Option between stretch and crop for Highres. fix

3 files changed, 42 insertions, 24 deletions

diff --git a/modules/processing.py b/modules/processing.py
index abbfdf98..0246f5dd 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -506,13 +506,14 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
     firstphase_width_truncated = 0

     firstphase_height_truncated = 0

 

-    def __init__(self, enable_hr=False, scale_latent=True, denoising_strength=0.75, first_pass_width=512, first_pass_height=512, **kwargs):

+    def __init__(self, enable_hr=False, scale_latent=True, denoising_strength=0.75, firstphase_width=512, firstphase_height=512, crop_scale=False, **kwargs):

         super().__init__(**kwargs)

         self.enable_hr = enable_hr

         self.scale_latent = scale_latent

         self.denoising_strength = denoising_strength

-        self.first_pass_width = first_pass_width

-        self.first_pass_height = first_pass_height

+        self.firstphase_width = firstphase_width

+        self.firstphase_height = firstphase_height

+        self.crop_scale = crop_scale

 

     def init(self, all_prompts, all_seeds, all_subseeds):

         if self.enable_hr:

@@ -521,14 +522,14 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             else:

                 state.job_count = state.job_count * 2

 

-            desired_pixel_count = self.first_pass_width * self.first_pass_height

-            actual_pixel_count = self.width * self.height

-            scale = math.sqrt(desired_pixel_count / actual_pixel_count)

+            #desired_pixel_count = self.firstphase_width * self.firstphase_height

+            #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

-            self.firstphase_width_truncated = int(scale * self.width)

-            self.firstphase_height_truncated = int(scale * self.height)

+            #self.firstphase_width = math.ceil(scale * self.width / 64) * 64

+            #self.firstphase_height = math.ceil(scale * self.height / 64) * 64

+            #self.firstphase_width_truncated = int(scale * self.width)

+            #self.firstphase_height_truncated = int(scale * self.height)

 

     def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength):

         self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, self.sd_model)

@@ -541,8 +542,17 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         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)

 

-        truncate_x = (self.firstphase_width - self.firstphase_width_truncated) // opt_f

-        truncate_y = (self.firstphase_height - self.firstphase_height_truncated) // opt_f

+        truncate_x = 0

+        truncate_y = 0

+

+        if self.crop_scale:

+            if self.width/self.firstphase_width > self.height/self.firstphase_height:

+                #Crop to landscape

+                truncate_y = (self.width -  self.firstphase_width)//2 // opt_f

+

+            elif self.width/self.firstphase_width < self.height/self.firstphase_height:

+                #Crop to portrait

+                truncate_x = (self.height - self.firstphase_height)//2 // opt_f

 

         samples = samples[:, :, truncate_y//2:samples.shape[2]-truncate_y//2, truncate_x//2:samples.shape[3]-truncate_x//2]

 

diff --git a/modules/txt2img.py b/modules/txt2img.py
index 85cbece4..447ec3d3 100644
--- a/modules/txt2img.py
+++ b/modules/txt2img.py
@@ -6,7 +6,7 @@ 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, scale_latent: bool, denoising_strength: float, first_pass_width: int, first_pass_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, scale_latent: bool, denoising_strength: float, firstphase_width: int, firstphase_height: int, crop_scale: bool, *args):

     p = StableDiffusionProcessingTxt2Img(

         sd_model=shared.sd_model,

         outpath_samples=opts.outdir_samples or opts.outdir_txt2img_samples,

@@ -32,8 +32,9 @@ def txt2img(prompt: str, negative_prompt: str, prompt_style: str, prompt_style2:
         enable_hr=enable_hr,

         scale_latent=scale_latent if enable_hr else None,

         denoising_strength=denoising_strength if enable_hr else None,

-		first_pass_width=first_pass_width if enable_hr else None,

-		first_pass_height=first_pass_height if enable_hr else None,

+		firstphase_width=firstphase_width if enable_hr else None,

+		firstphase_height=firstphase_height if enable_hr else None,

+        crop_scale=crop_scale if enable_hr else None,

 

     )

 

diff --git a/modules/ui.py b/modules/ui.py
index 544419b2..f2d81f68 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -540,12 +540,18 @@ def create_ui(wrap_gradio_gpu_call):
                     enable_hr = gr.Checkbox(label='Highres. fix', value=False)

 

                 with gr.Row(visible=False) as hr_options:

-                    first_pass_width = gr.Slider(minimum=64, maximum=1024, step=64, label="First pass width", value=512)

-                    first_pass_height = gr.Slider(minimum=64, maximum=1024, step=64, label="First pass height", value=512)

-                    scale_latent = gr.Checkbox(label='Scale latent', value=False)

-                    denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7)

+                    with gr.Column(scale=1.0):

+                        firstphase_width = gr.Slider(minimum=64, maximum=1024, step=64, label="First pass width", value=512)

+                        firstphase_height = gr.Slider(minimum=64, maximum=1024, step=64, label="First pass height", value=512)

+                        

+                    with gr.Column(scale=1.0):

+                        with gr.Row():

+                            crop_scale = gr.Checkbox(label='Crop when scaling', value=False)

+                            scale_latent = gr.Checkbox(label='Scale latent', value=False)

+                        with gr.Row():

+                            denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.7)

 

-                with gr.Row():

+                with gr.Row(equal_height=True):

                     batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1)

                     batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1)

 

@@ -606,8 +612,9 @@ def create_ui(wrap_gradio_gpu_call):
                     enable_hr,

                     scale_latent,

                     denoising_strength,

-                    first_pass_width,

-                    first_pass_height,

+                    firstphase_width,

+                    firstphase_height,

+                    crop_scale,

                 ] + custom_inputs,

                 outputs=[

                     txt2img_gallery,

@@ -672,8 +679,8 @@ def create_ui(wrap_gradio_gpu_call):
                 (denoising_strength, "Denoising strength"),

                 (enable_hr, lambda d: "Denoising strength" in d),

                 (hr_options, lambda d: gr.Row.update(visible="Denoising strength" in d)),

-                (first_pass_width, "First pass width"),

-                (first_pass_height, "First pass height"),

+                (firstphase_width, "First pass width"),

+                (firstphase_height, "First pass height"),

             ]

             modules.generation_parameters_copypaste.connect_paste(paste, txt2img_paste_fields, txt2img_prompt)

             token_button.click(fn=update_token_counter, inputs=[txt2img_prompt, steps], outputs=[token_counter])