir_model.py +++ b/modules/swinir_model.py @@ -8,7 +8,6 @@ from basicsr.utils.download_util import load_file_from_url from tqdm import tqdm from modules import modelloader -from modules.paths import models_path from modules.shared import cmd_opts, opts, device from modules.swinir_model_arch import SwinIR as net from modules.upscaler import Upscaler, UpscalerData @@ -25,7 +24,6 @@ class UpscalerSwinIR(Upscaler): "/003_realSR_BSRGAN_DFOWMFC_s64w8_SwinIR" \ "-L_x4_GAN.pth " self.model_name = "SwinIR 4x" - self.model_path = os.path.join(models_path, self.name) self.user_path = dirname super().__init__() scalers = [] diff --git a/modules/swinir_model_arch.py b/modules/swinir_model_arch.py index 461fb354..863f42db 100644 --- a/modules/swinir_model_arch.py +++ b/modules/swinir_model_arch.py @@ -166,7 +166,7 @@ class SwinTransformerBlock(nn.Module): Args: dim (int): Number of input channels. - input_resolution (tuple[int]): Input resulotion. + input_resolution (tuple[int]): Input resolution. num_heads (int): Number of attention heads. window_size (int): Window size. shift_size (int): Shift size for SW-MSA. diff --git a/modules/ui.py b/modules/ui.py index 21c9236b..1c0d35fe 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -25,6 +25,8 @@ import gradio.routes from modules import sd_hijack
from modules.paths import script_path
from modules.shared import opts, cmd_opts
+if cmd_opts.deepdanbooru:
+ from modules.deepbooru import get_deepbooru_tags
import modules.shared as shared
from modules.sd_samplers import samplers, samplers_for_img2img
from modules.sd_hijack import model_hijack
@@ -39,7 +41,7 @@ from modules.images import save_image import modules.textual_inversion.ui
import modules.images_history as img_his
-# this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the bowser will not show any UI
+# this is a fix for Windows users. Without it, javascript files will be served with text/html content-type and the browser will not show any UI
mimetypes.init()
mimetypes.add_type('application/javascript', '.js')
@@ -99,11 +101,12 @@ def send_gradio_gallery_to_image(x): return image_from_url_text(x[0])
-def save_files(js_data, images, index):
+def save_files(js_data, images, do_make_zip, index):
import csv
filenames = []
+ fullfns = []
- #quick dictionary to class object conversion. Its neccesary due apply_filename_pattern requiring it
+ #quick dictionary to class object conversion. Its necessary due apply_filename_pattern requiring it
class MyObject:
def __init__(self, d=None):
if d is not None:
@@ -138,14 +141,29 @@ def save_files(js_data, images, index): is_grid = image_index < p.index_of_first_image
i = 0 if is_grid else (image_index - p.index_of_first_image)
- fullfn = save_image(image, path, "", seed=p.all_seeds[i], prompt=p.all_prompts[i], extension=extension, info=p.infotexts[image_index], grid=is_grid, p=p, save_to_dirs=save_to_dirs)
+ fullfn, txt_fullfn = save_image(image, path, "", seed=p.all_seeds[i], prompt=p.all_prompts[i], extension=extension, info=p.infotexts[image_index], grid=is_grid, p=p, save_to_dirs=save_to_dirs)
filename = os.path.relpath(fullfn, path)
filenames.append(filename)
+ fullfns.append(fullfn)
+ if txt_fullfn:
+ filenames.append(os.path.basename(txt_fullfn))
+ fullfns.append(txt_fullfn)
writer.writerow([data["prompt"], data["seed"], data["width"], data["height"], data["sampler"], data["cfg_scale"], data["steps"], filenames[0], data["negative_prompt"]])
- return '', '', plaintext_to_html(f"Saved: {filenames[0]}")
+ # Make Zip
+ if do_make_zip:
+ zip_filepath = os.path.join(path, "images.zip")
+
+ from zipfile import ZipFile
+ with ZipFile(zip_filepath, "w") as zip_file:
+ for i in range(len(fullfns)):
+ with open(fullfns[i], mode="rb") as f:
+ zip_file.writestr(filenames[i], f.read())
+ fullfns.insert(0, zip_filepath)
+
+ return gr.File.update(value=fullfns, visible=True), '', '', plaintext_to_html(f"Saved: {filenames[0]}")
def wrap_gradio_call(func, extra_outputs=None):
@@ -192,6 +210,7 @@ def wrap_gradio_call(func, extra_outputs=None): # last item is always HTML
res[-1] += f"<div class='performance'><p class='time'>Time taken: <wbr>{elapsed_text}</p>{vram_html}</div>"
+ shared.state.skipped = False
shared.state.interrupted = False
shared.state.job_count = 0
@@ -292,6 +311,11 @@ def interrogate(image): return gr_show(True) if prompt is None else prompt
+def interrogate_deepbooru(image):
+ prompt = get_deepbooru_tags(image)
+ return gr_show(True) if prompt is None else prompt
+
+
def create_seed_inputs():
with gr.Row():
with gr.Box():
@@ -412,24 +436,36 @@ def create_toprow(is_img2img): with gr.Column(scale=1):
with gr.Row():
+ skip = gr.Button('Skip', elem_id=f"{id_part}_skip")
interrupt = gr.Button('Interrupt', elem_id=f"{id_part}_interrupt")
submit = gr.Button('Generate', elem_id=f"{id_part}_generate", variant='primary')
+ skip.click(
+ fn=lambda: shared.state.skip(),
+ inputs=[],
+ outputs=[],
+ )
+
interrupt.click(
fn=lambda: shared.state.interrupt(),
inputs=[],
outputs=[],
)
- with gr.Row():
+ with gr.Row(scale=1):
if is_img2img:
- interrogate = gr.Button('Interrogate', elem_id="interrogate")
+ interrogate = gr.Button('Interrogate\nCLIP', elem_id="interrogate")
+ if cmd_opts.deepdanbooru:
+ deepbooru = gr.Button('Interrogate\nDeepBooru', elem_id="deepbooru")
+ else:
+ deepbooru = None
else:
interrogate = None
+ deepbooru = None
prompt_style_apply = gr.Button('Apply style', elem_id="style_apply")
save_style = gr.Button('Create style', elem_id="style_create")
- return prompt, roll, prompt_style, negative_prompt, prompt_style2, submit, interrogate, prompt_style_apply, save_style, paste, token_counter, token_button
+ return prompt, roll, prompt_style, negative_prompt, prompt_style2, submit, interrogate, deepbooru, prompt_style_apply, save_style, paste, token_counter, token_button
def setup_progressbar(progressbar, preview, id_part, textinfo=None):
@@ -458,7 +494,7 @@ def create_ui(wrap_gradio_gpu_call): import modules.txt2img
with gr.Blocks(analytics_enabled=False) as txt2img_interface:
- txt2img_prompt, roll, txt2img_prompt_style, txt2img_negative_prompt, txt2img_prompt_style2, submit, _, txt2img_prompt_style_apply, txt2img_save_style, paste, token_counter, token_button = create_toprow(is_img2img=False)
+ txt2img_prompt, roll, txt2img_prompt_style, txt2img_negative_prompt, txt2img_prompt_style2, submit, _, _, txt2img_prompt_style_apply, txt2img_save_style, paste, token_counter, token_button = create_toprow(is_img2img=False)
dummy_component = gr.Label(visible=False)
with gr.Row(elem_id='txt2img_progress_row'):
@@ -513,6 +549,12 @@ def create_ui(wrap_gradio_gpu_call): button_id = "hidden_element" if shared.cmd_opts.hide_ui_dir_config else 'open_folder'
open_txt2img_folder = gr.Button(folder_symbol, elem_id=button_id)
+ with gr.Row():
+ do_make_zip = gr.Checkbox(label="Make Zip when Save?", value=False)
+
+ with gr.Row():
+ download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False)
+
with gr.Group():
html_info = gr.HTML()
generation_info = gr.Textbox(visible=False)
@@ -563,13 +605,15 @@ def create_ui(wrap_gradio_gpu_call): save.click(
fn=wrap_gradio_call(save_files),
- _js="(x, y, z) => [x, y, selected_gallery_index()]",
+ _js="(x, y, z, w) => [x, y, z, selected_gallery_index()]",
inputs=[
generation_info,
txt2img_gallery,
+ do_make_zip,
html_info,
],
outputs=[
+ download_files,
html_info,
html_info,
html_info,
@@ -611,7 +655,7 @@ def create_ui(wrap_gradio_gpu_call): with gr.Blocks(analytics_enabled=False) as img2img_interface:
- img2img_prompt, roll, img2img_prompt_style, img2img_negative_prompt, img2img_prompt_style2, submit, img2img_interrogate, img2img_prompt_style_apply, img2img_save_style, paste, token_counter, token_button = create_toprow(is_img2img=True)
+ img2img_prompt, roll, img2img_prompt_style, img2img_negative_prompt, img2img_prompt_style2, submit, img2img_interrogate, img2img_deepbooru, img2img_prompt_style_apply, img2img_save_style, paste, token_counter, token_button = create_toprow(is_img2img=True)
with gr.Row(elem_id='img2img_progress_row'):
with gr.Column(scale=1):
@@ -695,6 +739,12 @@ def create_ui(wrap_gradio_gpu_call): button_id = "hidden_element" if shared.cmd_opts.hide_ui_dir_config else 'open_folder'
open_img2img_folder = gr.Button(folder_symbol, elem_id=button_id)
+ with gr.Row():
+ do_make_zip = gr.Checkbox(label="Make Zip when Save?", value=False)
+
+ with gr.Row():
+ download_files = gr.File(None, file_count="multiple", interactive=False, show_label=False, visible=False)
+
with gr.Group():
html_info = gr.HTML()
generation_info = gr.Textbox(visible=False)
@@ -769,15 +819,24 @@ def create_ui(wrap_gradio_gpu_call): outputs=[img2img_prompt],
)
+ if cmd_opts.deepdanbooru:
+ img2img_deepbooru.click(
+ fn=interrogate_deepbooru,
+ inputs=[init_img],
+ outputs=[img2img_prompt],
+ )
+
save.click(
fn=wrap_gradio_call(save_files),
- _js="(x, y, z) => [x, y, selected_gallery_index()]",
+ _js="(x, y, z, w) => [x, y, z, selected_gallery_index()]",
inputs=[
generation_info,
img2img_gallery,
- html_info
+ do_make_zip,
+ html_info,
],
outputs=[
+ download_files,
html_info,
html_info,
html_info,
@@ -941,7 +1000,7 @@ def create_ui(wrap_gradio_gpu_call): custom_name = gr.Textbox(label="Custom Name (Optional)")
interp_amount = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Interpolation Amount', value=0.3)
interp_method = gr.Radio(choices=["Weighted Sum", "Sigmoid", "Inverse Sigmoid"], value="Weighted Sum", label="Interpolation Method")
- save_as_half = gr.Checkbox(value=False, label="Safe as float16")
+ save_as_half = gr.Checkbox(value=False, label="Save as float16")
modelmerger_merge = gr.Button(elem_id="modelmerger_merge", label="Merge", variant='primary')
with gr.Column(variant='panel'):
@@ -975,9 +1034,9 @@ def create_ui(wrap_gradio_gpu_call): process_dst = gr.Textbox(label='Destination directory')
with gr.Row():
- process_flip = gr.Checkbox(label='Flip')
- process_split = gr.Checkbox(label='Split into two')
- process_caption = gr.Checkbox(label='Add caption')
+ process_flip = gr.Checkbox(label='Create flipped copies')
+ process_split = gr.Checkbox(label='Split oversized images into two')
+ process_caption = gr.Checkbox(label='Use BLIP caption as filename')
with gr.Row():
with gr.Column(scale=3):
@@ -1097,6 +1156,15 @@ def create_ui(wrap_gradio_gpu_call): component_dict = {}
def open_folder(f):
+ if not os.path.isdir(f):
+ print(f"""
+WARNING
+An open_folder request was made with an argument that is not a folder.
+This could be an error or a malicious attempt to run code on your computer.
+Requested path was: {f}
+""", file=sys.stderr)
+ return
+
if not shared.cmd_opts.hide_ui_dir_config:
path = os.path.normpath(f)
if platform.system() == "Windows":
@@ -1110,10 +1178,13 @@ def create_ui(wrap_gradio_gpu_call): changed = 0
for key, value, comp in zip(opts.data_labels.keys(), args, components):
- if not opts.same_type(value, opts.data_labels[key].default):
- return f"Bad value for setting {key}: {value}; expecting {type(opts.data_labels[key].default).__name__}"
+ if comp != dummy_component and not opts.same_type(value, opts.data_labels[key].default):
+ return f"Bad value for setting {key}: {value}; expecting {type(opts.data_labels[key].default).__name__}", opts.dumpjson()
for key, value, comp in zip(opts.data_labels.keys(), args, components):
+ if comp == dummy_component:
+ continue
+
comp_args = opts.data_labels[key].component_args
if comp_args and isinstance(comp_args, dict) and comp_args.get('visible') is False:
continue
@@ -1140,6 +1211,21 @@ def create_ui(wrap_gradio_gpu_call): images_history = img_his.create_history_tabs(gr, opts, wrap_gradio_call(modules.extras.run_pnginfo), images_history_switch_dict)
+ def run_settings_single(value, key):
+ if not opts.same_type(value, opts.data_labels[key].default):
+ return gr.update(visible=True), opts.dumpjson()
+
+ oldval = opts.data.get(key, None)
+ opts.data[key] = value
+
+ if oldval != value:
+ if opts.data_labels[key].onchange is not None:
+ opts.data_labels[key].onchange()
+
+ opts.save(shared.config_filename)
+
+ return gr.update(value=value), opts.dumpjson()
+
with gr.Blocks(analytics_enabled=False) as settings_interface:
settings_submit = gr.Button(value="Apply settings", variant='primary')
result = gr.HTML()
@@ -1147,6 +1233,8 @@ def create_ui(wrap_gradio_gpu_call): settings_cols = 3
items_per_col = int(len(opts.data_labels) * 0.9 / settings_cols)
+ quicksettings_list = []
+
cols_displayed = 0
items_displayed = 0
previous_section = None
@@ -1169,10 +1257,14 @@ def create_ui(wrap_gradio_gpu_call): gr.HTML(elem_id="settings_header_text_{}".format(item.section[0]), value='<h1 class="gr-button-lg">{}</h1>'.format(item.section[1]))
- component = create_setting_component(k)
- component_dict[k] = component
- components.append(component)
- items_displayed += 1
+ if item.show_on_main_page:
+ quicksettings_list.append((i, k, item))
+ components.append(dummy_component)
+ else:
+ component = create_setting_component(k)
+ component_dict[k] = component
+ components.append(component)
+ items_displayed += 1
request_notifications = gr.Button(value='Request browser notifications', elem_id="request_notifications")
request_notifications.click(
@@ -1186,7 +1278,6 @@ def create_ui(wrap_gradio_gpu_call): reload_script_bodies = gr.Button(value='Reload custom script bodies (No ui updates, No restart)', variant='secondary')
restart_gradio = gr.Button(value='Restart Gradio and Refresh components (Custom Scripts, ui.py, js and css only)', variant='primary')
-
def reload_scripts():
modules.scripts.reload_script_body_only()
@@ -1235,7 +1326,11 @@ def create_ui(wrap_gradio_gpu_call): css += css_hide_progressbar
with gr.Blocks(css=css, analytics_enabled=False, title="Stable Diffusion") as demo:
-
+ with gr.Row(elem_id="quicksettings"):
+ for i, k, item in quicksettings_list:
+ component = create_setting_component(k)
+ component_dict[k] = component
+
settings_interface.gradio_ref = demo
with gr.Tabs() as tabs:
@@ -1252,7 +1347,16 @@ def create_ui(wrap_gradio_gpu_call): inputs=components,
outputs=[result, text_settings],
)
-
+
+ for i, k, item in quicksettings_list:
+ component = component_dict[k]
+
+ component.change(
+ fn=lambda value, k=k: run_settings_single(value, key=k),
+ inputs=[component],
+ outputs=[component, text_settings],
+ )
+
def modelmerger(*args):
try:
results = modules.extras.run_modelmerger(*args)
diff --git a/modules/upscaler.py b/modules/upscaler.py index d9d7c5e2..6ab2fb40 100644 --- a/modules/upscaler.py +++ b/modules/upscaler.py @@ -36,10 +36,11 @@ class Upscaler: self.half = not modules.shared.cmd_opts.no_half self.pre_pad = 0 self.mod_scale = None - if self.name is not None and create_dirs: + + if self.model_path is None and self.name: self.model_path = os.path.join(models_path, self.name) - if not os.path.exists(self.model_path): - os.makedirs(self.model_path) + if self.model_path and create_dirs: + os.makedirs(self.model_path, exist_ok=True) try: import cv2 |