Merge branch 'Inspiron' of https://github.com/yfszzx/stable-diffusion-webui-plus into Inspiron

javascript/hints.js

@@ -62,8 +62,8 @@ titles = {
 
     "Interrogate": "Reconstruct prompt from existing image and put it into the prompt field.",
 
-    "Images filename pattern": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [job_timestamp]; leave empty for default.",
-    "Directory name pattern": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [job_timestamp]; leave empty for default.",
+    "Images filename pattern": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
+    "Directory name pattern": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
     "Max prompt words": "Set the maximum number of words to be used in the [prompt_words] option; ATTENTION: If the words are too long, they may exceed the maximum length of the file path that the system can handle",
 
     "Loopback": "Process an image, use it as an input, repeat.",

javascript/localization.js

@@ -108,6 +108,9 @@ function processNode(node){
 
 function dumpTranslations(){
     dumped = {}
+    if (localization.rtl) {
+        dumped.rtl = true
+    }
 
     Object.keys(original_lines).forEach(function(text){
         if(dumped[text] !== undefined)  return
@@ -129,6 +132,24 @@ onUiUpdate(function(m){
 
 document.addEventListener("DOMContentLoaded", function() {
     processNode(gradioApp())
+
+    if (localization.rtl) {  // if the language is from right to left,
+        (new MutationObserver((mutations, observer) => { // wait for the style to load
+            mutations.forEach(mutation => {
+                mutation.addedNodes.forEach(node => {
+                    if (node.tagName === 'STYLE') {
+                        observer.disconnect();
+
+                        for (const x of node.sheet.rules) {  // find all rtl media rules
+                            if (Array.from(x.media || []).includes('rtl')) {
+                                x.media.appendMedium('all');  // enable them
+                            }
+                        }
+                    }
+                })
+            });
+        })).observe(gradioApp(), { childList: true });
+    }
 })
 
 function download_localization() {

modules/devices.py

@@ -45,7 +45,7 @@ def enable_tf32():
 
 errors.run(enable_tf32, "Enabling TF32")
 
-device = device_interrogate = device_gfpgan = device_bsrgan = device_esrgan = device_scunet = device_codeformer = None
+device = device_interrogate = device_gfpgan = device_swinir = device_esrgan = device_scunet = device_codeformer = None
 dtype = torch.float16
 dtype_vae = torch.float16
 
@@ -81,3 +81,7 @@ def autocast(disable=False):
         return contextlib.nullcontext()
 
     return torch.autocast("cuda")
+
+# MPS workaround for https://github.com/pytorch/pytorch/issues/79383
+def mps_contiguous(input_tensor, device): return input_tensor.contiguous() if device.type == 'mps' else input_tensor
+def mps_contiguous_to(input_tensor, device): return mps_contiguous(input_tensor, device).to(device)

modules/esrgan_model.py

@@ -190,7 +190,7 @@ def upscale_without_tiling(model, img):
     img = img[:, :, ::-1]
     img = np.ascontiguousarray(np.transpose(img, (2, 0, 1))) / 255
     img = torch.from_numpy(img).float()
-    img = img.unsqueeze(0).to(devices.device_esrgan)
+    img = devices.mps_contiguous_to(img.unsqueeze(0), devices.device_esrgan)
     with torch.no_grad():
         output = model(img)
     output = output.squeeze().float().cpu().clamp_(0, 1).numpy()

modules/images.py

@@ -16,7 +16,7 @@ from PIL import Image, ImageFont, ImageDraw, PngImagePlugin
 from fonts.ttf import Roboto
 import string
 
-from modules import sd_samplers, shared
+from modules import sd_samplers, shared, script_callbacks
 from modules.shared import opts, cmd_opts
 
 LANCZOS = (Image.Resampling.LANCZOS if hasattr(Image, 'Resampling') else Image.LANCZOS)
@@ -344,7 +344,10 @@ class FilenameGenerator:
         time_datetime = datetime.datetime.now()
 
         time_format = args[0] if len(args) > 0 else self.default_time_format
-        time_zone = pytz.timezone(args[1]) if len(args) > 1 else None
+        try:
+            time_zone = pytz.timezone(args[1]) if len(args) > 1 else None
+        except pytz.exceptions.UnknownTimeZoneError as _:
+            time_zone = None
 
         time_zone_time = time_datetime.astimezone(time_zone)
         try:
@@ -474,8 +477,10 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     if forced_filename is None:
         if short_filename or seed is None:
             file_decoration = ""
-        else:
+        elif opts.save_to_dirs:
             file_decoration = opts.samples_filename_pattern or "[seed]"
+        else:
+            file_decoration = opts.samples_filename_pattern or "[seed]-[prompt_spaces]"
 
         add_number = opts.save_images_add_number or file_decoration == ''
 
@@ -536,6 +541,7 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
     else:
         txt_fullfn = None
 
+    script_callbacks.image_saved_callback(image, p, fullfn, txt_fullfn)
     return fullfn, txt_fullfn
 
 

modules/script_callbacks.py

+import sys
+import traceback
+from collections import namedtuple
+import inspect
 
+
+def report_exception(c, job):
+    print(f"Error executing callback {job} for {c.script}", file=sys.stderr)
+    print(traceback.format_exc(), file=sys.stderr)
+
+
+ScriptCallback = namedtuple("ScriptCallback", ["script", "callback"])
 callbacks_model_loaded = []
 callbacks_ui_tabs = []
 callbacks_ui_settings = []
-
+callbacks_image_saved = []
 
 def clear_callbacks():
     callbacks_model_loaded.clear()
     callbacks_ui_tabs.clear()
+    callbacks_image_saved.clear()
 
 
 def model_loaded_callback(sd_model):
-    for callback in callbacks_model_loaded:
-        callback(sd_model)
+    for c in callbacks_model_loaded:
+        try:
+            c.callback(sd_model)
+        except Exception:
+            report_exception(c, 'model_loaded_callback')
 
 
 def ui_tabs_callback():
     res = []
     
-    for callback in callbacks_ui_tabs:
-        res += callback() or []
+    for c in callbacks_ui_tabs:
+        try:
+            res += c.callback() or []
+        except Exception:
+            report_exception(c, 'ui_tabs_callback')
 
     return res
 
 
 def ui_settings_callback():
-    for callback in callbacks_ui_settings:
-        callback()
+    for c in callbacks_ui_settings:
+        try:
+            c.callback()
+        except Exception:
+            report_exception(c, 'ui_settings_callback')
+
 
+def add_callback(callbacks, fun):
+    stack = [x for x in inspect.stack() if x.filename != __file__]
+    filename = stack[0].filename if len(stack) > 0 else 'unknown file'
+
+    callbacks.append(ScriptCallback(filename, fun))
+
+
+def image_saved_callback(image, p, fullfn, txt_fullfn):
+    for callback in callbacks_image_saved:
+        callback(image, p, fullfn, txt_fullfn)
 
 def on_model_loaded(callback):
     """register a function to be called when the stable diffusion model is created; the model is
     passed as an argument"""
-    callbacks_model_loaded.append(callback)
+    add_callback(callbacks_model_loaded, callback)
 
 
 def on_ui_tabs(callback):
@@ -44,10 +76,15 @@ def on_ui_tabs(callback):
     title is tab text displayed to user in the UI
     elem_id is HTML id for the tab
     """
-    callbacks_ui_tabs.append(callback)
+    add_callback(callbacks_ui_tabs, callback)
 
 
 def on_ui_settings(callback):
     """register a function to be called before UI settings are populated; add your settings
     by using shared.opts.add_option(shared.OptionInfo(...)) """
     callbacks_ui_settings.append(callback)
+
+
+def on_save_imaged(callback):
+    """register a function to call after modules.images.save_image is called returning same values, original image and p """
+    callbacks_image_saved.append(callback)

modules/scunet_model.py

@@ -54,9 +54,8 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
         img = img[:, :, ::-1]
         img = np.moveaxis(img, 2, 0) / 255
         img = torch.from_numpy(img).float()
-        img = img.unsqueeze(0).to(device)
+        img = devices.mps_contiguous_to(img.unsqueeze(0), device)
 
-        img = img.to(device)
         with torch.no_grad():
             output = model(img)
         output = output.squeeze().float().cpu().clamp_(0, 1).numpy()

modules/sd_samplers.py

@@ -228,7 +228,7 @@ class VanillaStableDiffusionSampler:
             unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
             
             
-        samples = self.launch_sampling(steps, lambda: self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning))
+        samples = self.launch_sampling(t_enc + 1, lambda: self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning))
 
         return samples
 
@@ -429,7 +429,7 @@ class KDiffusionSampler:
         self.model_wrap_cfg.init_latent = x
         self.last_latent = x
 
-        samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, xi, extra_args={
+        samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args={
             'cond': conditioning, 
             'image_cond': image_conditioning, 
             'uncond': unconditional_conditioning, 

modules/shared.py

@@ -58,7 +58,7 @@ parser.add_argument("--opt-split-attention", action='store_true', help="force-en
 parser.add_argument("--opt-split-attention-invokeai", action='store_true', help="force-enables InvokeAI's cross-attention layer optimization. By default, it's on when cuda is unavailable.")
 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")
 parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
-parser.add_argument("--use-cpu", nargs='+',choices=['all', 'sd', 'interrogate', 'gfpgan', 'bsrgan', 'esrgan', 'scunet', 'codeformer'], help="use CPU as torch device for specified modules", default=[], type=str.lower)
+parser.add_argument("--use-cpu", nargs='+',choices=['all', 'sd', 'interrogate', 'gfpgan', 'swinir', 'esrgan', 'scunet', 'codeformer'], help="use CPU as torch device for specified modules", default=[], type=str.lower)
 parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
 parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)
 parser.add_argument("--show-negative-prompt", action='store_true', help="does not do anything", default=False)
@@ -97,8 +97,8 @@ restricted_opts = [
     "outdir_save",
 ]
 
-devices.device, devices.device_interrogate, devices.device_gfpgan, devices.device_bsrgan, devices.device_esrgan, devices.device_scunet, devices.device_codeformer = \
-(devices.cpu if any(y in cmd_opts.use_cpu for y in [x, 'all']) else devices.get_optimal_device() for x in ['sd', 'interrogate', 'gfpgan', 'bsrgan', 'esrgan', 'scunet', 'codeformer'])
+devices.device, devices.device_interrogate, devices.device_gfpgan, devices.device_swinir, devices.device_esrgan, devices.device_scunet, devices.device_codeformer = \
+(devices.cpu if any(y in cmd_opts.use_cpu for y in [x, 'all']) else devices.get_optimal_device() for x in ['sd', 'interrogate', 'gfpgan', 'swinir', 'esrgan', 'scunet', 'codeformer'])
 
 device = devices.device
 weight_load_location = None if cmd_opts.lowram else "cpu"

modules/swinir_model.py

@@ -7,8 +7,8 @@ from PIL import Image
 from basicsr.utils.download_util import load_file_from_url
 from tqdm import tqdm
 
-from modules import modelloader
-from modules.shared import cmd_opts, opts, device
+from modules import modelloader, devices
+from modules.shared import cmd_opts, opts
 from modules.swinir_model_arch import SwinIR as net
 from modules.swinir_model_arch_v2 import Swin2SR as net2
 from modules.upscaler import Upscaler, UpscalerData
@@ -42,7 +42,7 @@ class UpscalerSwinIR(Upscaler):
         model = self.load_model(model_file)
         if model is None:
             return img
-        model = model.to(device)
+        model = model.to(devices.device_swinir)
         img = upscale(img, model)
         try:
             torch.cuda.empty_cache()
@@ -111,7 +111,7 @@ def upscale(
     img = img[:, :, ::-1]
     img = np.moveaxis(img, 2, 0) / 255
     img = torch.from_numpy(img).float()
-    img = img.unsqueeze(0).to(device)
+    img = devices.mps_contiguous_to(img.unsqueeze(0), devices.device_swinir)
     with torch.no_grad(), precision_scope("cuda"):
         _, _, h_old, w_old = img.size()
         h_pad = (h_old // window_size + 1) * window_size - h_old
@@ -139,8 +139,8 @@ def inference(img, model, tile, tile_overlap, window_size, scale):
     stride = tile - tile_overlap
     h_idx_list = list(range(0, h - tile, stride)) + [h - tile]
     w_idx_list = list(range(0, w - tile, stride)) + [w - tile]
-    E = torch.zeros(b, c, h * sf, w * sf, dtype=torch.half, device=device).type_as(img)
-    W = torch.zeros_like(E, dtype=torch.half, device=device)
+    E = torch.zeros(b, c, h * sf, w * sf, dtype=torch.half, device=devices.device_swinir).type_as(img)
+    W = torch.zeros_like(E, dtype=torch.half, device=devices.device_swinir)
 
     with tqdm(total=len(h_idx_list) * len(w_idx_list), desc="SwinIR tiles") as pbar:
         for h_idx in h_idx_list:

style.css

@@ -515,3 +515,77 @@ img2maskimg, #img2maskimg > .h-60, #img2maskimg > .h-60 > div, #img2maskimg > .h
     max-height: 480px !important;
     min-height: 480px !important;
 }
+
+/* The following handles localization for right-to-left (RTL) languages like Arabic.
+The rtl media type will only be activated by the logic in javascript/localization.js.
+If you change anything above, you need to make sure it is RTL compliant by just running
+your changes through converters like https://cssjanus.github.io/ or https://rtlcss.com/.
+Then, you will need to add the RTL counterpart only if needed in the rtl section below.*/
+@media rtl {
+    /* this part was manualy added */
+    :host {
+        direction: rtl;
+    }
+    .output-html:has(.performance), .gr-text-input {
+        direction: ltr;
+    }
+    .gr-radio, .gr-checkbox{
+        margin-left: 0.25em;
+    }
+
+    /* this part was automatically generated with few manual modifications */
+    .performance .time {
+        margin-right: unset;
+        margin-left: 0;
+    }
+    .justify-center.overflow-x-scroll {
+        justify-content: right;
+    }
+    .justify-center.overflow-x-scroll button:first-of-type {
+        margin-left: unset;
+        margin-right: auto;
+    }
+    .justify-center.overflow-x-scroll button:last-of-type {
+        margin-right: unset;
+        margin-left: auto;
+    }
+    #settings fieldset span.text-gray-500, #settings .gr-block.gr-box span.text-gray-500, #settings label.block span{
+        margin-right: unset;
+        margin-left: 8em;
+    }
+    #txt2img_progressbar, #img2img_progressbar, #ti_progressbar{
+        right: unset;
+        left: 0;
+    }
+    .progressDiv .progress{
+        padding: 0 0 0 8px;
+        text-align: left;
+    }
+    #lightboxModal{
+        left: unset;
+        right: 0;
+    }
+    .modalPrev, .modalNext{
+        border-radius: 3px 0 0 3px;
+    }
+    .modalNext {
+        right: unset;
+        left: 0;
+        border-radius: 0 3px 3px 0;
+    }
+    #imageARPreview{
+        left:unset;
+        right:0px;
+    }
+    #txt2img_skip, #img2img_skip{
+        right: unset;
+        left: 0px;
+    }
+    #context-menu{
+        box-shadow:-1px 1px 2px #CE6400;
+    }
+    .gr-box > div > div > input.gr-text-input{
+        right: unset;
+        left: 0.5em;
+    }
+}