From 3bca90b249d749ed5429f76e380d2ffa52fc0d41 Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Sun, 30 Jul 2023 13:48:27 +0300
Subject: hires fix checkpoint selection

---
 modules/processing.py | 47 ++++++++++++++++++++++++++++++-----------------
 1 file changed, 30 insertions(+), 17 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index b0992ee1..7026487a 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -935,7 +935,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
     cached_hr_uc = [None, None]
     cached_hr_c = [None, 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, hr_second_pass_steps: int = 0, hr_resize_x: int = 0, hr_resize_y: int = 0, hr_sampler_name: str = None, hr_prompt: str = '', hr_negative_prompt: str = '', **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, hr_checkpoint_name: str = None, hr_sampler_name: str = None, hr_prompt: str = '', hr_negative_prompt: str = '', **kwargs):
         super().__init__(**kwargs)
         self.enable_hr = enable_hr
         self.denoising_strength = denoising_strength
@@ -946,11 +946,14 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         self.hr_resize_y = hr_resize_y
         self.hr_upscale_to_x = hr_resize_x
         self.hr_upscale_to_y = hr_resize_y
+        self.hr_checkpoint_name = hr_checkpoint_name
+        self.hr_checkpoint_info = None
         self.hr_sampler_name = hr_sampler_name
         self.hr_prompt = hr_prompt
         self.hr_negative_prompt = hr_negative_prompt
         self.all_hr_prompts = None
         self.all_hr_negative_prompts = None
+        self.latent_scale_mode = None
 
         if firstphase_width != 0 or firstphase_height != 0:
             self.hr_upscale_to_x = self.width
@@ -973,6 +976,14 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
     def init(self, all_prompts, all_seeds, all_subseeds):
         if self.enable_hr:
+            if self.hr_checkpoint_name:
+                self.hr_checkpoint_info = sd_models.get_closet_checkpoint_match(self.hr_checkpoint_name)
+
+                if self.hr_checkpoint_info is None:
+                    raise Exception(f'Could not find checkpoint with name {self.hr_checkpoint_name}')
+
+                self.extra_generation_params["Hires checkpoint"] = self.hr_checkpoint_info.short_title
+
             if self.hr_sampler_name is not None and self.hr_sampler_name != self.sampler_name:
                 self.extra_generation_params["Hires sampler"] = self.hr_sampler_name
 
@@ -982,6 +993,11 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             if tuple(self.hr_negative_prompt) != tuple(self.negative_prompt):
                 self.extra_generation_params["Hires negative prompt"] = self.hr_negative_prompt
 
+            self.latent_scale_mode = shared.latent_upscale_modes.get(self.hr_upscaler, None) if self.hr_upscaler is not None else shared.latent_upscale_modes.get(shared.latent_upscale_default_mode, "nearest")
+            if self.enable_hr and self.latent_scale_mode is None:
+                if not any(x.name == self.hr_upscaler for x in shared.sd_upscalers):
+                    raise Exception(f"could not find upscaler named {self.hr_upscaler}")
+
             if opts.use_old_hires_fix_width_height and self.applied_old_hires_behavior_to != (self.width, self.height):
                 self.hr_resize_x = self.width
                 self.hr_resize_y = self.height
@@ -1020,14 +1036,6 @@ 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
@@ -1045,17 +1053,22 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
     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_modes.get(shared.latent_upscale_default_mode, "nearest")
-        if self.enable_hr and latent_scale_mode is None:
-            if not any(x.name == self.hr_upscaler for x in shared.sd_upscalers):
-                raise Exception(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:
             return samples
 
+        current = shared.sd_model.sd_checkpoint_info
+        try:
+            if self.hr_checkpoint_info is not None:
+                sd_models.reload_model_weights(info=self.hr_checkpoint_info)
+
+            return self.sample_hr_pass(samples, seeds, subseeds, subseed_strength, prompts)
+        finally:
+            sd_models.reload_model_weights(info=current)
+
+    def sample_hr_pass(self, samples, seeds, subseeds, subseed_strength, prompts):
         self.is_hr_pass = True
 
         target_width = self.hr_upscale_to_x
@@ -1073,11 +1086,11 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             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, p=self, suffix="-before-highres-fix")
 
-        if latent_scale_mode is not None:
+        if self.latent_scale_mode is not None:
             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["mode"], antialias=latent_scale_mode["antialias"])
+            samples = torch.nn.functional.interpolate(samples, size=(target_height // opt_f, target_width // opt_f), mode=self.latent_scale_mode["mode"], antialias=self.latent_scale_mode["antialias"])
 
             # Avoid making the inpainting conditioning unless necessary as
             # this does need some extra compute to decode / encode the image again.
@@ -1193,7 +1206,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         self.hr_uc = None
         self.hr_c = None
 
-        if self.enable_hr:
+        if self.enable_hr and self.hr_checkpoint_info is None:
             if shared.opts.hires_fix_use_firstpass_conds:
                 self.calculate_hr_conds()
 
-- 
cgit v1.2.3


From 40cd59207b96f9e522fdc104b43279880b671ce4 Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Sun, 30 Jul 2023 14:10:26 +0300
Subject: make it work with SDXL

---
 modules/processing.py | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index 7026487a..b8af1301 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -1197,8 +1197,11 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         if self.hr_c is not None:
             return
 
-        self.hr_uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, self.hr_negative_prompts, self.steps * self.step_multiplier, [self.cached_hr_uc, self.cached_uc], self.hr_extra_network_data)
-        self.hr_c = self.get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, self.hr_prompts, self.steps * self.step_multiplier, [self.cached_hr_c, self.cached_c], self.hr_extra_network_data)
+        hr_prompts = prompt_parser.SdConditioning(self.hr_prompts, width=self.hr_upscale_to_x, height=self.hr_upscale_to_y)
+        hr_negative_prompts = prompt_parser.SdConditioning(self.hr_negative_prompts, width=self.hr_upscale_to_x, height=self.hr_upscale_to_y, is_negative_prompt=True)
+
+        self.hr_uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, hr_negative_prompts, self.steps * self.step_multiplier, [self.cached_hr_uc, self.cached_uc], self.hr_extra_network_data)
+        self.hr_c = self.get_conds_with_caching(prompt_parser.get_multicond_learned_conditioning, hr_prompts, self.steps * self.step_multiplier, [self.cached_hr_c, self.cached_c], self.hr_extra_network_data)
 
     def setup_conds(self):
         super().setup_conds()
-- 
cgit v1.2.3


From 77761e7bad8a7cbffc9028dc0b2f63169aaf25f9 Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Sun, 30 Jul 2023 14:10:33 +0300
Subject: linter

---
 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 b8af1301..21dbef16 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -1055,6 +1055,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
         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))
+        del x
 
         if not self.enable_hr:
             return samples
@@ -1137,7 +1138,6 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         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()
 
         if not self.disable_extra_networks:
-- 
cgit v1.2.3


From eec540b22798ddcf8a03d947519c36635d77d722 Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Sun, 30 Jul 2023 15:04:12 +0300
Subject: repair non-latent upscaling broken for SDXL

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

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index 21dbef16..6fb14516 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -1119,6 +1119,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             decoded_samples = torch.from_numpy(np.array(batch_images))
             decoded_samples = decoded_samples.to(shared.device)
             decoded_samples = 2. * decoded_samples - 1.
+            decoded_samples = decoded_samples.to(shared.device, dtype=devices.dtype_vae)
 
             samples = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(decoded_samples))
 
-- 
cgit v1.2.3


From a64fbe89288802f8b5ec8ca7bcab5aaf2c7bfea5 Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Sun, 30 Jul 2023 15:12:09 +0300
Subject: make it possible to use checkpoints of different types (SD1, SDXL) in
 first and second pass of hires fix

---
 modules/processing.py | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index 6fb14516..c4da208f 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -1060,16 +1060,21 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         if not self.enable_hr:
             return samples
 
+        if self.latent_scale_mode is None:
+            decoded_samples = decode_first_stage(self.sd_model, samples)
+        else:
+            decoded_samples = None
+
         current = shared.sd_model.sd_checkpoint_info
         try:
             if self.hr_checkpoint_info is not None:
                 sd_models.reload_model_weights(info=self.hr_checkpoint_info)
 
-            return self.sample_hr_pass(samples, seeds, subseeds, subseed_strength, prompts)
+            return self.sample_hr_pass(samples, decoded_samples, seeds, subseeds, subseed_strength, prompts)
         finally:
             sd_models.reload_model_weights(info=current)
 
-    def sample_hr_pass(self, samples, seeds, subseeds, subseed_strength, prompts):
+    def sample_hr_pass(self, samples, decoded_samples, seeds, subseeds, subseed_strength, prompts):
         self.is_hr_pass = True
 
         target_width = self.hr_upscale_to_x
@@ -1100,7 +1105,6 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             else:
                 image_conditioning = self.txt2img_image_conditioning(samples)
         else:
-            decoded_samples = decode_first_stage(self.sd_model, samples)
             lowres_samples = torch.clamp((decoded_samples + 1.0) / 2.0, min=0.0, max=1.0)
 
             batch_images = []
-- 
cgit v1.2.3


From cc53db6652b11e6f7bca42c3aa93bd6761ed3d3f Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Sun, 30 Jul 2023 15:30:33 +0300
Subject: this time for sure

---
 modules/processing.py | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index c4da208f..3190b964 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -538,8 +538,12 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see
     return x
 
 
+class DecodedSamples(list):
+    already_decoded = True
+
+
 def decode_latent_batch(model, batch, target_device=None, check_for_nans=False):
-    samples = []
+    samples = DecodedSamples()
 
     for i in range(batch.shape[0]):
         sample = decode_first_stage(model, batch[i:i + 1])[0]
@@ -793,7 +797,11 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
             with devices.without_autocast() if devices.unet_needs_upcast else devices.autocast():
                 samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
 
-            x_samples_ddim = decode_latent_batch(p.sd_model, samples_ddim, target_device=devices.cpu, check_for_nans=True)
+            if getattr(samples_ddim, 'already_decoded', False):
+                x_samples_ddim = samples_ddim
+            else:
+                x_samples_ddim = decode_latent_batch(p.sd_model, samples_ddim, target_device=devices.cpu, check_for_nans=True)
+
             x_samples_ddim = torch.stack(x_samples_ddim).float()
             x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
 
@@ -1161,9 +1169,11 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
         sd_models.apply_token_merging(self.sd_model, self.get_token_merging_ratio())
 
+        decoded_samples = decode_latent_batch(self.sd_model, samples, target_device=devices.cpu, check_for_nans=True)
+
         self.is_hr_pass = False
 
-        return samples
+        return decoded_samples
 
     def close(self):
         super().close()
-- 
cgit v1.2.3


From 02038036ff571e0f04a94c3e279609666e239dec Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Sun, 30 Jul 2023 16:16:31 +0300
Subject: make it so that VAE NaNs autodetection also works during first pass
 of hires fix

---
 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 3190b964..0677de81 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -1069,7 +1069,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             return samples
 
         if self.latent_scale_mode is None:
-            decoded_samples = decode_first_stage(self.sd_model, samples)
+            decoded_samples = torch.stack(decode_latent_batch(self.sd_model, samples, target_device=devices.cpu, check_for_nans=True))
         else:
             decoded_samples = None
 
-- 
cgit v1.2.3


From 0af4127fd14360ebb12c6569d98aebf8047abbfc Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Sun, 30 Jul 2023 19:36:24 +0300
Subject: delete the field that is preventing the model from being unloaded and
 is causing increased RAM usage

---
 modules/processing.py | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index 0677de81..b09433b0 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -1076,11 +1076,15 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         current = shared.sd_model.sd_checkpoint_info
         try:
             if self.hr_checkpoint_info is not None:
+                del self.sampler
                 sd_models.reload_model_weights(info=self.hr_checkpoint_info)
+                devices.torch_gc()
 
             return self.sample_hr_pass(samples, decoded_samples, seeds, subseeds, subseed_strength, prompts)
         finally:
+            del self.sampler
             sd_models.reload_model_weights(info=current)
+            devices.torch_gc()
 
     def sample_hr_pass(self, samples, decoded_samples, seeds, subseeds, subseed_strength, prompts):
         self.is_hr_pass = True
-- 
cgit v1.2.3


From dca121e9035ba36b3f7484c8a31a7776d85c0960 Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Mon, 31 Jul 2023 09:13:07 +0300
Subject: set the field to None instead

---
 modules/processing.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index b09433b0..35e7b87e 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -1076,13 +1076,13 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         current = shared.sd_model.sd_checkpoint_info
         try:
             if self.hr_checkpoint_info is not None:
-                del self.sampler
+                self.sampler = None
                 sd_models.reload_model_weights(info=self.hr_checkpoint_info)
                 devices.torch_gc()
 
             return self.sample_hr_pass(samples, decoded_samples, seeds, subseeds, subseed_strength, prompts)
         finally:
-            del self.sampler
+            self.sampler = None
             sd_models.reload_model_weights(info=current)
             devices.torch_gc()
 
-- 
cgit v1.2.3


From 29d7e31d89e9d686784eacbdbfc5b15959eb4449 Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Mon, 31 Jul 2023 10:43:26 +0300
Subject: repair AttributeError: 'NoneType' object has no attribute
 'conditioning_key'

---
 modules/processing.py | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index 35e7b87e..1f0c0b3b 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -1104,6 +1104,13 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             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, p=self, suffix="-before-highres-fix")
 
+        img2img_sampler_name = self.hr_sampler_name or self.sampler_name
+
+        if self.sampler_name in ['PLMS', 'UniPC']:  # PLMS/UniPC do not support img2img so we just silently switch to DDIM
+            img2img_sampler_name = 'DDIM'
+
+        self.sampler = sd_samplers.create_sampler(img2img_sampler_name, self.sd_model)
+
         if self.latent_scale_mode is not None:
             for i in range(samples.shape[0]):
                 save_intermediate(samples, i)
@@ -1143,13 +1150,6 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
         shared.state.nextjob()
 
-        img2img_sampler_name = self.hr_sampler_name or self.sampler_name
-
-        if self.sampler_name in ['PLMS', 'UniPC']:  # PLMS/UniPC do not support img2img so we just silently switch to DDIM
-            img2img_sampler_name = 'DDIM'
-
-        self.sampler = sd_samplers.create_sampler(img2img_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)
-- 
cgit v1.2.3


From c09bc2c60856ca1ab2243386176badf909affdbe Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Mon, 31 Jul 2023 13:20:26 +0300
Subject: fix "clamp_scalar_cpu" not implemented for 'Half'

---
 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 1f0c0b3b..f8f8bddc 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -1069,7 +1069,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             return samples
 
         if self.latent_scale_mode is None:
-            decoded_samples = torch.stack(decode_latent_batch(self.sd_model, samples, target_device=devices.cpu, check_for_nans=True))
+            decoded_samples = torch.stack(decode_latent_batch(self.sd_model, samples, target_device=devices.cpu, check_for_nans=True)).to(dtype=torch.float32)
         else:
             decoded_samples = None
 
-- 
cgit v1.2.3


From ccb92339348f6973de39cde062982a51a4cd0818 Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Wed, 2 Aug 2023 18:53:09 +0300
Subject: add yet another torch_gc to reclaim some of VRAM after the initial
 stage of img2img

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

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index b0992ee1..0b66cd2a 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -1348,6 +1348,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
         image = image.to(shared.device, dtype=devices.dtype_vae)
 
         self.init_latent = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image))
+        devices.torch_gc()
 
         if self.resize_mode == 3:
             self.init_latent = torch.nn.functional.interpolate(self.init_latent, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")
-- 
cgit v1.2.3


From 84b6fcd02ca6d6ab48c4b6be4bb8724b1c2e7014 Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Thu, 3 Aug 2023 00:00:23 +0300
Subject: add NV option for Random number generator source setting, which
 allows to generate same pictures on CPU/AMD/Mac as on NVidia  videocards.

---
 modules/processing.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index 0b66cd2a..8f34c8b4 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -492,7 +492,7 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see
         noise_shape = shape if seed_resize_from_h <= 0 or seed_resize_from_w <= 0 else (shape[0], seed_resize_from_h//8, seed_resize_from_w//8)
 
         subnoise = None
-        if subseeds is not None:
+        if subseeds is not None and subseed_strength != 0:
             subseed = 0 if i >= len(subseeds) else subseeds[i]
 
             subnoise = devices.randn(subseed, noise_shape)
@@ -524,7 +524,7 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see
             cnt = p.sampler.number_of_needed_noises(p)
 
             if eta_noise_seed_delta > 0:
-                torch.manual_seed(seed + eta_noise_seed_delta)
+                devices.manual_seed(seed + eta_noise_seed_delta)
 
             for j in range(cnt):
                 sampler_noises[j].append(devices.randn_without_seed(tuple(noise_shape)))
@@ -636,7 +636,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter
         "Token merging ratio": None if token_merging_ratio == 0 else token_merging_ratio,
         "Token merging ratio hr": None if not enable_hr or token_merging_ratio_hr == 0 else token_merging_ratio_hr,
         "Init image hash": getattr(p, 'init_img_hash', None),
-        "RNG": opts.randn_source if opts.randn_source != "GPU" else None,
+        "RNG": opts.randn_source if opts.randn_source != "GPU" and opts.randn_source != "NV" else None,
         "NGMS": None if p.s_min_uncond == 0 else p.s_min_uncond,
         **p.extra_generation_params,
         "Version": program_version() if opts.add_version_to_infotext else None,
-- 
cgit v1.2.3


From 75336dfc84cae280036bc52a6805eb10d9ae30ba Mon Sep 17 00:00:00 2001
From: Kohaku-Blueleaf <59680068+KohakuBlueleaf@users.noreply.github.com>
Date: Fri, 4 Aug 2023 13:38:52 +0800
Subject: add TAESD for i2i and t2i

---
 modules/processing.py | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index 8f34c8b4..099d86b7 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -573,9 +573,10 @@ def decode_latent_batch(model, batch, target_device=None, check_for_nans=False):
 
 
 def decode_first_stage(model, x):
-    x = model.decode_first_stage(x.to(devices.dtype_vae))
-
-    return x
+    from modules.sd_samplers_common import samples_to_images_tensor, approximation_indexes
+    x = x.to(devices.dtype_vae)
+    approx_index = approximation_indexes.get(opts.sd_vae_decode_method, 0)
+    return samples_to_images_tensor(x, approx_index, model)
 
 
 def get_fixed_seed(seed):
@@ -1344,10 +1345,8 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
             raise RuntimeError(f"bad number of images passed: {len(imgs)}; expecting {self.batch_size} or less")
 
         image = torch.from_numpy(batch_images)
-        image = 2. * image - 1.
-        image = image.to(shared.device, dtype=devices.dtype_vae)
-
-        self.init_latent = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image))
+        from modules.sd_samplers_common import images_tensor_to_samples, approximation_indexes
+        self.init_latent = images_tensor_to_samples(image, approximation_indexes.get(opts.sd_vae_encode_method), self.sd_model)
         devices.torch_gc()
 
         if self.resize_mode == 3:
-- 
cgit v1.2.3


From f0c1063a707a4a43823b0ed00e2a8eeb22a9ed0a Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Fri, 4 Aug 2023 09:09:09 +0300
Subject: resolve some of circular import issues for kohaku

---
 modules/processing.py | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index 8f34c8b4..8086a2b0 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -30,6 +30,7 @@ from ldm.models.diffusion.ddpm import LatentDepth2ImageDiffusion
 from einops import repeat, rearrange
 from blendmodes.blend import blendLayers, BlendType
 
+decode_first_stage = sd_samplers_common.decode_first_stage
 
 # some of those options should not be changed at all because they would break the model, so I removed them from options.
 opt_C = 4
@@ -572,12 +573,6 @@ def decode_latent_batch(model, batch, target_device=None, check_for_nans=False):
     return samples
 
 
-def decode_first_stage(model, x):
-    x = model.decode_first_stage(x.to(devices.dtype_vae))
-
-    return x
-
-
 def get_fixed_seed(seed):
     if seed is None or seed == '' or seed == -1:
         return int(random.randrange(4294967294))
-- 
cgit v1.2.3


From 094c416a801b16c7d8e1944e2e9fae2c9e98bf12 Mon Sep 17 00:00:00 2001
From: Kohaku-Blueleaf <59680068+KohakuBlueleaf@users.noreply.github.com>
Date: Fri, 4 Aug 2023 17:53:16 +0800
Subject: change all encode

---
 modules/processing.py | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index aae39866..544667a4 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -16,6 +16,7 @@ from typing import Any, Dict, List
 import modules.sd_hijack
 from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, extra_networks, sd_vae_approx, scripts, sd_samplers_common, sd_unet, errors
 from modules.sd_hijack import model_hijack
+from modules.sd_samplers_common import images_tensor_to_samples, decode_first_stage, approximation_indexes
 from modules.shared import opts, cmd_opts, state
 import modules.shared as shared
 import modules.paths as paths
@@ -30,7 +31,6 @@ from ldm.models.diffusion.ddpm import LatentDepth2ImageDiffusion
 from einops import repeat, rearrange
 from blendmodes.blend import blendLayers, BlendType
 
-decode_first_stage = sd_samplers_common.decode_first_stage
 
 # some of those options should not be changed at all because they would break the model, so I removed them from options.
 opt_C = 4
@@ -84,7 +84,7 @@ def txt2img_image_conditioning(sd_model, x, width, height):
 
         # 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))
+        image_conditioning = images_tensor_to_samples(image_conditioning, approximation_indexes.get(opts.sd_vae_encode_method))
 
         # 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)
@@ -203,7 +203,7 @@ class StableDiffusionProcessing:
         midas_in = torch.from_numpy(transformed["midas_in"][None, ...]).to(device=shared.device)
         midas_in = repeat(midas_in, "1 ... -> n ...", n=self.batch_size)
 
-        conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(source_image))
+        conditioning_image = images_tensor_to_samples(source_image*0.5+0.5, approximation_indexes.get(opts.sd_vae_encode_method))
         conditioning = torch.nn.functional.interpolate(
             self.sd_model.depth_model(midas_in),
             size=conditioning_image.shape[2:],
@@ -216,7 +216,7 @@ class StableDiffusionProcessing:
         return conditioning
 
     def edit_image_conditioning(self, source_image):
-        conditioning_image = self.sd_model.encode_first_stage(source_image).mode()
+        conditioning_image = images_tensor_to_samples(source_image*0.5+0.5, approximation_indexes.get(opts.sd_vae_encode_method))
 
         return conditioning_image
 
@@ -255,7 +255,7 @@ class StableDiffusionProcessing:
         )
 
         # Encode the new masked image using first stage of network.
-        conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(conditioning_image))
+        conditioning_image = images_tensor_to_samples(conditioning_image*0.5+0.5, approximation_indexes.get(opts.sd_vae_encode_method))
 
         # Create the concatenated conditioning tensor to be fed to `c_concat`
         conditioning_mask = torch.nn.functional.interpolate(conditioning_mask, size=latent_image.shape[-2:])
@@ -1099,9 +1099,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
             decoded_samples = torch.from_numpy(np.array(batch_images))
             decoded_samples = decoded_samples.to(shared.device)
-            decoded_samples = 2. * decoded_samples - 1.
 
-            samples = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(decoded_samples))
+            samples = images_tensor_to_samples(decoded_samples, approximation_indexes.get(opts.sd_vae_encode_method))
 
             image_conditioning = self.img2img_image_conditioning(decoded_samples, samples)
 
@@ -1339,7 +1338,6 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
             raise RuntimeError(f"bad number of images passed: {len(imgs)}; expecting {self.batch_size} or less")
 
         image = torch.from_numpy(batch_images)
-        from modules.sd_samplers_common import images_tensor_to_samples, approximation_indexes
         self.init_latent = images_tensor_to_samples(image, approximation_indexes.get(opts.sd_vae_encode_method), self.sd_model)
         devices.torch_gc()
 
-- 
cgit v1.2.3


From 6346d8eeaa17ba0f7e41618908519f6e9bfe07e0 Mon Sep 17 00:00:00 2001
From: Kohaku-Blueleaf <59680068+KohakuBlueleaf@users.noreply.github.com>
Date: Fri, 4 Aug 2023 17:53:30 +0800
Subject: Revert "change all encode"

This reverts commit 094c416a801b16c7d8e1944e2e9fae2c9e98bf12.
---
 modules/processing.py | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index 544667a4..aae39866 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -16,7 +16,6 @@ from typing import Any, Dict, List
 import modules.sd_hijack
 from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, extra_networks, sd_vae_approx, scripts, sd_samplers_common, sd_unet, errors
 from modules.sd_hijack import model_hijack
-from modules.sd_samplers_common import images_tensor_to_samples, decode_first_stage, approximation_indexes
 from modules.shared import opts, cmd_opts, state
 import modules.shared as shared
 import modules.paths as paths
@@ -31,6 +30,7 @@ from ldm.models.diffusion.ddpm import LatentDepth2ImageDiffusion
 from einops import repeat, rearrange
 from blendmodes.blend import blendLayers, BlendType
 
+decode_first_stage = sd_samplers_common.decode_first_stage
 
 # some of those options should not be changed at all because they would break the model, so I removed them from options.
 opt_C = 4
@@ -84,7 +84,7 @@ def txt2img_image_conditioning(sd_model, x, width, height):
 
         # 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 = images_tensor_to_samples(image_conditioning, approximation_indexes.get(opts.sd_vae_encode_method))
+        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)
@@ -203,7 +203,7 @@ class StableDiffusionProcessing:
         midas_in = torch.from_numpy(transformed["midas_in"][None, ...]).to(device=shared.device)
         midas_in = repeat(midas_in, "1 ... -> n ...", n=self.batch_size)
 
-        conditioning_image = images_tensor_to_samples(source_image*0.5+0.5, approximation_indexes.get(opts.sd_vae_encode_method))
+        conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(source_image))
         conditioning = torch.nn.functional.interpolate(
             self.sd_model.depth_model(midas_in),
             size=conditioning_image.shape[2:],
@@ -216,7 +216,7 @@ class StableDiffusionProcessing:
         return conditioning
 
     def edit_image_conditioning(self, source_image):
-        conditioning_image = images_tensor_to_samples(source_image*0.5+0.5, approximation_indexes.get(opts.sd_vae_encode_method))
+        conditioning_image = self.sd_model.encode_first_stage(source_image).mode()
 
         return conditioning_image
 
@@ -255,7 +255,7 @@ class StableDiffusionProcessing:
         )
 
         # Encode the new masked image using first stage of network.
-        conditioning_image = images_tensor_to_samples(conditioning_image*0.5+0.5, approximation_indexes.get(opts.sd_vae_encode_method))
+        conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(conditioning_image))
 
         # Create the concatenated conditioning tensor to be fed to `c_concat`
         conditioning_mask = torch.nn.functional.interpolate(conditioning_mask, size=latent_image.shape[-2:])
@@ -1099,8 +1099,9 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
             decoded_samples = torch.from_numpy(np.array(batch_images))
             decoded_samples = decoded_samples.to(shared.device)
+            decoded_samples = 2. * decoded_samples - 1.
 
-            samples = images_tensor_to_samples(decoded_samples, approximation_indexes.get(opts.sd_vae_encode_method))
+            samples = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(decoded_samples))
 
             image_conditioning = self.img2img_image_conditioning(decoded_samples, samples)
 
@@ -1338,6 +1339,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
             raise RuntimeError(f"bad number of images passed: {len(imgs)}; expecting {self.batch_size} or less")
 
         image = torch.from_numpy(batch_images)
+        from modules.sd_samplers_common import images_tensor_to_samples, approximation_indexes
         self.init_latent = images_tensor_to_samples(image, approximation_indexes.get(opts.sd_vae_encode_method), self.sd_model)
         devices.torch_gc()
 
-- 
cgit v1.2.3


From 21000f13a169263a7da2c66b300130d7a6339c7d Mon Sep 17 00:00:00 2001
From: Kohaku-Blueleaf <59680068+KohakuBlueleaf@users.noreply.github.com>
Date: Fri, 4 Aug 2023 18:23:14 +0800
Subject: replace get_first_stage_encoding

---
 modules/processing.py | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index aae39866..aa6d4d2a 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -16,6 +16,7 @@ from typing import Any, Dict, List
 import modules.sd_hijack
 from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, extra_networks, sd_vae_approx, scripts, sd_samplers_common, sd_unet, errors
 from modules.sd_hijack import model_hijack
+from modules.sd_samplers_common import images_tensor_to_samples, decode_first_stage, approximation_indexes
 from modules.shared import opts, cmd_opts, state
 import modules.shared as shared
 import modules.paths as paths
@@ -30,7 +31,6 @@ from ldm.models.diffusion.ddpm import LatentDepth2ImageDiffusion
 from einops import repeat, rearrange
 from blendmodes.blend import blendLayers, BlendType
 
-decode_first_stage = sd_samplers_common.decode_first_stage
 
 # some of those options should not be changed at all because they would break the model, so I removed them from options.
 opt_C = 4
@@ -84,7 +84,7 @@ def txt2img_image_conditioning(sd_model, x, width, height):
 
         # 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))
+        image_conditioning = images_tensor_to_samples(image_conditioning, approximation_indexes.get(opts.sd_vae_encode_method))
 
         # 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)
@@ -203,7 +203,7 @@ class StableDiffusionProcessing:
         midas_in = torch.from_numpy(transformed["midas_in"][None, ...]).to(device=shared.device)
         midas_in = repeat(midas_in, "1 ... -> n ...", n=self.batch_size)
 
-        conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(source_image))
+        conditioning_image = images_tensor_to_samples(source_image*0.5+0.5, approximation_indexes.get(opts.sd_vae_encode_method))
         conditioning = torch.nn.functional.interpolate(
             self.sd_model.depth_model(midas_in),
             size=conditioning_image.shape[2:],
@@ -216,7 +216,7 @@ class StableDiffusionProcessing:
         return conditioning
 
     def edit_image_conditioning(self, source_image):
-        conditioning_image = self.sd_model.encode_first_stage(source_image).mode()
+        conditioning_image = images_tensor_to_samples(source_image*0.5+0.5, approximation_indexes.get(opts.sd_vae_encode_method))
 
         return conditioning_image
 
@@ -1099,9 +1099,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 
             decoded_samples = torch.from_numpy(np.array(batch_images))
             decoded_samples = decoded_samples.to(shared.device)
-            decoded_samples = 2. * decoded_samples - 1.
 
-            samples = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(decoded_samples))
+            samples = images_tensor_to_samples(decoded_samples, approximation_indexes.get(opts.sd_vae_encode_method))
 
             image_conditioning = self.img2img_image_conditioning(decoded_samples, samples)
 
@@ -1339,7 +1338,6 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
             raise RuntimeError(f"bad number of images passed: {len(imgs)}; expecting {self.batch_size} or less")
 
         image = torch.from_numpy(batch_images)
-        from modules.sd_samplers_common import images_tensor_to_samples, approximation_indexes
         self.init_latent = images_tensor_to_samples(image, approximation_indexes.get(opts.sd_vae_encode_method), self.sd_model)
         devices.torch_gc()
 
-- 
cgit v1.2.3


From aa744cadc8e357e696a608c8d0c77a7bfc1c9f39 Mon Sep 17 00:00:00 2001
From: Kohaku-Blueleaf <59680068+KohakuBlueleaf@users.noreply.github.com>
Date: Sat, 5 Aug 2023 12:35:40 +0800
Subject: add infotext

---
 modules/processing.py | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index aa6d4d2a..a9ee7507 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -788,6 +788,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
             with devices.without_autocast() if devices.unet_needs_upcast else devices.autocast():
                 samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
 
+            p.extra_generation_params['VAE Decoder'] = opts.sd_vae_decode_method
             x_samples_ddim = decode_latent_batch(p.sd_model, samples_ddim, target_device=devices.cpu, check_for_nans=True)
             x_samples_ddim = torch.stack(x_samples_ddim).float()
             x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)
@@ -1100,6 +1101,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             decoded_samples = torch.from_numpy(np.array(batch_images))
             decoded_samples = decoded_samples.to(shared.device)
 
+            self.extra_generation_params['VAE Encoder'] = opts.sd_vae_encode_method
             samples = images_tensor_to_samples(decoded_samples, approximation_indexes.get(opts.sd_vae_encode_method))
 
             image_conditioning = self.img2img_image_conditioning(decoded_samples, samples)
@@ -1338,6 +1340,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
             raise RuntimeError(f"bad number of images passed: {len(imgs)}; expecting {self.batch_size} or less")
 
         image = torch.from_numpy(batch_images)
+        self.extra_generation_params['VAE Encoder'] = opts.sd_vae_encode_method
         self.init_latent = images_tensor_to_samples(image, approximation_indexes.get(opts.sd_vae_encode_method), self.sd_model)
         devices.torch_gc()
 
-- 
cgit v1.2.3


From b85ec2b9b66492ff9bf3d40a4d9b424390067f0f Mon Sep 17 00:00:00 2001
From: Kohaku-Blueleaf <59680068+KohakuBlueleaf@users.noreply.github.com>
Date: Sat, 5 Aug 2023 13:14:00 +0800
Subject: Fix some merge mistakes

---
 modules/processing.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index b9900ded..43cb763f 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -1136,7 +1136,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
                 batch_images.append(image)
 
             decoded_samples = torch.from_numpy(np.array(batch_images))
-            decoded_samples = decoded_samples.to(shared.device)
+            decoded_samples = decoded_samples.to(shared.device, dtype=devices.dtype_vae)
 
             self.extra_generation_params['VAE Encoder'] = opts.sd_vae_encode_method
             samples = images_tensor_to_samples(decoded_samples, approximation_indexes.get(opts.sd_vae_encode_method))
@@ -1374,6 +1374,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
             raise RuntimeError(f"bad number of images passed: {len(imgs)}; expecting {self.batch_size} or less")
 
         image = torch.from_numpy(batch_images)
+        image = image.to(shared.device, dtype=devices.dtype_vae)
         self.extra_generation_params['VAE Encoder'] = opts.sd_vae_encode_method
         self.init_latent = images_tensor_to_samples(image, approximation_indexes.get(opts.sd_vae_encode_method), self.sd_model)
         devices.torch_gc()
-- 
cgit v1.2.3


From 3f451f3042cc69a751cebc329c11f9f145da5186 Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Sat, 5 Aug 2023 10:36:26 +0300
Subject: do not add VAE Encoder/Decoder to infotext if it's the default

---
 modules/processing.py | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index 43cb763f..a9d66005 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -795,7 +795,9 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
             if getattr(samples_ddim, 'already_decoded', False):
                 x_samples_ddim = samples_ddim
             else:
-                p.extra_generation_params['VAE Decoder'] = opts.sd_vae_decode_method
+                if opts.sd_vae_decode_method != 'Full':
+                    p.extra_generation_params['VAE Decoder'] = opts.sd_vae_decode_method
+
                 x_samples_ddim = decode_latent_batch(p.sd_model, samples_ddim, target_device=devices.cpu, check_for_nans=True)
 
             x_samples_ddim = torch.stack(x_samples_ddim).float()
@@ -1138,7 +1140,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             decoded_samples = torch.from_numpy(np.array(batch_images))
             decoded_samples = decoded_samples.to(shared.device, dtype=devices.dtype_vae)
 
-            self.extra_generation_params['VAE Encoder'] = opts.sd_vae_encode_method
+            if opts.sd_vae_encode_method != 'Full':
+                self.extra_generation_params['VAE Encoder'] = opts.sd_vae_encode_method
             samples = images_tensor_to_samples(decoded_samples, approximation_indexes.get(opts.sd_vae_encode_method))
 
             image_conditioning = self.img2img_image_conditioning(decoded_samples, samples)
@@ -1375,7 +1378,10 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
 
         image = torch.from_numpy(batch_images)
         image = image.to(shared.device, dtype=devices.dtype_vae)
-        self.extra_generation_params['VAE Encoder'] = opts.sd_vae_encode_method
+
+        if opts.sd_vae_encode_method != 'Full':
+            self.extra_generation_params['VAE Encoder'] = opts.sd_vae_encode_method
+
         self.init_latent = images_tensor_to_samples(image, approximation_indexes.get(opts.sd_vae_encode_method), self.sd_model)
         devices.torch_gc()
 
-- 
cgit v1.2.3


From 1d7dcdb6c38c7bca945b3fa8a5d4a1f93446f22a Mon Sep 17 00:00:00 2001
From: w-e-w <40751091+w-e-w@users.noreply.github.com>
Date: Sat, 5 Aug 2023 19:07:39 +0900
Subject: Option to not save incomplete images

---
 modules/processing.py | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index 43cb763f..bf4f938b 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -103,6 +103,10 @@ def txt2img_image_conditioning(sd_model, x, width, height):
         return x.new_zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
 
 
+def save_images_if_interrupted():
+    return not (opts.dont_save_interrupted_images and (state.interrupted or state.skipped))
+
+
 class StableDiffusionProcessing:
     """
     The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
@@ -821,6 +825,8 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
             def infotext(index=0, use_main_prompt=False):
                 return create_infotext(p, p.prompts, p.seeds, p.subseeds, use_main_prompt=use_main_prompt, index=index, all_negative_prompts=p.negative_prompts)
 
+            save_images_if_interrupt = save_images_if_interrupted()
+
             for i, x_sample in enumerate(x_samples_ddim):
                 p.batch_index = i
 
@@ -828,7 +834,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                 x_sample = x_sample.astype(np.uint8)
 
                 if p.restore_faces:
-                    if opts.save and not p.do_not_save_samples and opts.save_images_before_face_restoration:
+                    if opts.save and not p.do_not_save_samples and opts.save_images_before_face_restoration and save_images_if_interrupt:
                         images.save_image(Image.fromarray(x_sample), p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-before-face-restoration")
 
                     devices.torch_gc()
@@ -842,16 +848,15 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                     pp = scripts.PostprocessImageArgs(image)
                     p.scripts.postprocess_image(p, pp)
                     image = pp.image
-
                 if p.color_corrections is not None and i < len(p.color_corrections):
-                    if opts.save and not p.do_not_save_samples and opts.save_images_before_color_correction:
+                    if opts.save and not p.do_not_save_samples and opts.save_images_before_color_correction and save_images_if_interrupt:
                         image_without_cc = apply_overlay(image, p.paste_to, i, p.overlay_images)
                         images.save_image(image_without_cc, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-before-color-correction")
                     image = apply_color_correction(p.color_corrections[i], image)
 
                 image = apply_overlay(image, p.paste_to, i, p.overlay_images)
 
-                if opts.samples_save and not p.do_not_save_samples:
+                if opts.samples_save and not p.do_not_save_samples and save_images_if_interrupt:
                     images.save_image(image, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p)
 
                 text = infotext(i)
@@ -859,8 +864,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                 if opts.enable_pnginfo:
                     image.info["parameters"] = text
                 output_images.append(image)
-
-                if hasattr(p, 'mask_for_overlay') and p.mask_for_overlay and any([opts.save_mask, opts.save_mask_composite, opts.return_mask, opts.return_mask_composite]):
+                if hasattr(p, 'mask_for_overlay') and p.mask_for_overlay and any([opts.save_mask, opts.save_mask_composite, opts.return_mask, opts.return_mask_composite]) and save_images_if_interrupt:
                     image_mask = p.mask_for_overlay.convert('RGB')
                     image_mask_composite = Image.composite(image.convert('RGBA').convert('RGBa'), Image.new('RGBa', image.size), images.resize_image(2, p.mask_for_overlay, image.width, image.height).convert('L')).convert('RGBA')
 
@@ -896,7 +900,6 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
                     grid.info["parameters"] = text
                 output_images.insert(0, grid)
                 index_of_first_image = 1
-
             if opts.grid_save:
                 images.save_image(grid, p.outpath_grids, "grid", p.all_seeds[0], p.all_prompts[0], opts.grid_format, info=infotext(use_main_prompt=True), short_filename=not opts.grid_extended_filename, p=p, grid=True)
 
@@ -1091,7 +1094,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         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:
+            if not opts.save or self.do_not_save_samples or not opts.save_images_before_highres_fix or not save_images_if_interrupted():
                 return
 
             if not isinstance(image, Image.Image):
-- 
cgit v1.2.3


From 496cef956b3337c4745b1224e244706bd747195a Mon Sep 17 00:00:00 2001
From: catboxanon <122327233+catboxanon@users.noreply.github.com>
Date: Sat, 5 Aug 2023 21:14:13 -0400
Subject: Allow s_noise override to actually be used

---
 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 a9d66005..1601a14c 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -149,7 +149,7 @@ class StableDiffusionProcessing:
         self.s_churn = s_churn or opts.s_churn
         self.s_tmin = s_tmin or opts.s_tmin
         self.s_tmax = s_tmax or float('inf')  # not representable as a standard ui option
-        self.s_noise = s_noise or opts.s_noise
+        self.s_noise = opts.data.get('s_noise', s_noise)
         self.override_settings = {k: v for k, v in (override_settings or {}).items() if k not in shared.restricted_opts}
         self.override_settings_restore_afterwards = override_settings_restore_afterwards
         self.is_using_inpainting_conditioning = False
-- 
cgit v1.2.3


From c11104fed5ffee7b9a22674889580028296c5e55 Mon Sep 17 00:00:00 2001
From: catboxanon <122327233+catboxanon@users.noreply.github.com>
Date: Sat, 5 Aug 2023 21:42:03 -0400
Subject: Add s_tmax

---
 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 a9d66005..a5cd2a47 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -148,7 +148,7 @@ class StableDiffusionProcessing:
         self.s_min_uncond = s_min_uncond or opts.s_min_uncond
         self.s_churn = s_churn or opts.s_churn
         self.s_tmin = s_tmin or opts.s_tmin
-        self.s_tmax = s_tmax or float('inf')  # not representable as a standard ui option
+        self.s_tmax = opts.data.get('s_tmax', 0) or float('inf')  # not representable as a standard ui option
         self.s_noise = s_noise or opts.s_noise
         self.override_settings = {k: v for k, v in (override_settings or {}).items() if k not in shared.restricted_opts}
         self.override_settings_restore_afterwards = override_settings_restore_afterwards
-- 
cgit v1.2.3


From 85c2c138d2f5f853c79bde3775d69628e86c65ca Mon Sep 17 00:00:00 2001
From: catboxanon <122327233+catboxanon@users.noreply.github.com>
Date: Sat, 5 Aug 2023 21:51:46 -0400
Subject: Attempt to read s_tmax from arg first if option not found

---
 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 a5cd2a47..2003532d 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -148,7 +148,7 @@ class StableDiffusionProcessing:
         self.s_min_uncond = s_min_uncond or opts.s_min_uncond
         self.s_churn = s_churn or opts.s_churn
         self.s_tmin = s_tmin or opts.s_tmin
-        self.s_tmax = opts.data.get('s_tmax', 0) or float('inf')  # not representable as a standard ui option
+        self.s_tmax = opts.data.get('s_tmax', s_tmax or 0) or float('inf')  # not representable as a standard ui option
         self.s_noise = s_noise or opts.s_noise
         self.override_settings = {k: v for k, v in (override_settings or {}).items() if k not in shared.restricted_opts}
         self.override_settings_restore_afterwards = override_settings_restore_afterwards
-- 
cgit v1.2.3


From f18a03219039ebaa48ce96adc5b50e0e5ed5d84f Mon Sep 17 00:00:00 2001
From: catboxanon <122327233+catboxanon@users.noreply.github.com>
Date: Sat, 5 Aug 2023 23:05:25 -0400
Subject: Correct s_noise fix

---
 modules/processing.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index 1601a14c..bb268db7 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -110,7 +110,7 @@ class StableDiffusionProcessing:
     cached_uc = [None, None]
     cached_c = [None, None]
 
-    def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str = "", styles: List[str] = None, seed: int = -1, subseed: int = -1, subseed_strength: float = 0, seed_resize_from_h: int = -1, seed_resize_from_w: int = -1, seed_enable_extras: bool = True, sampler_name: str = None, batch_size: int = 1, n_iter: int = 1, steps: int = 50, cfg_scale: float = 7.0, width: int = 512, height: int = 512, restore_faces: bool = False, tiling: bool = False, do_not_save_samples: bool = False, do_not_save_grid: bool = False, extra_generation_params: Dict[Any, Any] = None, overlay_images: Any = None, negative_prompt: str = None, eta: float = None, do_not_reload_embeddings: bool = False, denoising_strength: float = 0, ddim_discretize: str = None, s_min_uncond: float = 0.0, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0, override_settings: Dict[str, Any] = None, override_settings_restore_afterwards: bool = True, sampler_index: int = None, script_args: list = None):
+    def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str = "", styles: List[str] = None, seed: int = -1, subseed: int = -1, subseed_strength: float = 0, seed_resize_from_h: int = -1, seed_resize_from_w: int = -1, seed_enable_extras: bool = True, sampler_name: str = None, batch_size: int = 1, n_iter: int = 1, steps: int = 50, cfg_scale: float = 7.0, width: int = 512, height: int = 512, restore_faces: bool = False, tiling: bool = False, do_not_save_samples: bool = False, do_not_save_grid: bool = False, extra_generation_params: Dict[Any, Any] = None, overlay_images: Any = None, negative_prompt: str = None, eta: float = None, do_not_reload_embeddings: bool = False, denoising_strength: float = 0, ddim_discretize: str = None, s_min_uncond: float = 0.0, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = None, override_settings: Dict[str, Any] = None, override_settings_restore_afterwards: bool = True, sampler_index: int = None, script_args: list = None):
         if sampler_index is not None:
             print("sampler_index argument for StableDiffusionProcessing does not do anything; use sampler_name", file=sys.stderr)
 
@@ -149,7 +149,7 @@ class StableDiffusionProcessing:
         self.s_churn = s_churn or opts.s_churn
         self.s_tmin = s_tmin or opts.s_tmin
         self.s_tmax = s_tmax or float('inf')  # not representable as a standard ui option
-        self.s_noise = opts.data.get('s_noise', s_noise)
+        self.s_noise = s_noise if s_noise is not None else opts.data.get('s_noise', 1.0)
         self.override_settings = {k: v for k, v in (override_settings or {}).items() if k not in shared.restricted_opts}
         self.override_settings_restore_afterwards = override_settings_restore_afterwards
         self.is_using_inpainting_conditioning = False
-- 
cgit v1.2.3


From d86d12e9117772f041682124badc7baac7c57911 Mon Sep 17 00:00:00 2001
From: AUTOMATIC1111 <16777216c@gmail.com>
Date: Sun, 6 Aug 2023 06:21:36 +0300
Subject: rework saving incomplete images

---
 modules/processing.py | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index 8f26621b..aef8fafd 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -103,10 +103,6 @@ def txt2img_image_conditioning(sd_model, x, width, height):
         return x.new_zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
 
 
-def save_images_if_interrupted():
-    return not (opts.dont_save_interrupted_images and (state.interrupted or state.skipped))
-
-
 class StableDiffusionProcessing:
     """
     The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
@@ -372,6 +368,10 @@ class StableDiffusionProcessing:
     def parse_extra_network_prompts(self):
         self.prompts, self.extra_network_data = extra_networks.parse_prompts(self.prompts)
 
+    def save_samples(self) -> bool:
+        """Returns whether generated images need to be written to disk"""
+        return opts.samples_save and not self.do_not_save_samples and (opts.save_incomplete_images or not state.interrupted and not state.skipped)
+
 
 class Processed:
     def __init__(self, p: StableDiffusionProcessing, images_list, seed=-1, info="", subseed=None, all_prompts=None, all_negative_prompts=None, all_seeds=None, all_subseeds=None, index_of_first_image=0, infotexts=None, comments=""):
@@ -827,7 +827,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
             def infotext(index=0, use_main_prompt=False):
                 return create_infotext(p, p.prompts, p.seeds, p.subseeds, use_main_prompt=use_main_prompt, index=index, all_negative_prompts=p.negative_prompts)
 
-            save_images_if_interrupt = save_images_if_interrupted()