added the option to specify target resolution with possibility of truncating for hires fix; also sampling steps

5 files changed, 81 insertions, 19 deletions

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)