From f4535f6e4f001314bd155bc6e1b6908e02792b9a Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Sat, 31 Dec 2022 23:40:55 +0300
Subject: make it so that memory/embeddings info is displayed in a separate UI
 element from generation parameters, and is preserved when you change the
 displayed infotext by clicking on gallery images

---
 modules/txt2img.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'modules/txt2img.py')

diff --git a/modules/txt2img.py b/modules/txt2img.py
index c8f81176..7f61e19a 100644
--- a/modules/txt2img.py
+++ b/modules/txt2img.py
@@ -59,4 +59,4 @@ def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2:
     if opts.do_not_show_images:
         processed.images = []
 
-    return processed.images, generation_info_js, plaintext_to_html(processed.info)
+    return processed.images, generation_info_js, plaintext_to_html(processed.info), plaintext_to_html(processed.comments)
-- 
cgit v1.2.3


From ef27a18b6b7cb1a8eebdc9b2e88d25baf2c2414d Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Mon, 2 Jan 2023 19:42:10 +0300
Subject: Hires fix rework

---
 modules/generation_parameters_copypaste.py | 32 ++++++++++++++
 modules/images.py                          | 24 +++++++++--
 modules/processing.py                      | 68 ++++++++++++------------------
 modules/shared.py                          |  7 ++-
 modules/txt2img.py                         |  6 +--
 modules/ui.py                              | 15 +++----
 scripts/xy_grid.py                         |  4 +-
 7 files changed, 96 insertions(+), 60 deletions(-)

(limited to 'modules/txt2img.py')

diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py
index 8e7f0df0..d6fa822b 100644
--- a/modules/generation_parameters_copypaste.py
+++ b/modules/generation_parameters_copypaste.py
@@ -1,5 +1,6 @@
 import base64
 import io
+import math
 import os
 import re
 from pathlib import Path
@@ -164,6 +165,35 @@ def find_hypernetwork_key(hypernet_name, hypernet_hash=None):
     return None
 
 
+def restore_old_hires_fix_params(res):
+    """for infotexts that specify old First pass size parameter, convert it into
+    width, height, and hr scale"""
+
+    firstpass_width = res.get('First pass size-1', None)
+    firstpass_height = res.get('First pass size-2', None)
+
+    if firstpass_width is None or firstpass_height is None:
+        return
+
+    firstpass_width, firstpass_height = int(firstpass_width), int(firstpass_height)
+    width = int(res.get("Size-1", 512))
+    height = int(res.get("Size-2", 512))
+
+    if firstpass_width == 0 or firstpass_height == 0:
+        # old algorithm for auto-calculating first pass size
+        desired_pixel_count = 512 * 512
+        actual_pixel_count = width * height
+        scale = math.sqrt(desired_pixel_count / actual_pixel_count)
+        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
+
+
 def parse_generation_parameters(x: str):
     """parses generation parameters string, the one you see in text field under the picture in UI:
 ```
@@ -221,6 +251,8 @@ 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)
 
+    restore_old_hires_fix_params(res)
+
     return res
 
 
diff --git a/modules/images.py b/modules/images.py
index f84fd485..c3a5fc8b 100644
--- a/modules/images.py
+++ b/modules/images.py
@@ -230,16 +230,32 @@ def draw_prompt_matrix(im, width, height, all_prompts):
     return draw_grid_annotations(im, width, height, hor_texts, ver_texts)
 
 
-def resize_image(resize_mode, im, width, height):
+def resize_image(resize_mode, im, width, height, upscaler_name=None):
+    """
+    Resizes an image with the specified resize_mode, width, and height.
+
+    Args:
+        resize_mode: The mode to use when resizing the image.
+            0: Resize the image to the specified width and height.
+            1: Resize the image to fill the specified width and height, maintaining the aspect ratio, and then center the image within the dimensions, cropping the excess.
+            2: Resize the image to fit within the specified width and height, maintaining the aspect ratio, and then center the image within the dimensions, filling empty with data from image.
+        im: The image to resize.
+        width: The width to resize the image to.
+        height: The height to resize the image to.
+        upscaler_name: The name of the upscaler to use. If not provided, defaults to opts.upscaler_for_img2img.
+    """
+
+    upscaler_name = upscaler_name or opts.upscaler_for_img2img
+
     def resize(im, w, h):
-        if opts.upscaler_for_img2img is None or opts.upscaler_for_img2img == "None" or im.mode == 'L':
+        if upscaler_name is None or upscaler_name == "None" or im.mode == 'L':
             return im.resize((w, h), resample=LANCZOS)
 
         scale = max(w / im.width, h / im.height)
 
         if scale > 1.0:
-            upscalers = [x for x in shared.sd_upscalers if x.name == opts.upscaler_for_img2img]
-            assert len(upscalers) > 0, f"could not find upscaler named {opts.upscaler_for_img2img}"
+            upscalers = [x for x in shared.sd_upscalers if x.name == upscaler_name]
+            assert len(upscalers) > 0, f"could not find upscaler named {upscaler_name}"
 
             upscaler = upscalers[0]
             im = upscaler.scaler.upscale(im, scale, upscaler.data_path)
diff --git a/modules/processing.py b/modules/processing.py
index 42dc19ea..4654570c 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -658,14 +658,18 @@ 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, **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, **kwargs):
         super().__init__(**kwargs)
         self.enable_hr = enable_hr
         self.denoising_strength = denoising_strength
-        self.firstphase_width = firstphase_width
-        self.firstphase_height = firstphase_height
-        self.truncate_x = 0
-        self.truncate_y = 0
+        self.hr_scale = hr_scale
+        self.hr_upscaler = hr_upscaler
+
+        if firstphase_width != 0 or firstphase_height != 0:
+            print("firstphase_width/firstphase_height no longer supported; use hr_scale", file=sys.stderr)
+            self.hr_scale = self.width / firstphase_width
+            self.width = firstphase_width
+            self.height = firstphase_height
 
     def init(self, all_prompts, all_seeds, all_subseeds):
         if self.enable_hr:
@@ -674,47 +678,29 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             else:
                 state.job_count = state.job_count * 2
 
-            self.extra_generation_params["First pass size"] = f"{self.firstphase_width}x{self.firstphase_height}"
-
-            if self.firstphase_width == 0 or self.firstphase_height == 0:
-                desired_pixel_count = 512 * 512
-                actual_pixel_count = self.width * self.height
-                scale = math.sqrt(desired_pixel_count / actual_pixel_count)
-                self.firstphase_width = math.ceil(scale * self.width / 64) * 64
-                self.firstphase_height = math.ceil(scale * self.height / 64) * 64
-                firstphase_width_truncated = int(scale * self.width)
-                firstphase_height_truncated = int(scale * self.height)
-
-            else:
-
-                width_ratio = self.width / self.firstphase_width
-                height_ratio = self.height / self.firstphase_height
-
-                if width_ratio > height_ratio:
-                    firstphase_width_truncated = self.firstphase_width
-                    firstphase_height_truncated = self.firstphase_width * self.height / self.width
-                else:
-                    firstphase_width_truncated = self.firstphase_height * self.width / self.height
-                    firstphase_height_truncated = self.firstphase_height
-
-            self.truncate_x = int(self.firstphase_width - firstphase_width_truncated) // opt_f
-            self.truncate_y = int(self.firstphase_height - firstphase_height_truncated) // opt_f
+            self.extra_generation_params["Hires upscale"] = self.hr_scale
+            if self.hr_upscaler is not None:
+                self.extra_generation_params["Hires upscaler"] = self.hr_upscaler
 
     def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts):
         self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model)
 
+        latent_scale_mode = shared.latent_upscale_modes.get(self.hr_upscaler, None) if self.hr_upscaler is not None else shared.latent_upscale_default_mode
+        if self.enable_hr and latent_scale_mode is None:
+            assert len([x for x in shared.sd_upscalers if x.name == self.hr_upscaler]) > 0, f"could not find upscaler named {self.hr_upscaler}"
+
+        x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
+        samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
+
         if not self.enable_hr:
-            x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
-            samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
             return samples
 
-        x = create_random_tensors([opt_C, self.firstphase_height // opt_f, self.firstphase_width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
-        samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x, self.firstphase_width, self.firstphase_height))
-
-        samples = samples[:, :, self.truncate_y//2:samples.shape[2]-self.truncate_y//2, self.truncate_x//2:samples.shape[3]-self.truncate_x//2]
+        target_width = int(self.width * self.hr_scale)
+        target_height = int(self.height * self.hr_scale)
 
-        """saves image before applying hires fix, if enabled in options; takes as an argument either an image or batch with latent space images"""
         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"""
+
             if not opts.save or self.do_not_save_samples or not opts.save_images_before_highres_fix:
                 return
 
@@ -723,11 +709,11 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
             images.save_image(image, self.outpath_samples, "", seeds[index], prompts[index], opts.samples_format, suffix="-before-highres-fix")
 
-        if opts.use_scale_latent_for_hires_fix:
+        if latent_scale_mode is not None:
             for i in range(samples.shape[0]):
                 save_intermediate(samples, i)
 
-            samples = torch.nn.functional.interpolate(samples, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")
+            samples = torch.nn.functional.interpolate(samples, size=(target_height // opt_f, target_width // opt_f), mode=latent_scale_mode)
 
             # Avoid making the inpainting conditioning unless necessary as
             # this does need some extra compute to decode / encode the image again.
@@ -747,7 +733,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
                 save_intermediate(image, i)
 
-                image = images.resize_image(0, image, self.width, self.height)
+                image = images.resize_image(0, image, target_width, target_height, upscaler_name=self.hr_upscaler)
                 image = np.array(image).astype(np.float32) / 255.0
                 image = np.moveaxis(image, 2, 0)
                 batch_images.append(image)
@@ -764,7 +750,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
         self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model)
 
-        noise = create_random_tensors(samples.shape[1:], seeds=seeds, subseeds=subseeds, subseed_strength=subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
+        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
diff --git a/modules/shared.py b/modules/shared.py
index 7f430b93..b65559ee 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -327,7 +327,6 @@ options_templates.update(options_section(('upscaling', "Upscaling"), {
     "ESRGAN_tile_overlap": OptionInfo(8, "Tile overlap, in pixels for ESRGAN upscalers. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}),
     "realesrgan_enabled_models": OptionInfo(["R-ESRGAN 4x+", "R-ESRGAN 4x+ Anime6B"], "Select which Real-ESRGAN models to show in the web UI. (Requires restart)", gr.CheckboxGroup, lambda: {"choices": realesrgan_models_names()}),
     "upscaler_for_img2img": OptionInfo(None, "Upscaler for img2img", gr.Dropdown, lambda: {"choices": [x.name for x in sd_upscalers]}),
-    "use_scale_latent_for_hires_fix": OptionInfo(False, "Upscale latent space image when doing hires. fix"),
 }))
 
 options_templates.update(options_section(('face-restoration', "Face restoration"), {
@@ -545,6 +544,12 @@ opts = Options()
 if os.path.exists(config_filename):
     opts.load(config_filename)
 
+latent_upscale_default_mode = "Latent"
+latent_upscale_modes = {
+    "Latent": "bilinear",
+    "Latent (nearest)": "nearest",
+}
+
 sd_upscalers = []
 
 sd_model = None
diff --git a/modules/txt2img.py b/modules/txt2img.py
index 7f61e19a..e189a899 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, firstphase_width: int, firstphase_height: int, *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, *args):
     p = StableDiffusionProcessingTxt2Img(
         sd_model=shared.sd_model,
         outpath_samples=opts.outdir_samples or opts.outdir_txt2img_samples,
@@ -33,8 +33,8 @@ def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2:
         tiling=tiling,
         enable_hr=enable_hr,
         denoising_strength=denoising_strength if enable_hr else None,
-        firstphase_width=firstphase_width if enable_hr else None,
-        firstphase_height=firstphase_height if enable_hr else None,
+        hr_scale=hr_scale,
+        hr_upscaler=hr_upscaler,
     )
 
     p.scripts = modules.scripts.scripts_txt2img
diff --git a/modules/ui.py b/modules/ui.py
index 7070ea15..27cd9ddd 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -684,11 +684,11 @@ def create_ui():
                 with gr.Row():
                     restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1, elem_id="txt2img_restore_faces")
                     tiling = gr.Checkbox(label='Tiling', value=False, elem_id="txt2img_tiling")
-                    enable_hr = gr.Checkbox(label='Highres. fix', value=False, elem_id="txt2img_enable_hr")
+                    enable_hr = gr.Checkbox(label='Hires. fix', value=False, elem_id="txt2img_enable_hr")
 
                 with gr.Row(visible=False) as hr_options:
-                    firstphase_width = gr.Slider(minimum=0, maximum=1024, step=8, label="Firstpass width", value=0, elem_id="txt2img_firstphase_width")
-                    firstphase_height = gr.Slider(minimum=0, maximum=1024, step=8, label="Firstpass height", value=0, elem_id="txt2img_firstphase_height")
+                    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 gr.Row(equal_height=True):
@@ -729,8 +729,8 @@ def create_ui():
                     width,
                     enable_hr,
                     denoising_strength,
-                    firstphase_width,
-                    firstphase_height,
+                    hr_scale,
+                    hr_upscaler,
                 ] + custom_inputs,
 
                 outputs=[
@@ -762,7 +762,6 @@ def create_ui():
                 outputs=[hr_options],
             )
 
-
             txt2img_paste_fields = [
                 (txt2img_prompt, "Prompt"),
                 (txt2img_negative_prompt, "Negative prompt"),
@@ -781,8 +780,8 @@ def create_ui():
                 (denoising_strength, "Denoising strength"),
                 (enable_hr, lambda d: "Denoising strength" in d),
                 (hr_options, lambda d: gr.Row.update(visible="Denoising strength" in d)),
-                (firstphase_width, "First pass size-1"),
-                (firstphase_height, "First pass size-2"),
+                (hr_scale, "Hires upscale"),
+                (hr_upscaler, "Hires upscaler"),
                 *modules.scripts.scripts_txt2img.infotext_fields
             ]
             parameters_copypaste.add_paste_fields("txt2img", None, txt2img_paste_fields)
diff --git a/scripts/xy_grid.py b/scripts/xy_grid.py
index 3e0b2805..f92f9776 100644
--- a/scripts/xy_grid.py
+++ b/scripts/xy_grid.py
@@ -202,7 +202,7 @@ axis_options = [
     AxisOption("Eta", float, apply_field("eta"), format_value_add_label, None),
     AxisOption("Clip skip", int, apply_clip_skip, format_value_add_label, None),
     AxisOption("Denoising", float, apply_field("denoising_strength"), format_value_add_label, None),
-    AxisOption("Upscale latent space for hires.", str, apply_upscale_latent_space, format_value_add_label, None),
+    AxisOption("Hires upscaler", str, apply_field("hr_upscaler"), format_value_add_label, None),
     AxisOption("Cond. Image Mask Weight", float, apply_field("inpainting_mask_weight"), format_value_add_label, None),
     AxisOption("VAE", str, apply_vae, format_value_add_label, None),
     AxisOption("Styles", str, apply_styles, format_value_add_label, None),
@@ -267,7 +267,6 @@ class SharedSettingsStackHelper(object):
         self.CLIP_stop_at_last_layers = opts.CLIP_stop_at_last_layers
         self.hypernetwork = opts.sd_hypernetwork
         self.model = shared.sd_model
-        self.use_scale_latent_for_hires_fix = opts.use_scale_latent_for_hires_fix
         self.vae = opts.sd_vae
   
     def __exit__(self, exc_type, exc_value, tb):
@@ -278,7 +277,6 @@ class SharedSettingsStackHelper(object):
         hypernetwork.apply_strength()
 
         opts.data["CLIP_stop_at_last_layers"] = self.CLIP_stop_at_last_layers
-        opts.data["use_scale_latent_for_hires_fix"] = self.use_scale_latent_for_hires_fix
 
 
 re_range = re.compile(r"\s*([+-]?\s*\d+)\s*-\s*([+-]?\s*\d+)(?:\s*\(([+-]\d+)\s*\))?\s*")
-- 
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/txt2img.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