Merge branch 'extra-network-preview-lazyload' of https://github.com/missionfloyd/stable-diffusion-webui into extra-network-preview-lazyload

4 files changed, 118 insertions, 60 deletions

diff --git a/scripts/img2imgalt.py b/scripts/img2imgalt.py
index 2572443f..bb00fb3f 100644
--- a/scripts/img2imgalt.py
+++ b/scripts/img2imgalt.py
@@ -6,23 +6,21 @@ from tqdm import trange
 import modules.scripts as scripts

 import gradio as gr

 

-from modules import processing, shared, sd_samplers, prompt_parser, sd_samplers_common

-from modules.processing import Processed

-from modules.shared import opts, cmd_opts, state

+from modules import processing, shared, sd_samplers, sd_samplers_common

 

 import torch

 import k_diffusion as K

 

-from PIL import Image

-from torch import autocast

-from einops import rearrange, repeat

-

-

 def find_noise_for_image(p, cond, uncond, cfg_scale, steps):

     x = p.init_latent

 

     s_in = x.new_ones([x.shape[0]])

-    dnw = K.external.CompVisDenoiser(shared.sd_model)

+    if shared.sd_model.parameterization == "v":

+        dnw = K.external.CompVisVDenoiser(shared.sd_model)

+        skip = 1

+    else:

+        dnw = K.external.CompVisDenoiser(shared.sd_model)

+        skip = 0

     sigmas = dnw.get_sigmas(steps).flip(0)

 

     shared.state.sampling_steps = steps

@@ -37,7 +35,7 @@ def find_noise_for_image(p, cond, uncond, cfg_scale, steps):
         image_conditioning = torch.cat([p.image_conditioning] * 2)

         cond_in = {"c_concat": [image_conditioning], "c_crossattn": [cond_in]}

 

-        c_out, c_in = [K.utils.append_dims(k, x_in.ndim) for k in dnw.get_scalings(sigma_in)]

+        c_out, c_in = [K.utils.append_dims(k, x_in.ndim) for k in dnw.get_scalings(sigma_in)[skip:]]

         t = dnw.sigma_to_t(sigma_in)

 

         eps = shared.sd_model.apply_model(x_in * c_in, t, cond=cond_in)

@@ -69,7 +67,12 @@ def find_noise_for_image_sigma_adjustment(p, cond, uncond, cfg_scale, steps):
     x = p.init_latent

 

     s_in = x.new_ones([x.shape[0]])

-    dnw = K.external.CompVisDenoiser(shared.sd_model)

+    if shared.sd_model.parameterization == "v":

+        dnw = K.external.CompVisVDenoiser(shared.sd_model)

+        skip = 1

+    else:

+        dnw = K.external.CompVisDenoiser(shared.sd_model)

+        skip = 0

     sigmas = dnw.get_sigmas(steps).flip(0)

 

     shared.state.sampling_steps = steps

@@ -84,7 +87,7 @@ def find_noise_for_image_sigma_adjustment(p, cond, uncond, cfg_scale, steps):
         image_conditioning = torch.cat([p.image_conditioning] * 2)

         cond_in = {"c_concat": [image_conditioning], "c_crossattn": [cond_in]}

 

-        c_out, c_in = [K.utils.append_dims(k, x_in.ndim) for k in dnw.get_scalings(sigma_in)]

+        c_out, c_in = [K.utils.append_dims(k, x_in.ndim) for k in dnw.get_scalings(sigma_in)[skip:]]

 

         if i == 1:

             t = dnw.sigma_to_t(torch.cat([sigmas[i] * s_in] * 2))

@@ -125,7 +128,7 @@ class Script(scripts.Script):
     def show(self, is_img2img):

         return is_img2img

 

-    def ui(self, is_img2img):     

+    def ui(self, is_img2img):

         info = gr.Markdown('''

         * `CFG Scale` should be 2 or lower.

         ''')

@@ -213,4 +216,3 @@ class Script(scripts.Script):
         processed = processing.process_images(p)

 

         return processed

-

diff --git a/scripts/loopback.py b/scripts/loopback.py
index ec1f85e5..d3065fe6 100644
--- a/scripts/loopback.py
+++ b/scripts/loopback.py
@@ -1,14 +1,10 @@
-import numpy as np

-from tqdm import trange

+import math

 

-import modules.scripts as scripts

 import gradio as gr

-

-from modules import processing, shared, sd_samplers, images

+import modules.scripts as scripts

+from modules import deepbooru, images, processing, shared

 from modules.processing import Processed

-from modules.sd_samplers import samplers

-from modules.shared import opts, cmd_opts, state

-from modules import deepbooru

+from modules.shared import opts, state

 

 

 class Script(scripts.Script):

@@ -20,39 +16,65 @@ class Script(scripts.Script):
 

     def ui(self, is_img2img):        

         loops = gr.Slider(minimum=1, maximum=32, step=1, label='Loops', value=4, elem_id=self.elem_id("loops"))

-        denoising_strength_change_factor = gr.Slider(minimum=0.9, maximum=1.1, step=0.01, label='Denoising strength change factor', value=1, elem_id=self.elem_id("denoising_strength_change_factor"))

+        final_denoising_strength = gr.Slider(minimum=0, maximum=1, step=0.01, label='Final denoising strength', value=0.5, elem_id=self.elem_id("final_denoising_strength"))

+        denoising_curve = gr.Dropdown(label="Denoising strength curve", choices=["Aggressive", "Linear", "Lazy"], value="Linear")

         append_interrogation = gr.Dropdown(label="Append interrogated prompt at each iteration", choices=["None", "CLIP", "DeepBooru"], value="None")

 

-        return [loops, denoising_strength_change_factor, append_interrogation]

+        return [loops, final_denoising_strength, denoising_curve, append_interrogation]

 

-    def run(self, p, loops, denoising_strength_change_factor, append_interrogation):

+    def run(self, p, loops, final_denoising_strength, denoising_curve, append_interrogation):

         processing.fix_seed(p)

         batch_count = p.n_iter

         p.extra_generation_params = {

-            "Denoising strength change factor": denoising_strength_change_factor,

+            "Final denoising strength": final_denoising_strength,

+            "Denoising curve": denoising_curve

         }

 

         p.batch_size = 1

         p.n_iter = 1

 

-        output_images, info = None, None

+        info = None

         initial_seed = None

         initial_info = None

+        initial_denoising_strength = p.denoising_strength

 

         grids = []

         all_images = []

         original_init_image = p.init_images

         original_prompt = p.prompt

+        original_inpainting_fill = p.inpainting_fill

         state.job_count = loops * batch_count

 

         initial_color_corrections = [processing.setup_color_correction(p.init_images[0])]

 

-        for n in range(batch_count):

-            history = []

+        def calculate_denoising_strength(loop):

+            strength = initial_denoising_strength

+

+            if loops == 1:

+                return strength

 

+            progress = loop / (loops - 1)

+            if denoising_curve == "Aggressive":

+                strength = math.sin((progress) * math.pi * 0.5)

+            elif denoising_curve == "Lazy":

+                strength = 1 - math.cos((progress) * math.pi * 0.5)

+            else:

+                strength = progress

+

+            change = (final_denoising_strength - initial_denoising_strength) * strength

+            return initial_denoising_strength + change

+

+        history = []

+

+        for n in range(batch_count):

             # Reset to original init image at the start of each batch

             p.init_images = original_init_image

 

+            # Reset to original denoising strength

+            p.denoising_strength = initial_denoising_strength

+

+            last_image = None

+

             for i in range(loops):

                 p.n_iter = 1

                 p.batch_size = 1

@@ -72,26 +94,46 @@ class Script(scripts.Script):
 

                 processed = processing.process_images(p)

 

+                # Generation cancelled.

+                if state.interrupted:

+                    break

+

                 if initial_seed is None:

                     initial_seed = processed.seed

                     initial_info = processed.info

 

-                init_img = processed.images[0]

-

-                p.init_images = [init_img]

                 p.seed = processed.seed + 1

-                p.denoising_strength = min(max(p.denoising_strength * denoising_strength_change_factor, 0.1), 1)

-                history.append(processed.images[0])

+                p.denoising_strength = calculate_denoising_strength(i + 1)

+                

+                if state.skipped:

+                    break

+

+                last_image = processed.images[0]

+                p.init_images = [last_image]

+                p.inpainting_fill = 1 # Set "masked content" to "original" for next loop.

 

+                if batch_count == 1:

+                    history.append(last_image)

+                    all_images.append(last_image)

+

+            if batch_count > 1 and not state.skipped and not state.interrupted:

+                history.append(last_image)

+                all_images.append(last_image)

+

+            p.inpainting_fill = original_inpainting_fill

+                

+            if state.interrupted:

+                    break

+

+        if len(history) > 1:

             grid = images.image_grid(history, rows=1)

             if opts.grid_save:

                 images.save_image(grid, p.outpath_grids, "grid", initial_seed, p.prompt, opts.grid_format, info=info, short_filename=not opts.grid_extended_filename, grid=True, p=p)

 

-            grids.append(grid)

-            all_images += history

-

-        if opts.return_grid:

-            all_images = grids + all_images

+            if opts.return_grid:

+                grids.append(grid)

+                

+        all_images = grids + all_images

 

         processed = Processed(p, all_images, initial_seed, initial_info)

 

diff --git a/scripts/postprocessing_upscale.py b/scripts/postprocessing_upscale.py
index 8842bd91..11eab31a 100644
--- a/scripts/postprocessing_upscale.py
+++ b/scripts/postprocessing_upscale.py
@@ -17,22 +17,24 @@ class ScriptPostprocessingUpscale(scripts_postprocessing.ScriptPostprocessing):
     def ui(self):

         selected_tab = gr.State(value=0)

 

-        with gr.Tabs(elem_id="extras_resize_mode"):

-            with gr.TabItem('Scale by', elem_id="extras_scale_by_tab") as tab_scale_by:

-                upscaling_resize = gr.Slider(minimum=1.0, maximum=8.0, step=0.05, label="Resize", value=4, elem_id="extras_upscaling_resize")

-

-            with gr.TabItem('Scale to', elem_id="extras_scale_to_tab") as tab_scale_to:

-                with FormRow():

-                    upscaling_resize_w = gr.Number(label="Width", value=512, precision=0, elem_id="extras_upscaling_resize_w")

-                    upscaling_resize_h = gr.Number(label="Height", value=512, precision=0, elem_id="extras_upscaling_resize_h")

-                    upscaling_crop = gr.Checkbox(label='Crop to fit', value=True, elem_id="extras_upscaling_crop")

-

-        with FormRow():

-            extras_upscaler_1 = gr.Dropdown(label='Upscaler 1', elem_id="extras_upscaler_1", choices=[x.name for x in shared.sd_upscalers], value=shared.sd_upscalers[0].name)

-

-        with FormRow():

-            extras_upscaler_2 = gr.Dropdown(label='Upscaler 2', elem_id="extras_upscaler_2", choices=[x.name for x in shared.sd_upscalers], value=shared.sd_upscalers[0].name)

-            extras_upscaler_2_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="Upscaler 2 visibility", value=0.0, elem_id="extras_upscaler_2_visibility")

+        with gr.Column():

+            with FormRow():

+                with gr.Tabs(elem_id="extras_resize_mode"):

+                    with gr.TabItem('Scale by', elem_id="extras_scale_by_tab") as tab_scale_by:

+                        upscaling_resize = gr.Slider(minimum=1.0, maximum=8.0, step=0.05, label="Resize", value=4, elem_id="extras_upscaling_resize")

+

+                    with gr.TabItem('Scale to', elem_id="extras_scale_to_tab") as tab_scale_to:

+                        with FormRow():

+                            upscaling_resize_w = gr.Number(label="Width", value=512, precision=0, elem_id="extras_upscaling_resize_w")

+                            upscaling_resize_h = gr.Number(label="Height", value=512, precision=0, elem_id="extras_upscaling_resize_h")

+                            upscaling_crop = gr.Checkbox(label='Crop to fit', value=True, elem_id="extras_upscaling_crop")

+

+            with FormRow():

+                extras_upscaler_1 = gr.Dropdown(label='Upscaler 1', elem_id="extras_upscaler_1", choices=[x.name for x in shared.sd_upscalers], value=shared.sd_upscalers[0].name)

+

+            with FormRow():

+                extras_upscaler_2 = gr.Dropdown(label='Upscaler 2', elem_id="extras_upscaler_2", choices=[x.name for x in shared.sd_upscalers], value=shared.sd_upscalers[0].name)

+                extras_upscaler_2_visibility = gr.Slider(minimum=0.0, maximum=1.0, step=0.001, label="Upscaler 2 visibility", value=0.0, elem_id="extras_upscaler_2_visibility")

 

         tab_scale_by.select(fn=lambda: 0, inputs=[], outputs=[selected_tab])

         tab_scale_to.select(fn=lambda: 1, inputs=[], outputs=[selected_tab])

diff --git a/scripts/xyz_grid.py b/scripts/xyz_grid.py
index ce584981..3895a795 100644
--- a/scripts/xyz_grid.py
+++ b/scripts/xyz_grid.py
@@ -247,7 +247,7 @@ def draw_xyz_grid(p, xs, ys, zs, x_labels, y_labels, z_labels, cell, draw_legend
 

         state.job = f"{index(ix, iy, iz) + 1} out of {list_size}"

 

-        processed: Processed = cell(x, y, z)

+        processed: Processed = cell(x, y, z, ix, iy, iz)

 

         if processed_result is None:

             # Use our first processed result object as a template container to hold our full results

@@ -515,6 +515,7 @@ class Script(scripts.Script):
         zs = process_axis(z_opt, z_values)

 

         # this could be moved to common code, but unlikely to be ever triggered anywhere else

+        Image.MAX_IMAGE_PIXELS = None # disable check in Pillow and rely on check below to allow large custom image sizes

         grid_mp = round(len(xs) * len(ys) * len(zs) * p.width * p.height / 1000000)

         assert grid_mp < opts.img_max_size_mp, f'Error: Resulting grid would be too large ({grid_mp} MPixels) (max configured size is {opts.img_max_size_mp} MPixels)'

 

@@ -558,8 +559,6 @@ class Script(scripts.Script):
         print(f"X/Y/Z plot will create {len(xs) * len(ys) * len(zs) * image_cell_count} images on {len(zs)} {len(xs)}x{len(ys)} grid{plural_s}{cell_console_text}. (Total steps to process: {total_steps})")

         shared.total_tqdm.updateTotal(total_steps)

 

-        grid_infotext = [None]

-

         state.xyz_plot_x = AxisInfo(x_opt, xs)

         state.xyz_plot_y = AxisInfo(y_opt, ys)

         state.xyz_plot_z = AxisInfo(z_opt, zs)

@@ -588,7 +587,9 @@ class Script(scripts.Script):
             else:

                 second_axes_processed = 'y'

 

-        def cell(x, y, z):

+        grid_infotext = [None] * (1 + len(zs))

+

+        def cell(x, y, z, ix, iy, iz):

             if shared.state.interrupted:

                 return Processed(p, [], p.seed, "")

 

@@ -600,7 +601,9 @@ class Script(scripts.Script):
 

             res = process_images(pc)

 

-            if grid_infotext[0] is None:

+            # Sets subgrid infotexts

+            subgrid_index = 1 + iz

+            if grid_infotext[subgrid_index] is None and ix == 0 and iy == 0:

                 pc.extra_generation_params = copy(pc.extra_generation_params)

                 pc.extra_generation_params['Script'] = self.title()

 

@@ -616,6 +619,12 @@ class Script(scripts.Script):
                     if y_opt.label in ["Seed", "Var. seed"] and not no_fixed_seeds:

                         pc.extra_generation_params["Fixed Y Values"] = ", ".join([str(y) for y in ys])

 

+                grid_infotext[subgrid_index] = processing.create_infotext(pc, pc.all_prompts, pc.all_seeds, pc.all_subseeds)

+

+            # Sets main grid infotext

+            if grid_infotext[0] is None and ix == 0 and iy == 0 and iz == 0:

+                pc.extra_generation_params = copy(pc.extra_generation_params)

+

                 if z_opt.label != 'Nothing':

                     pc.extra_generation_params["Z Type"] = z_opt.label

                     pc.extra_generation_params["Z Values"] = z_values

@@ -650,6 +659,9 @@ class Script(scripts.Script):
 

         z_count = len(zs)

 

+        # Set the grid infotexts to the real ones with extra_generation_params (1 main grid + z_count sub-grids)

+        processed.infotexts[:1+z_count] = grid_infotext[:1+z_count]

+

         if not include_lone_images:

             # Don't need sub-images anymore, drop from list:

             processed.images = processed.images[:z_count+1]