Merge branch 'dev' into dora-weight-decompose

extensions-builtin/Lora/network_oft.py

@@ -36,13 +36,6 @@ class NetworkModuleOFT(network.NetworkModule):
             # self.alpha is unused
             self.dim = self.oft_blocks.shape[1] # (num_blocks, block_size, block_size)
 
-        # LyCORIS BOFT
-        if self.oft_blocks.dim() == 4:
-            self.is_boft = True
-        self.rescale = weights.w.get('rescale', None)
-        if self.rescale is not None:
-            self.rescale = self.rescale.reshape(-1, *[1]*(self.org_module[0].weight.dim() - 1))
-
         is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear]
         is_conv = type(self.sd_module) in [torch.nn.Conv2d]
         is_other_linear = type(self.sd_module) in [torch.nn.MultiheadAttention] # unsupported
@@ -54,6 +47,13 @@ class NetworkModuleOFT(network.NetworkModule):
         elif is_other_linear:
             self.out_dim = self.sd_module.embed_dim
 
+        # LyCORIS BOFT
+        if self.oft_blocks.dim() == 4:
+            self.is_boft = True
+        self.rescale = weights.w.get('rescale', None)
+        if self.rescale is not None and not is_other_linear:
+            self.rescale = self.rescale.reshape(-1, *[1]*(self.org_module[0].weight.dim() - 1))
+
         self.num_blocks = self.dim
         self.block_size = self.out_dim // self.dim
         self.constraint = (0 if self.alpha is None else self.alpha) * self.out_dim

extensions-builtin/canvas-zoom-and-pan/javascript/zoom.js

@@ -252,6 +252,7 @@ onUiLoaded(async() => {
     let isMoving = false;
     let mouseX, mouseY;
     let activeElement;
+    let interactedWithAltKey = false;
 
     const elements = Object.fromEntries(
         Object.keys(elementIDs).map(id => [
@@ -508,6 +509,10 @@ onUiLoaded(async() => {
             if (isModifierKey(e, hotkeysConfig.canvas_hotkey_zoom)) {
                 e.preventDefault();
 
+                if(hotkeysConfig.canvas_hotkey_zoom === "Alt"){
+                    interactedWithAltKey = true;
+                }
+
                 let zoomPosX, zoomPosY;
                 let delta = 0.2;
                 if (elemData[elemId].zoomLevel > 7) {
@@ -793,13 +798,17 @@ onUiLoaded(async() => {
 
         targetElement.addEventListener("wheel", e => {
             // change zoom level
-            const operation = e.deltaY > 0 ? "-" : "+";
+            const operation = (e.deltaY || -e.wheelDelta) > 0 ? "-" : "+";
             changeZoomLevel(operation, e);
 
             // Handle brush size adjustment with ctrl key pressed
             if (isModifierKey(e, hotkeysConfig.canvas_hotkey_adjust)) {
                 e.preventDefault();
 
+                if(hotkeysConfig.canvas_hotkey_adjust === "Alt"){
+                    interactedWithAltKey = true;
+                }
+
                 // Increase or decrease brush size based on scroll direction
                 adjustBrushSize(elemId, e.deltaY);
             }
@@ -839,6 +848,20 @@ onUiLoaded(async() => {
         document.addEventListener("keydown", handleMoveKeyDown);
         document.addEventListener("keyup", handleMoveKeyUp);
 
+
+        // Prevent firefox from opening main menu when alt is used as a hotkey for zoom or brush size
+        function handleAltKeyUp(e) {
+            if (e.key !== "Alt" || !interactedWithAltKey) {
+                return;
+            }
+
+            e.preventDefault();
+            interactedWithAltKey = false;
+        }
+
+        document.addEventListener("keyup", handleAltKeyUp);
+
+
         // Detect zoom level and update the pan speed.
         function updatePanPosition(movementX, movementY) {
             let panSpeed = 2;

extensions-builtin/postprocessing-for-training/scripts/postprocessing_autosized_crop.py

@@ -0,0 +1,64 @@
+from PIL import Image
+
+from modules import scripts_postprocessing, ui_components
+import gradio as gr
+
+
+def center_crop(image: Image, w: int, h: int):
+    iw, ih = image.size
+    if ih / h < iw / w:
+        sw = w * ih / h
+        box = (iw - sw) / 2, 0, iw - (iw - sw) / 2, ih
+    else:
+        sh = h * iw / w
+        box = 0, (ih - sh) / 2, iw, ih - (ih - sh) / 2
+    return image.resize((w, h), Image.Resampling.LANCZOS, box)
+
+
+def multicrop_pic(image: Image, mindim, maxdim, minarea, maxarea, objective, threshold):
+    iw, ih = image.size
+    err = lambda w, h: 1 - (lambda x: x if x < 1 else 1 / x)(iw / ih / (w / h))
+    wh = max(((w, h) for w in range(mindim, maxdim + 1, 64) for h in range(mindim, maxdim + 1, 64)
+              if minarea <= w * h <= maxarea and err(w, h) <= threshold),
+             key=lambda wh: (wh[0] * wh[1], -err(*wh))[::1 if objective == 'Maximize area' else -1],
+             default=None
+             )
+    return wh and center_crop(image, *wh)
+
+
+class ScriptPostprocessingAutosizedCrop(scripts_postprocessing.ScriptPostprocessing):
+    name = "Auto-sized crop"
+    order = 4020
+
+    def ui(self):
+        with ui_components.InputAccordion(False, label="Auto-sized crop") as enable:
+            gr.Markdown('Each image is center-cropped with an automatically chosen width and height.')
+            with gr.Row():
+                mindim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension lower bound", value=384, elem_id="postprocess_multicrop_mindim")
+                maxdim = gr.Slider(minimum=64, maximum=2048, step=8, label="Dimension upper bound", value=768, elem_id="postprocess_multicrop_maxdim")
+            with gr.Row():
+                minarea = gr.Slider(minimum=64 * 64, maximum=2048 * 2048, step=1, label="Area lower bound", value=64 * 64, elem_id="postprocess_multicrop_minarea")
+                maxarea = gr.Slider(minimum=64 * 64, maximum=2048 * 2048, step=1, label="Area upper bound", value=640 * 640, elem_id="postprocess_multicrop_maxarea")
+            with gr.Row():
+                objective = gr.Radio(["Maximize area", "Minimize error"], value="Maximize area", label="Resizing objective", elem_id="postprocess_multicrop_objective")
+                threshold = gr.Slider(minimum=0, maximum=1, step=0.01, label="Error threshold", value=0.1, elem_id="postprocess_multicrop_threshold")
+
+        return {
+            "enable": enable,
+            "mindim": mindim,
+            "maxdim": maxdim,
+            "minarea": minarea,
+            "maxarea": maxarea,
+            "objective": objective,
+            "threshold": threshold,
+        }
+
+    def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, mindim, maxdim, minarea, maxarea, objective, threshold):
+        if not enable:
+            return
+
+        cropped = multicrop_pic(pp.image, mindim, maxdim, minarea, maxarea, objective, threshold)
+        if cropped is not None:
+            pp.image = cropped
+        else:
+            print(f"skipped {pp.image.width}x{pp.image.height} image (can't find suitable size within error threshold)")

extensions-builtin/postprocessing-for-training/scripts/postprocessing_caption.py

@@ -0,0 +1,30 @@
+from modules import scripts_postprocessing, ui_components, deepbooru, shared
+import gradio as gr
+
+
+class ScriptPostprocessingCeption(scripts_postprocessing.ScriptPostprocessing):
+    name = "Caption"
+    order = 4040
+
+    def ui(self):
+        with ui_components.InputAccordion(False, label="Caption") as enable:
+            option = gr.CheckboxGroup(value=["Deepbooru"], choices=["Deepbooru", "BLIP"], show_label=False)
+
+        return {
+            "enable": enable,
+            "option": option,
+        }
+
+    def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, option):
+        if not enable:
+            return
+
+        captions = [pp.caption]
+
+        if "Deepbooru" in option:
+            captions.append(deepbooru.model.tag(pp.image))
+
+        if "BLIP" in option:
+            captions.append(shared.interrogator.interrogate(pp.image.convert("RGB")))
+
+        pp.caption = ", ".join([x for x in captions if x])

extensions-builtin/postprocessing-for-training/scripts/postprocessing_create_flipped_copies.py

@@ -0,0 +1,32 @@
+from PIL import ImageOps, Image
+
+from modules import scripts_postprocessing, ui_components
+import gradio as gr
+
+
+class ScriptPostprocessingCreateFlippedCopies(scripts_postprocessing.ScriptPostprocessing):
+    name = "Create flipped copies"
+    order = 4030
+
+    def ui(self):
+        with ui_components.InputAccordion(False, label="Create flipped copies") as enable:
+            with gr.Row():
+                option = gr.CheckboxGroup(value=["Horizontal"], choices=["Horizontal", "Vertical", "Both"], show_label=False)
+
+        return {
+            "enable": enable,
+            "option": option,
+        }
+
+    def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, option):
+        if not enable:
+            return
+
+        if "Horizontal" in option:
+            pp.extra_images.append(ImageOps.mirror(pp.image))
+
+        if "Vertical" in option:
+            pp.extra_images.append(pp.image.transpose(Image.Transpose.FLIP_TOP_BOTTOM))
+
+        if "Both" in option:
+            pp.extra_images.append(pp.image.transpose(Image.Transpose.FLIP_TOP_BOTTOM).transpose(Image.Transpose.FLIP_LEFT_RIGHT))

extensions-builtin/postprocessing-for-training/scripts/postprocessing_focal_crop.py

@@ -0,0 +1,54 @@
+
+from modules import scripts_postprocessing, ui_components, errors
+import gradio as gr
+
+from modules.textual_inversion import autocrop
+
+
+class ScriptPostprocessingFocalCrop(scripts_postprocessing.ScriptPostprocessing):
+    name = "Auto focal point crop"
+    order = 4010
+
+    def ui(self):
+        with ui_components.InputAccordion(False, label="Auto focal point crop") as enable:
+            face_weight = gr.Slider(label='Focal point face weight', value=0.9, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_face_weight")
+            entropy_weight = gr.Slider(label='Focal point entropy weight', value=0.15, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_entropy_weight")
+            edges_weight = gr.Slider(label='Focal point edges weight', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_focal_crop_edges_weight")
+            debug = gr.Checkbox(label='Create debug image', elem_id="train_process_focal_crop_debug")
+
+        return {
+            "enable": enable,
+            "face_weight": face_weight,
+            "entropy_weight": entropy_weight,
+            "edges_weight": edges_weight,
+            "debug": debug,
+        }
+
+    def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, face_weight, entropy_weight, edges_weight, debug):
+        if not enable:
+            return
+
+        if not pp.shared.target_width or not pp.shared.target_height:
+            return
+
+        dnn_model_path = None
+        try:
+            dnn_model_path = autocrop.download_and_cache_models()
+        except Exception:
+            errors.report("Unable to load face detection model for auto crop selection. Falling back to lower quality haar method.", exc_info=True)
+
+        autocrop_settings = autocrop.Settings(
+            crop_width=pp.shared.target_width,
+            crop_height=pp.shared.target_height,
+            face_points_weight=face_weight,
+            entropy_points_weight=entropy_weight,
+            corner_points_weight=edges_weight,
+            annotate_image=debug,
+            dnn_model_path=dnn_model_path,
+        )
+
+        result, *others = autocrop.crop_image(pp.image, autocrop_settings)
+
+        pp.image = result
+        pp.extra_images = [pp.create_copy(x, nametags=["focal-crop-debug"], disable_processing=True) for x in others]
+

extensions-builtin/postprocessing-for-training/scripts/postprocessing_split_oversized.py

@@ -0,0 +1,71 @@
+import math
+
+from modules import scripts_postprocessing, ui_components
+import gradio as gr
+
+
+def split_pic(image, inverse_xy, width, height, overlap_ratio):
+    if inverse_xy:
+        from_w, from_h = image.height, image.width
+        to_w, to_h = height, width
+    else:
+        from_w, from_h = image.width, image.height
+        to_w, to_h = width, height
+    h = from_h * to_w // from_w
+    if inverse_xy:
+        image = image.resize((h, to_w))
+    else:
+        image = image.resize((to_w, h))
+
+    split_count = math.ceil((h - to_h * overlap_ratio) / (to_h * (1.0 - overlap_ratio)))
+    y_step = (h - to_h) / (split_count - 1)
+    for i in range(split_count):
+        y = int(y_step * i)
+        if inverse_xy:
+            splitted = image.crop((y, 0, y + to_h, to_w))
+        else:
+            splitted = image.crop((0, y, to_w, y + to_h))
+        yield splitted
+
+
+class ScriptPostprocessingSplitOversized(scripts_postprocessing.ScriptPostprocessing):
+    name = "Split oversized images"
+    order = 4000
+
+    def ui(self):
+        with ui_components.InputAccordion(False, label="Split oversized images") as enable:
+            with gr.Row():
+                split_threshold = gr.Slider(label='Threshold', value=0.5, minimum=0.0, maximum=1.0, step=0.05, elem_id="postprocess_split_threshold")
+                overlap_ratio = gr.Slider(label='Overlap ratio', value=0.2, minimum=0.0, maximum=0.9, step=0.05, elem_id="postprocess_overlap_ratio")
+
+        return {
+            "enable": enable,
+            "split_threshold": split_threshold,
+            "overlap_ratio": overlap_ratio,
+        }
+
+    def process(self, pp: scripts_postprocessing.PostprocessedImage, enable, split_threshold, overlap_ratio):
+        if not enable:
+            return
+
+        width = pp.shared.target_width
+        height = pp.shared.target_height
+
+        if not width or not height:
+            return
+
+        if pp.image.height > pp.image.width:
+            ratio = (pp.image.width * height) / (pp.image.height * width)
+            inverse_xy = False
+        else:
+            ratio = (pp.image.height * width) / (pp.image.width * height)
+            inverse_xy = True
+
+        if ratio >= 1.0 or ratio > split_threshold:
+            return
+
+        result, *others = split_pic(pp.image, inverse_xy, width, height, overlap_ratio)
+
+        pp.image = result
+        pp.extra_images = [pp.create_copy(x) for x in others]
+