Merge branch 'master' into embed-embeddings-in-images

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

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

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 = []

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,

modules/hypernetwork.py

@@ -40,27 +40,37 @@ class Hypernetwork:
             self.layers[size] = (HypernetworkModule(size, sd[0]), HypernetworkModule(size, sd[1]))
 
 
-def load_hypernetworks(path):
+def list_hypernetworks(path):
     res = {}
-
     for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True):
-        try:
-            hn = Hypernetwork(filename)
-            res[hn.name] = hn
-        except Exception:
-            print(f"Error loading hypernetwork {filename}", file=sys.stderr)
-            print(traceback.format_exc(), file=sys.stderr)
-
+        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.selected_hypernetwork()
+    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:

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:
@@ -424,10 +456,13 @@ 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
 
 def addCaptionLines(lines,image,initialx,textfont):
     draw = ImageDraw.Draw(image)

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"

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")

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
@@ -123,7 +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_ignore_last_layers
+        self.clip_skip = opts.CLIP_stop_at_last_layers
 
         self.eta = p.eta
         self.ddim_discretize = p.ddim_discretize
@@ -268,16 +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_ignore_last_layers)
+    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]),
@@ -285,7 +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==0 else clip_skip,
+        "Clip skip": None if clip_skip <= 1 else clip_skip,
     }
 
     generation_params.update(p.extra_generation_params)
@@ -445,7 +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 
@@ -464,7 +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
 

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:

modules/safe.py

@@ -0,0 +1,89 @@
+# 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
+
+
+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 torch.storage._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

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"

modules/sd_hijack.py

@@ -282,14 +282,12 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
         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)
 
-        tmp = -opts.CLIP_ignore_last_layers
-        if (opts.CLIP_ignore_last_layers == 0):
-            outputs = self.wrapped.transformer(input_ids=tokens, position_ids=position_ids)
-            z = outputs.last_hidden_state
-        else:
-            outputs = self.wrapped.transformer(input_ids=tokens, position_ids=position_ids, output_hidden_states=tmp)
-            z = outputs.hidden_states[tmp]
+        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_of_same_length = [x + [1.0] * (target_token_count - len(x)) for x in batch_multipliers]

modules/sd_hijack_optimizations.py

@@ -28,7 +28,7 @@ def split_cross_attention_forward_v1(self, x, context=None, mask=None):
     q_in = self.to_q(x)
     context = default(context, x)
 
-    hypernetwork = shared.selected_hypernetwork()
+    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:
@@ -68,7 +68,7 @@ def split_cross_attention_forward(self, x, context=None, mask=None):
     q_in = self.to_q(x)
     context = default(context, x)
 
-    hypernetwork = shared.selected_hypernetwork()
+    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:
@@ -132,7 +132,7 @@ 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.selected_hypernetwork()
+    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))

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
@@ -122,6 +121,13 @@ def select_checkpoint():
     return checkpoint_info
 
 
+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
@@ -131,11 +137,8 @@ def load_model_weights(model, checkpoint_info):
     pl_sd = torch.load(checkpoint_file, map_location="cpu")
     if "global_step" in pl_sd:
         print(f"Global Step: {pl_sd['global_step']}")
-    
-    if "state_dict" in pl_sd:
-        sd = pl_sd["state_dict"]
-    else:
-        sd = pl_sd
+
+    sd = get_state_dict_from_checkpoint(pl_sd)
 
     model.load_state_dict(sd, strict=False)
 
@@ -165,7 +168,7 @@ def load_model():
     checkpoint_info = select_checkpoint()
 
     if checkpoint_info.config != shared.cmd_opts.config:
-        print(f"Loading config from: {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)
@@ -192,7 +195,8 @@ def reload_model_weights(sd_model, info=None):
         return
 
     if sd_model.sd_checkpoint_info.config != checkpoint_info.config:
-        return load_model()
+        shared.sd_model = load_model()
+        return shared.sd_model
 
     if shared.cmd_opts.lowvram or shared.cmd_opts.medvram:
         lowvram.send_everything_to_cpu()

modules/shared.py

@@ -45,6 +45,7 @@ parser.add_argument("--swinir-models-path", type=str, help="Path to directory wi
 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")
@@ -64,6 +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()
@@ -78,11 +80,8 @@ parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram
 xformers_available = False
 config_filename = cmd_opts.ui_settings_file
 
-hypernetworks = hypernetwork.load_hypernetworks(os.path.join(models_path, 'hypernetworks'))
-
-
-def selected_hypernetwork():
-    return hypernetworks.get(opts.sd_hypernetwork, None)
+hypernetworks = hypernetwork.list_hypernetworks(os.path.join(models_path, 'hypernetworks'))
+loaded_hypernetwork = None
 
 
 class State:
@@ -132,13 +131,14 @@ 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_identifier, options_dict):
@@ -215,7 +215,7 @@ 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"),
@@ -225,7 +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_ignore_last_layers': OptionInfo(0, "Ignore last layers of CLIP model", gr.Slider, {"minimum": 0, "maximum": 5, "step": 1}),
+    '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()}),
 }))
 
@@ -240,10 +240,11 @@ 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_initially_zoomed": OptionInfo(True, "Show images zoomed in by default in full page image viewer"),

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 = []

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
@@ -98,9 +100,10 @@ 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 necessary due apply_filename_pattern requiring it
     class MyObject:
@@ -137,14 +140,29 @@ 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):
@@ -292,6 +310,11 @@ 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():
@@ -428,15 +451,20 @@ def create_toprow(is_img2img):
                     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):
@@ -465,7 +493,7 @@ 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'):
@@ -521,6 +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)
@@ -570,13 +604,15 @@ 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,
@@ -617,7 +653,7 @@ def create_ui(wrap_gradio_gpu_call):
             token_button.click(fn=update_token_counter, inputs=[txt2img_prompt, steps], outputs=[token_counter])
 
     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):
@@ -701,6 +737,12 @@ 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)
@@ -774,15 +816,24 @@ 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,
@@ -1104,6 +1155,15 @@ 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":
@@ -1117,10 +1177,13 @@ 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
@@ -1138,6 +1201,21 @@ def create_ui(wrap_gradio_gpu_call):
 
         return f'{changed} settings changed.', opts.dumpjson()
 
+    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()
@@ -1145,6 +1223,8 @@ 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
@@ -1167,10 +1247,14 @@ 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(
@@ -1184,7 +1268,6 @@ 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()
 
@@ -1231,7 +1314,11 @@ 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:
@@ -1248,7 +1335,16 @@ 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)

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