From e5b7ee910e7bb88f08e8876b5732cb034c6fe529 Mon Sep 17 00:00:00 2001
From: MMaker <mmaker@mmaker.moe>
Date: Wed, 4 Jan 2023 04:22:01 -0500
Subject: fix: Save full res of intermediate step

---
 modules/processing.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index a172af0b..93e75ba6 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -705,7 +705,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
                 return
 
             if not isinstance(image, Image.Image):
-                image = sd_samplers.sample_to_image(image, index)
+                image = sd_samplers.sample_to_image(image, index, approximation=0)
 
             images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, suffix="-before-highres-fix")
 
-- 
cgit v1.2.3


From 15fd0b8bc4734ea85bca1acfb12b51465ab9817d Mon Sep 17 00:00:00 2001
From: MMaker <mmaker@mmaker.moe>
Date: Wed, 4 Jan 2023 05:12:54 -0500
Subject: Update processing.py

---
 modules/processing.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index a172af0b..7c72b56a 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -713,7 +713,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             for i in range(samples.shape[0]):
                 save_intermediate(samples, i)
 
-            samples = torch.nn.functional.interpolate(samples, size=(target_height // opt_f, target_width // opt_f), mode=latent_scale_mode)
+            samples = torch.nn.functional.interpolate(samples, size=(target_height // opt_f, target_width // opt_f), mode=latent_scale_mode["mode"], antialias=latent_scale_mode["antialias"])
 
             # Avoid making the inpainting conditioning unless necessary as
             # this does need some extra compute to decode / encode the image again.
-- 
cgit v1.2.3


From 4d66bf2c0d27702cc83b9cc57ebb1f359d18d938 Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Wed, 4 Jan 2023 17:24:46 +0300
Subject: add infotext to "-before-highres-fix" images

---
 modules/processing.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index fd7c7015..c03e77e7 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -136,6 +136,7 @@ class StableDiffusionProcessing():
         self.all_negative_prompts = None
         self.all_seeds = None
         self.all_subseeds = None
+        self.iteration = 0
 
     def txt2img_image_conditioning(self, x, width=None, height=None):
         if self.sampler.conditioning_key not in {'hybrid', 'concat'}:
@@ -544,6 +545,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
             state.job_count = p.n_iter
 
         for n in range(p.n_iter):
+            p.iteration = n
+
             if state.skipped:
                 state.skipped = False
 
@@ -707,7 +710,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             if not isinstance(image, Image.Image):
                 image = sd_samplers.sample_to_image(image, index, approximation=0)
 
-            images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, suffix="-before-highres-fix")
+            info = create_infotext(self, self.all_prompts, self.all_seeds, self.all_subseeds, [], iteration=self.iteration, position_in_batch=index)
+            images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, info=info, suffix="-before-highres-fix")
 
         if latent_scale_mode is not None:
             for i in range(samples.shape[0]):
-- 
cgit v1.2.3


From 525cea924562afd676f55470095268a0f6fca59e Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Wed, 4 Jan 2023 17:58:07 +0300
Subject: use shared function from processing for creating dummy mask when
 training inpainting model

---
 modules/processing.py                          | 39 +++++++++++++-------------
 modules/textual_inversion/textual_inversion.py | 33 ++++++----------------
 2 files changed, 29 insertions(+), 43 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index c03e77e7..c7264aff 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -76,6 +76,24 @@ def apply_overlay(image, paste_loc, index, overlays):
     return image
 
 
+def txt2img_image_conditioning(sd_model, x, width, height):
+    if sd_model.model.conditioning_key not in {'hybrid', 'concat'}:
+        # Dummy zero conditioning if we're not using inpainting model.
+        # Still takes up a bit of memory, but no encoder call.
+        # Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
+        return x.new_zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
+
+    # The "masked-image" in this case will just be all zeros since the entire image is masked.
+    image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
+    image_conditioning = sd_model.get_first_stage_encoding(sd_model.encode_first_stage(image_conditioning))
+
+    # Add the fake full 1s mask to the first dimension.
+    image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
+    image_conditioning = image_conditioning.to(x.dtype)
+
+    return image_conditioning
+
+
 class StableDiffusionProcessing():
     """
     The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
@@ -139,26 +157,9 @@ class StableDiffusionProcessing():
         self.iteration = 0
 
     def txt2img_image_conditioning(self, x, width=None, height=None):
-        if self.sampler.conditioning_key not in {'hybrid', 'concat'}:
-            # Dummy zero conditioning if we're not using inpainting model.
-            # Still takes up a bit of memory, but no encoder call.
-            # Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
-            return x.new_zeros(x.shape[0], 5, 1, 1)
+        self.is_using_inpainting_conditioning = self.sd_model.model.conditioning_key in {'hybrid', 'concat'}
 
-        self.is_using_inpainting_conditioning = True
-
-        height = height or self.height
-        width = width or self.width
-
-        # The "masked-image" in this case will just be all zeros since the entire image is masked.
-        image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
-        image_conditioning = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image_conditioning))
-
-        # Add the fake full 1s mask to the first dimension.
-        image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
-        image_conditioning = image_conditioning.to(x.dtype)
-
-        return image_conditioning
+        return txt2img_image_conditioning(self.sd_model, x, width or self.width, height or self.height)
 
     def depth2img_image_conditioning(self, source_image):
         # Use the AddMiDaS helper to Format our source image to suit the MiDaS model
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py
index 8731ea5d..2250e41b 100644
--- a/modules/textual_inversion/textual_inversion.py
+++ b/modules/textual_inversion/textual_inversion.py
@@ -252,26 +252,6 @@ def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, dat
         assert log_directory, "Log directory is empty"
 
 
-def create_dummy_mask(x, width=None, height=None):
-    if shared.sd_model.model.conditioning_key in {'hybrid', 'concat'}:
-
-        # The "masked-image" in this case will just be all zeros since the entire image is masked.
-        image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
-        image_conditioning = shared.sd_model.get_first_stage_encoding(shared.sd_model.encode_first_stage(image_conditioning))
-
-        # Add the fake full 1s mask to the first dimension.
-        image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
-        image_conditioning = image_conditioning.to(x.dtype)
-
-    else:
-        # Dummy zero conditioning if we're not using inpainting model.
-        # Still takes up a bit of memory, but no encoder call.
-        # Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
-        image_conditioning = torch.zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
-
-    return image_conditioning
-
-
 def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, steps, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_embedding_every, template_file, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
     save_embedding_every = save_embedding_every or 0
     create_image_every = create_image_every or 0
@@ -346,7 +326,6 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_
         else:
             print("No saved optimizer exists in checkpoint")
 
-
     scaler = torch.cuda.amp.GradScaler()
 
     batch_size = ds.batch_size
@@ -362,7 +341,9 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_
     forced_filename = "<none>"
     embedding_yet_to_be_embedded = False
 
+    is_training_inpainting_model = shared.sd_model.model.conditioning_key in {'hybrid', 'concat'}
     img_c = None
+
     pbar = tqdm.tqdm(total=steps - initial_step)
     try:
         for i in range((steps-initial_step) * gradient_step):
@@ -384,10 +365,14 @@ def train_embedding(embedding_name, learn_rate, batch_size, gradient_step, data_
                     x = batch.latent_sample.to(devices.device, non_blocking=pin_memory)
                     c = shared.sd_model.cond_stage_model(batch.cond_text)
 
-                    if img_c is None:
-                        img_c = create_dummy_mask(c, training_width, training_height)
+                    if is_training_inpainting_model:
+                        if img_c is None:
+                            img_c = processing.txt2img_image_conditioning(shared.sd_model, c, training_width, training_height)
+
+                        cond = {"c_concat": [img_c], "c_crossattn": [c]}
+                    else:
+                        cond = c
 
-                    cond = {"c_concat": [img_c], "c_crossattn": [c]}
                     loss = shared.sd_model(x, cond)[0] / gradient_step
                     del x
 
-- 
cgit v1.2.3


From 097a90b88bb92878cf435c513b4757b5b82ae299 Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Wed, 4 Jan 2023 19:19:11 +0300
Subject: add XY plot parameters to grid image and do not add them to
 individual images

---
 modules/processing.py |  2 +-
 scripts/xy_grid.py    | 38 ++++++++++++++++++++++++--------------
 2 files changed, 25 insertions(+), 15 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index c7264aff..47712159 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -422,7 +422,7 @@ def fix_seed(p):
     p.subseed = get_fixed_seed(p.subseed)
 
 
-def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments, iteration=0, position_in_batch=0):
+def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iteration=0, position_in_batch=0):
     index = position_in_batch + iteration * p.batch_size
 
     clip_skip = getattr(p, 'clip_skip', opts.CLIP_stop_at_last_layers)
diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py
index 59907f0b..78ff12c5 100644
--- a/scripts/xy_grid.py
+++ b/scripts/xy_grid.py
@@ -10,7 +10,7 @@ import numpy as np
 import modules.scripts as scripts
 import gradio as gr
 
-from modules import images, paths, sd_samplers
+from modules import images, paths, sd_samplers, processing
 from modules.hypernetworks import hypernetwork
 from modules.processing import process_images, Processed, StableDiffusionProcessingTxt2Img
 from modules.shared import opts, cmd_opts, state
@@ -285,6 +285,7 @@ re_range_float = re.compile(r"\s*([+-]?\s*\d+(?:.\d*)?)\s*-\s*([+-]?\s*\d+(?:.\d
 re_range_count = re.compile(r"\s*([+-]?\s*\d+)\s*-\s*([+-]?\s*\d+)(?:\s*\[(\d+)\s*\])?\s*")
 re_range_count_float = re.compile(r"\s*([+-]?\s*\d+(?:.\d*)?)\s*-\s*([+-]?\s*\d+(?:.\d*)?)(?:\s*\[(\d+(?:.\d*)?)\s*\])?\s*")
 
+
 class Script(scripts.Script):
     def title(self):
         return "X/Y plot"
@@ -381,7 +382,7 @@ class Script(scripts.Script):
         ys = process_axis(y_opt, y_values)
 
         def fix_axis_seeds(axis_opt, axis_list):
-            if axis_opt.label in ['Seed','Var. seed']:
+            if axis_opt.label in ['Seed', 'Var. seed']:
                 return [int(random.randrange(4294967294)) if val is None or val == '' or val == -1 else val for val in axis_list]
             else:
                 return axis_list
@@ -403,24 +404,33 @@ class Script(scripts.Script):
         print(f"X/Y plot will create {len(xs) * len(ys) * p.n_iter} images on a {len(xs)}x{len(ys)} grid. (Total steps to process: {total_steps * p.n_iter})")
         shared.total_tqdm.updateTotal(total_steps * p.n_iter)
 
+        grid_infotext = [None]
+
         def cell(x, y):
             pc = copy(p)
             x_opt.apply(pc, x, xs)
             y_opt.apply(pc, y, ys)
 
-            return process_images(pc)
+            res = process_images(pc)
+
+            if grid_infotext[0] is None:
+                pc.extra_generation_params = copy(pc.extra_generation_params)
+
+                if x_opt.label != 'Nothing':
+                    pc.extra_generation_params["X Type"] = x_opt.label
+                    pc.extra_generation_params["X Values"] = x_values
+                    if x_opt.label in ["Seed", "Var. seed"] and not no_fixed_seeds:
+                        pc.extra_generation_params["Fixed X Values"] = ", ".join([str(x) for x in xs])
+
+                if y_opt.label != 'Nothing':
+                    pc.extra_generation_params["Y Type"] = y_opt.label
+                    pc.extra_generation_params["Y Values"] = y_values
+                    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])
 
-        if not x_opt.label == 'Nothing':
-            p.extra_generation_params["XY Plot X Type"] = x_opt.label
-            p.extra_generation_params["XY Plot X Values"] = '{' + x_values + '}'
-            if x_opt.label in ["Seed","Var. seed"] and not no_fixed_seeds:
-                p.extra_generation_params["XY Plot Fixed X Values"] = '{' + ", ".join([str(x) for x in xs])+ '}'
+                grid_infotext[0] = processing.create_infotext(pc, pc.all_prompts, pc.all_seeds, pc.all_subseeds)
 
-        if not y_opt.label == 'Nothing':
-            p.extra_generation_params["XY Plot Y Type"] = y_opt.label
-            p.extra_generation_params["XY Plot Y Values"] = '{' + y_values + '}'
-            if y_opt.label in ["Seed","Var. seed"] and not no_fixed_seeds:
-                p.extra_generation_params["XY Plot Fixed Y Values"] = '{' + ", ".join([str(y) for y in ys])+ '}'
+            return res
 
         with SharedSettingsStackHelper():
             processed = draw_xy_grid(
@@ -435,6 +445,6 @@ class Script(scripts.Script):
             )
 
         if opts.grid_save:
-            images.save_image(processed.images[0], p.outpath_grids, "xy_grid", extension=opts.grid_format, prompt=p.prompt, seed=processed.seed, grid=True, p=p)
+            images.save_image(processed.images[0], p.outpath_grids, "xy_grid", info=grid_infotext[0], extension=opts.grid_format, prompt=p.prompt, seed=processed.seed, grid=True, p=p)
 
         return processed
-- 
cgit v1.2.3


From 81490780949fffed77493b4bd741e96ec737fe27 Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Wed, 4 Jan 2023 22:04:40 +0300
Subject: added the option to specify target resolution with possibility of
 truncating for hires fix; also sampling steps

---
 javascript/hints.js                        | 11 ++++---
 modules/generation_parameters_copypaste.py |  9 ++++--
 modules/processing.py                      | 51 +++++++++++++++++++++++++++---
 modules/txt2img.py                         |  5 ++-
 modules/ui.py                              | 24 ++++++++++----
 5 files changed, 81 insertions(+), 19 deletions(-)

(limited to 'modules/processing.py')

diff --git a/javascript/hints.js b/javascript/hints.js
index 63e17e05..dda66e09 100644
--- a/javascript/hints.js
+++ b/javascript/hints.js
@@ -81,9 +81,6 @@ titles = {
 
     "vram": "Torch active: Peak amount of VRAM used by Torch during generation, excluding cached data.\nTorch reserved: Peak amount of VRAM allocated by Torch, including all active and cached data.\nSys VRAM: Peak amount of VRAM allocation across all applications / total GPU VRAM (peak utilization%).",
 
-    "Highres. fix": "Use a two step process to partially create an image at smaller resolution, upscale, and then improve details in it without changing composition",
-    "Scale latent": "Uscale the image in latent space. Alternative is to produce the full image from latent representation, upscale that, and then move it back to latent space.",
-
     "Eta noise seed delta": "If this values is non-zero, it will be added to seed and used to initialize RNG for noises when using samplers with Eta. You can use this to produce even more variation of images, or you can use this to match images of other software if you know what you are doing.",
     "Do not add watermark to images": "If this option is enabled, watermark will not be added to created images. Warning: if you do not add watermark, you may be behaving in an unethical manner.",
 
@@ -100,7 +97,13 @@ titles = {
     "Clip skip": "Early stopping parameter for CLIP model; 1 is stop at last layer as usual, 2 is stop at penultimate layer, etc.",
 
     "Approx NN": "Cheap neural network approximation. Very fast compared to VAE, but produces pictures with 4 times smaller horizontal/vertical resoluton and lower quality.",
-    "Approx cheap": "Very cheap approximation. Very fast compared to VAE, but produces pictures with 8 times smaller horizontal/vertical resoluton and extremely low quality."
+    "Approx cheap": "Very cheap approximation. Very fast compared to VAE, but produces pictures with 8 times smaller horizontal/vertical resoluton and extremely low quality.",
+
+    "Hires. fix": "Use a two step process to partially create an image at smaller resolution, upscale, and then improve details in it without changing composition",
+    "Hires steps": "Number of sampling steps for upscaled picture. If 0, uses same as for original.",
+    "Upscale by": "Adjusts the size of the image by multiplying the original width and height by the selected value. Ignored if either Resize width to or Resize height to are non-zero.",
+    "Resize width to": "Resizes image to this width. If 0, width is inferred from either of two nearby sliders.",
+    "Resize height to": "Resizes image to this height. If 0, height is inferred from either of two nearby sliders."
 }
 
 
diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py
index 4baf4d9a..12a9de3d 100644
--- a/modules/generation_parameters_copypaste.py
+++ b/modules/generation_parameters_copypaste.py
@@ -212,11 +212,10 @@ def restore_old_hires_fix_params(res):
         firstpass_width = math.ceil(scale * width / 64) * 64
         firstpass_height = math.ceil(scale * height / 64) * 64
 
-    hr_scale = width / firstpass_width if firstpass_width > 0 else height / firstpass_height
-
     res['Size-1'] = firstpass_width
     res['Size-2'] = firstpass_height
-    res['Hires upscale'] = hr_scale
+    res['Hires resize-1'] = width
+    res['Hires resize-2'] = height
 
 
 def parse_generation_parameters(x: str):
@@ -276,6 +275,10 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
         hypernet_hash = res.get("Hypernet hash", None)
         res["Hypernet"] = find_hypernetwork_key(hypernet_name, hypernet_hash)
 
+    if "Hires resize-1" not in res:
+        res["Hires resize-1"] = 0
+        res["Hires resize-2"] = 0
+
     restore_old_hires_fix_params(res)
 
     return res
diff --git a/modules/processing.py b/modules/processing.py
index 47712159..9cad05f2 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -662,12 +662,17 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
 class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
     sampler = None
 
-    def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, **kwargs):
+    def __init__(self, enable_hr: bool = False, denoising_strength: float = 0.75, firstphase_width: int = 0, firstphase_height: int = 0, hr_scale: float = 2.0, hr_upscaler: str = None, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, **kwargs):
         super().__init__(**kwargs)
         self.enable_hr = enable_hr
         self.denoising_strength = denoising_strength
         self.hr_scale = hr_scale
         self.hr_upscaler = hr_upscaler
+        self.hr_second_pass_steps = hr_second_pass_steps
+        self.hr_resize_x = hr_resize_x
+        self.hr_resize_y = hr_resize_y
+        self.hr_upscale_to_x = hr_resize_x
+        self.hr_upscale_to_y = hr_resize_y
 
         if firstphase_width != 0 or firstphase_height != 0:
             print("firstphase_width/firstphase_height no longer supported; use hr_scale", file=sys.stderr)
@@ -675,6 +680,9 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             self.width = firstphase_width
             self.height = firstphase_height
 
+        self.truncate_x = 0
+        self.truncate_y = 0
+
     def init(self, all_prompts, all_seeds, all_subseeds):
         if self.enable_hr:
             if state.job_count == -1:
@@ -682,7 +690,38 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             else:
                 state.job_count = state.job_count * 2
 
-            self.extra_generation_params["Hires upscale"] = self.hr_scale
+            if self.hr_resize_x == 0 and self.hr_resize_y == 0:
+                self.extra_generation_params["Hires upscale"] = self.hr_scale
+                self.hr_upscale_to_x = int(self.width * self.hr_scale)
+                self.hr_upscale_to_y = int(self.height * self.hr_scale)
+            else:
+                self.extra_generation_params["Hires resize"] = f"{self.hr_resize_x}x{self.hr_resize_y}"
+
+                if self.hr_resize_y == 0:
+                    self.hr_upscale_to_x = self.hr_resize_x
+                    self.hr_upscale_to_y = self.hr_resize_x * self.height // self.width
+                elif self.hr_resize_x == 0:
+                    self.hr_upscale_to_x = self.hr_resize_y * self.width // self.height
+                    self.hr_upscale_to_y = self.hr_resize_y
+                else:
+                    target_w = self.hr_resize_x
+                    target_h = self.hr_resize_y
+                    src_ratio = self.width / self.height
+                    dst_ratio = self.hr_resize_x / self.hr_resize_y
+
+                    if src_ratio < dst_ratio:
+                        self.hr_upscale_to_x = self.hr_resize_x
+                        self.hr_upscale_to_y = self.hr_resize_x * self.height // self.width
+                    else:
+                        self.hr_upscale_to_x = self.hr_resize_y * self.width // self.height
+                        self.hr_upscale_to_y = self.hr_resize_y
+
+                    self.truncate_x = (self.hr_upscale_to_x - target_w) // opt_f
+                    self.truncate_y = (self.hr_upscale_to_y - target_h) // opt_f
+
+            if self.hr_second_pass_steps:
+                self.extra_generation_params["Hires steps"] = self.hr_second_pass_steps
+
             if self.hr_upscaler is not None:
                 self.extra_generation_params["Hires upscaler"] = self.hr_upscaler
 
@@ -699,8 +738,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         if not self.enable_hr:
             return samples
 
-        target_width = int(self.width * self.hr_scale)
-        target_height = int(self.height * self.hr_scale)
+        target_width = self.hr_upscale_to_x
+        target_height = self.hr_upscale_to_y
 
         def save_intermediate(image, index):
             """saves image before applying hires fix, if enabled in options; takes as an argument either an image or batch with latent space images"""
@@ -755,13 +794,15 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
         self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model)
 
+        samples = samples[:, :, self.truncate_y//2:samples.shape[2]-(self.truncate_y+1)//2, self.truncate_x//2:samples.shape[3]-(self.truncate_x+1)//2]
+
         noise = create_random_tensors(samples.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=subseed_strength, p=self)
 
         # GC now before running the next img2img to prevent running out of memory
         x = None
         devices.torch_gc()
 
-        samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.steps, image_conditioning=image_conditioning)
+        samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.hr_second_pass_steps or self.steps, image_conditioning=image_conditioning)
 
         return samples
 
diff --git a/modules/txt2img.py b/modules/txt2img.py
index e189a899..38b5f591 100644
--- a/modules/txt2img.py
+++ b/modules/txt2img.py
@@ -8,7 +8,7 @@ import modules.processing as processing
 from modules.ui import plaintext_to_html
 
 
-def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, *args):
+def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, *args):
     p = StableDiffusionProcessingTxt2Img(
         sd_model=shared.sd_model,
         outpath_samples=opts.outdir_samples or opts.outdir_txt2img_samples,
@@ -35,6 +35,9 @@ def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2:
         denoising_strength=denoising_strength if enable_hr else None,
         hr_scale=hr_scale,
         hr_upscaler=hr_upscaler,
+        hr_second_pass_steps=hr_second_pass_steps,
+        hr_resize_x=hr_resize_x,
+        hr_resize_y=hr_resize_y,
     )
 
     p.scripts = modules.scripts.scripts_txt2img
diff --git a/modules/ui.py b/modules/ui.py
index 44f4f3a4..04091e67 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -637,10 +637,10 @@ def create_sampler_and_steps_selection(choices, tabname):
         with FormRow(elem_id=f"sampler_selection_{tabname}"):
             sampler_index = gr.Dropdown(label='Sampling method', elem_id=f"{tabname}_sampling", choices=[x.name for x in choices], value=choices[0].name, type="index")
             sampler_index.save_to_config = True
-            steps = gr.Slider(minimum=1, maximum=150, step=1, elem_id=f"{tabname}_steps", label="Sampling Steps", value=20)
+            steps = gr.Slider(minimum=1, maximum=150, step=1, elem_id=f"{tabname}_steps", label="Sampling steps", value=20)
     else:
         with FormGroup(elem_id=f"sampler_selection_{tabname}"):
-            steps = gr.Slider(minimum=1, maximum=150, step=1, elem_id=f"{tabname}_steps", label="Sampling Steps", value=20)
+            steps = gr.Slider(minimum=1, maximum=150, step=1, elem_id=f"{tabname}_steps", label="Sampling steps", value=20)
             sampler_index = gr.Radio(label='Sampling method', elem_id=f"{tabname}_sampling", choices=[x.name for x in choices], value=choices[0].name, type="index")
 
     return steps, sampler_index
@@ -709,10 +709,16 @@ def create_ui():
                             enable_hr = gr.Checkbox(label='Hires. fix', value=False, elem_id="txt2img_enable_hr")
 
                     elif category == "hires_fix":
-                        with FormRow(visible=False, elem_id="txt2img_hires_fix") as hr_options:
-                            hr_upscaler = gr.Dropdown(label="Upscaler", elem_id="txt2img_hr_upscaler", choices=[*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]], value=shared.latent_upscale_default_mode)
-                            hr_scale = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Upscale by", value=2.0, elem_id="txt2img_hr_scale")
-                            denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7, elem_id="txt2img_denoising_strength")
+                        with FormGroup(visible=False, elem_id="txt2img_hires_fix") as hr_options:
+                            with FormRow(elem_id="txt2img_hires_fix_row1"):
+                                hr_upscaler = gr.Dropdown(label="Upscaler", elem_id="txt2img_hr_upscaler", choices=[*shared.latent_upscale_modes, *[x.name for x in shared.sd_upscalers]], value=shared.latent_upscale_default_mode)
+                                hr_second_pass_steps = gr.Slider(minimum=0, maximum=150, step=1, label='Hires steps', value=0, elem_id="txt2img_hires_steps")
+                                denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7, elem_id="txt2img_denoising_strength")
+
+                            with FormRow(elem_id="txt2img_hires_fix_row2"):
+                                hr_scale = gr.Slider(minimum=1.0, maximum=4.0, step=0.05, label="Upscale by", value=2.0, elem_id="txt2img_hr_scale")
+                                hr_resize_x = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize width to", value=0, elem_id="txt2img_hr_resize_x")
+                                hr_resize_y = gr.Slider(minimum=0, maximum=2048, step=8, label="Resize height to", value=0, elem_id="txt2img_hr_resize_y")
 
                     elif category == "batch":
                         if not opts.dimensions_and_batch_together:
@@ -753,6 +759,9 @@ def create_ui():
                     denoising_strength,
                     hr_scale,
                     hr_upscaler,
+                    hr_second_pass_steps,
+                    hr_resize_x,
+                    hr_resize_y,
                 ] + custom_inputs,
 
                 outputs=[
@@ -804,6 +813,9 @@ def create_ui():
                 (hr_options, lambda d: gr.Row.update(visible="Denoising strength" in d)),
                 (hr_scale, "Hires upscale"),
                 (hr_upscaler, "Hires upscaler"),
+                (hr_second_pass_steps, "Hires steps"),
+                (hr_resize_x, "Hires resize-1"),
+                (hr_resize_y, "Hires resize-2"),
                 *modules.scripts.scripts_txt2img.infotext_fields
             ]
             parameters_copypaste.add_paste_fields("txt2img", None, txt2img_paste_fields)
-- 
cgit v1.2.3


From bc43293c640aef65df3136de9e5bd8b7e79eb3e0 Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Wed, 4 Jan 2023 23:56:43 +0300
Subject: fix incorrect display/calculation for number of steps for hires fix
 in progress bars

---
 modules/processing.py  | 9 ++++++---
 modules/sd_samplers.py | 5 +++--
 modules/shared.py      | 4 +++-
 3 files changed, 12 insertions(+), 6 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index 9cad05f2..f28e7212 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -685,10 +685,13 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
     def init(self, all_prompts, all_seeds, all_subseeds):
         if self.enable_hr:
-            if state.job_count == -1:
-                state.job_count = self.n_iter * 2
-            else:
+            if not state.processing_has_refined_job_count:
+                if state.job_count == -1:
+                    state.job_count = self.n_iter
+
+                shared.total_tqdm.updateTotal((self.steps + (self.hr_second_pass_steps or self.steps)) * state.job_count)
                 state.job_count = state.job_count * 2
+                state.processing_has_refined_job_count = True
 
             if self.hr_resize_x == 0 and self.hr_resize_y == 0:
                 self.extra_generation_params["Hires upscale"] = self.hr_scale
diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py
index e904d860..3851a77f 100644
--- a/modules/sd_samplers.py
+++ b/modules/sd_samplers.py
@@ -97,8 +97,9 @@ sampler_extra_params = {
 
 def setup_img2img_steps(p, steps=None):
     if opts.img2img_fix_steps or steps is not None:
-        steps = int((steps or p.steps) / min(p.denoising_strength, 0.999)) if p.denoising_strength > 0 else 0
-        t_enc = p.steps - 1
+        requested_steps = (steps or p.steps)
+        steps = int(requested_steps / min(p.denoising_strength, 0.999)) if p.denoising_strength > 0 else 0
+        t_enc = requested_steps - 1
     else:
         steps = p.steps
         t_enc = int(min(p.denoising_strength, 0.999) * steps)
diff --git a/modules/shared.py b/modules/shared.py
index 54a6ba23..04c545ee 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -153,6 +153,7 @@ class State:
     job = ""
     job_no = 0
     job_count = 0
+    processing_has_refined_job_count = False
     job_timestamp = '0'
     sampling_step = 0
     sampling_steps = 0
@@ -194,6 +195,7 @@ class State:
     def begin(self):
         self.sampling_step = 0
         self.job_count = -1
+        self.processing_has_refined_job_count = False
         self.job_no = 0
         self.job_timestamp = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
         self.current_latent = None
@@ -608,7 +610,7 @@ class TotalTQDM:
             return
         if self._tqdm is None:
             self.reset()
-        self._tqdm.total=new_total
+        self._tqdm.total = new_total
 
     def clear(self):
         if self._tqdm is not None:
-- 
cgit v1.2.3


From 99b67cff0b48c4a1ad6e14d9cc591b11db6e293c Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Thu, 5 Jan 2023 01:25:52 +0300
Subject: make hires fix not do anything if the user chooses the second pass
 resolution to be the same as first pass resolution

---
 modules/processing.py | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index f28e7212..7e853287 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -683,16 +683,9 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         self.truncate_x = 0
         self.truncate_y = 0
 
+
     def init(self, all_prompts, all_seeds, all_subseeds):
         if self.enable_hr:
-            if not state.processing_has_refined_job_count:
-                if state.job_count == -1:
-                    state.job_count = self.n_iter
-
-                shared.total_tqdm.updateTotal((self.steps + (self.hr_second_pass_steps or self.steps)) * state.job_count)
-                state.job_count = state.job_count * 2
-                state.processing_has_refined_job_count = True
-
             if self.hr_resize_x == 0 and self.hr_resize_y == 0:
                 self.extra_generation_params["Hires upscale"] = self.hr_scale
                 self.hr_upscale_to_x = int(self.width * self.hr_scale)
@@ -722,6 +715,22 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
                     self.truncate_x = (self.hr_upscale_to_x - target_w) // opt_f
                     self.truncate_y = (self.hr_upscale_to_y - target_h) // opt_f
 
+            # special case: the user has chosen to do nothing
+            if self.hr_upscale_to_x == self.width and self.hr_upscale_to_y == self.height:
+                self.enable_hr = False
+                self.denoising_strength = None
+                self.extra_generation_params.pop("Hires upscale", None)
+                self.extra_generation_params.pop("Hires resize", None)
+                return
+
+            if not state.processing_has_refined_job_count:
+                if state.job_count == -1:
+                    state.job_count = self.n_iter
+
+                shared.total_tqdm.updateTotal((self.steps + (self.hr_second_pass_steps or self.steps)) * state.job_count)
+                state.job_count = state.job_count * 2
+                state.processing_has_refined_job_count = True
+
             if self.hr_second_pass_steps:
                 self.extra_generation_params["Hires steps"] = self.hr_second_pass_steps
 
-- 
cgit v1.2.3