Upload 6 files

Instructions.txt

@@ -4,8 +4,6 @@
 
     Spaghetti AI for Windows using NVIDIA GPU
 
-        December 28th, 2023 - This app remains a work in progress.
-
 
         I wanted to come up with a unique name for the app, so I chose something
         silly.
@@ -369,7 +367,82 @@ cd C:/Spaghetti_AI && .venv\Scripts\activate.bat && pip install https://gradio-b
 --------------------
 
 
-    Step 10:
+    Step 10 (Important):
+
+        I feel this is a very important step. When you try to create model data
+        for each base model, as well as use the refiner and upscaler, model data
+        will try to be downloaded. There is also an option to download all, or
+        just the default data, at one time. That we will cover in a later step.
+        But before you can download model data, you need to make sure two things
+        are set to "0". At least one will not be when you get this script so
+        that you read this section.
+
+        All the model data could be 40 gigabytes or more of data. I strongly
+        recommend that you then disable the script from downloading updates to
+        the model data once you have downloaded what you want. HuggingFace
+        doesn't just download a model once and never try again. If something is
+        updated, it will download it again. It will not delete the older
+        version. This could eventually allow it to use all the space on your
+        hard drive as that could potentially add 5 to 15 gigabytes of data each
+        time a model updates. There are two variables that you need to make sure
+        are "0". If you do not use "spaghetti_ai_launcher.bat", then there is
+        only one.
+
+        In "spaghetti_ai_launcher.bat", if you use it, set this to 0:
+
+            HF_HUB_OFFLINE
+
+        In "spaghetti_ai_script.py", set this to 0:
+
+            only_use_local_files
+
+        To have model data download, both variables must be set to 0 or model
+        data will not download. Eventually I may only use one of those. You
+        can't set, that I can see, "HF_HUB_OFFLINE" in the python script. It
+        should now block all requests online, including to download model data,
+        whereas the other only prevents model data from being downloaded. Some
+        people might not use "spaghetti_ai_launcher.bat", so it's hard to just
+        pick one to use.
+
+        If you use "spaghetti_ai_launcher.bat" to launch the script, you can set
+        "HF_HUB_OFFLINE" in that file to 1 to not download data again and not
+        set "only_use_local_files". That variable will automatically be changed
+        to "1" if "HF_HUB_OFFLINE" is set to "1"
+
+        "HF_HUB_OFFLINE" can be set permanently in Windows, until you change it,
+        but this is the easiest way that doesn't impact other installations. If
+        you wanted to permanently store that environment variable in Windows,
+        which I don't recommend, it would impact other installations that use
+        Hugging Face. This only has it apply when using the script.
+
+        You can read about environment variables here at Hugging Face:
+
+            https://huggingface.co/docs/huggingface_hub/package_reference/environment_variables#hfhuboffline
+
+        In regard to Hugging Face caching things, you can learn more on this
+        page:
+
+            https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations
+
+        The first time you use the script you will need to set HF_HUB_OFFLINE to
+        0 like this there:
+
+set HF_HUB_OFFLINE=0
+
+        Do not include any spaces before or after the equals sign.
+
+        Or access the app from the command line when you want to download data
+        if "only_use_local_files" is set to "0".
+
+        The script will not work otherwise. Because of the importance of this
+        variable, I prefer to not have the script work with the .bat file until
+        someone changes that value themselves.
+
+
+--------------------
+
+
+    Step 11:
 
         You're ready to run the script that runs the web interface.
 
@@ -424,11 +497,13 @@ cd C:/Spaghetti_AI && .venv\Scripts\activate.bat && py .venv\app_files\spaghetti
         You should know that this folder can grow considerably. You need to
         manually clean it out when you need to get rid of old models.
         Occasionally, new versions will be downloaded when you create an image.
-        When that happens, you may want to remove the old version if the new
-        version works. Otherwise, you could have 10 to 20 gigabytes of space
-        added each time you use a model that updates.
+        O(unless you turned off the ability to download model data) When that
+        Ohappens, you may want to remove the old version if the new version
+        Oworks. Otherwise, you could have 5 to 15 gigabytes of space added each
+        Otime you use a model that updates.
 
-        You should also know that temporary images created are likely stored here:
+        You should also know that temporary images created are likely stored
+        Ohere:
 
             %USERPROFILE%/AppData/Local/Temp/gradio
 
@@ -451,7 +526,7 @@ cd C:/Spaghetti_AI && .venv\Scripts\activate.bat && py .venv\app_files\spaghetti
 --------------------
 
 
-    Step 11:
+    Step 12:
 
         When you open the link, you'll see the display to create the imagery.
         You must leave the command prompt open. When you process an image, the
@@ -465,7 +540,7 @@ cd C:/Spaghetti_AI && .venv\Scripts\activate.bat && py .venv\app_files\spaghetti
 --------------------
 
 
-    Step 12:
+    Step 13:
 
         To create a shortcut to the command that needs to be launched every
         time, use:
@@ -510,52 +585,8 @@ cd C:/Spaghetti_AI && .venv\Scripts\activate.bat && py .venv\app_files\spaghetti
         You might also not be able to use a shortcut. If so, just copy
         "spaghetti_ai_launcher.bat" and put it on your desktop and name it what
         you want. The downside, if you do that, would be reconfiguring your
-        firewall to use it from that location too.
-
-
---------------------
-
-
-    Step 13 (Important):
-
-        I feel this is a very important step. After you have created model data
-        for each base model, as well as have used the refiner and upscaler, data
-        will then have been downloaded. (or you use the method to download the
-        data at the same time) This could be 40 gigabytes or more of data. I
-        strongly recommend that you then disable the script from downloading
-        updates to the model data. It will not automatically delete old data. If
-        you didn't manually go through and delete the older data, eventually the
-        model data would use all of the space on your computer.
-
-        If you use "spaghetti_ai_launcher.bat" to launch the script, you can set
-        "HF_HUB_OFFLINE" in that file to 1 to not download data again.
-
-        That is the easiest way that doesn't impact other installations. If you
-        wanted to permanently store that environment variable in Windows, which
-        I don't recommend, it would impact other installations that use Hugging
-        Face. This only has it apply when using the script.
-
-        You can read about environment variables here at Hugging Face:
-
-            https://huggingface.co/docs/huggingface_hub/package_reference/environment_variables#hfhuboffline
-
-        In regard to Hugging Face caching things, you can learn more on this
-        page:
-
-            https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations
-
-        The first time you use the script you will need to set HF_HUB_OFFLINE to
-        0 like this there:
-
-set HF_HUB_OFFLINE=0
-
-        Do not include any spaces before or after the equals sign.
-
-        Or access the app from the command line when you want to download data.
-
-        The script will not work otherwise. Because of the importance of this
-        variable, I prefer to not have the script work with the .bat file until
-        someone changes that value themselves.
+        firewall to use it from that location too. It's best to create a
+        shortcut.
 
 
 --------------------
@@ -601,7 +632,8 @@ set HF_HUB_OFFLINE=0
               The main script.
 
               "C:/Spaghetti_AI" needs to be set in "main_dir" in this file if
-              you change the path.
+              you change the path. If "only_use_local_files" is set to "1", you
+              will need to change it to download model data.
 
         - Spaghetti AI (no icon).lnk
         - Spaghetti AI.lnk
@@ -617,3 +649,25 @@ set HF_HUB_OFFLINE=0
               provided or another. If you change the path from
               "C:/Spaghetti_AI", the shortcut will have to be edited in the
               "Target" field of the "Shortcut" tab.
+
+
+--------------------
+
+
+    Various Information
+
+        You get this error:
+
+            "CUDA out of memory. Tried to allocate 82.00 MiB. GPU 0 has a total
+            capacty of 12.00 GiB of which 0 bytes is free. Of the allocated
+            memory 16.97 GiB is allocated by PyTorch, and 439.95 MiB is reserved
+            by PyTorch but unallocated. If reserved but unallocated memory is
+            large try setting max_split_size_mb to avoid fragmentation. See
+            documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF"
+
+        Try setting these to 1 in spaghetti_ai_script.py:
+
+use_sequential_cpu_offload_for_base_model = 1
+use_sequential_cpu_offload_for_refiner = 1
+use_sequential_cpu_offload_for_upscaler = 1
+

README.md

@@ -4,7 +4,7 @@ emoji: 💻
 colorFrom: blue
 colorTo: blue
 sdk: gradio
-sdk_version: 4.11.0
+sdk_version: 4.13.0
 app_file: spaghetti_ai_script.py
 pinned: false
 license: mit

spaghetti_ai.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d0277d19fa65d8476f48587806150af5f3dc70042405e62b2027233c1de5f4
-size 88898
+oid sha256:b1b63dabdff2dc4c16c0a0732144d07b0e8fca2daba0f8f86f39c78751f332af
+size 93329

spaghetti_ai_install.txt

@@ -5,8 +5,6 @@ REM
 REM
 REM    Install Spaghetti AI for Windows using NVIDIA GPU
 REM
-REM        December 28th, 2023 - This app remains a work in progress.
-REM
 REM
 REM        Before running this script, you need to complete the following steps.
 REM

spaghetti_ai_launcher.bat

@@ -5,8 +5,6 @@ REM
 REM
 REM    Install Spaghetti AI for Windows using NVIDIA GPU
 REM
-REM        December 28th, 2023 - This app remains a work in progress.
-REM
 REM
 REM    Instructions for this file
 REM

spaghetti_ai_script.py

@@ -11,14 +11,6 @@ import time
 
 ##########
 
-#
-#    The zip file wasn't updated on January 4th, 2024. This is just a version
-#    I wanted to get out that I have been working on for awhile. The cancel
-#    button doesn't work yet so that is not enabled.
-#
-
-##########
-
 #
 #    Spaghetti AI by MagicFixesEverything
 #        https://huggingface.co/magicfixeseverything
@@ -242,7 +234,7 @@ auto_open_browser = 0
 #        immediately. It will stop after completing the current step it is on.
 #
 
-enable_image_generation_cancellation = 0
+enable_image_generation_cancellation = 1
 
 ####################
 
@@ -252,9 +244,7 @@ enable_image_generation_cancellation = 0
 #        This will likely be removed in the future.
 #
 #        This doesn't work well at all. It just closes the command prompt. I
-#        might remove this eventually unless someone knows of a way it can work
-#        better, such as stopping the generation without closing the command
-#        prompt.
+#        might remove this eventually.
 #
 
 enable_close_command_prompt_button = 0
@@ -357,6 +347,16 @@ default_add_seed_into_pipe = 1
 
 ####################
 
+#
+#    Use torch.manual_seed But Do Not Add To Pipe
+#
+#        We need this to match the PhotoReal site to make it work.
+#
+
+default_use_torch_manual_seed_but_do_not_add_to_pipe = 0
+
+####################
+
 #
 #    Save Base Image When Using Refiner
 #
@@ -443,6 +443,9 @@ base_model_names_object = {
 #        https://huggingface.co/spaces/Manjushri/SDXL-1.0
 #        https://huggingface.co/spaces/Manjushri/PhotoReal-V3.8.1
 #
+#    The PhotoReal site doesn't explicitly add the seed to the generation, so
+#    that option needs to be unchecked to match that imagery.
+#
 #    You can use the following customizations...
 #
 ##########
@@ -470,7 +473,7 @@ base_model_names_object = {
 #          For some reason, I haven't been able to match this version of the
 #          configuration yet. That means this link doesn't work:
 #
-#          http://127.0.0.1:7860/?model=photoreal&model_config=photoreal_3-8-1&scheduler=model_default&width=768&height=768&guidance=5&steps=50&prompt=&neg_prompt=&seed=&add_seed=no&refiner=no&denoise_start=0.95&refiner_steps=&use_denoise_end=no&latent_space_before_refiner=no&upscaler=no&upscaler_steps=
+#          http://127.0.0.1:7860/?model=photoreal&model_config=photoreal_3-8-1&scheduler=model_default&width=768&height=768&guidance=5&steps=50&prompt=&neg_prompt=&seed=&add_seed=no&use_torch_manual_seed_but_not_in_generator=yes&refiner=no&denoise_start=0.95&refiner_steps=&use_denoise_end=no&latent_space_before_refiner=no&upscaler=no&upscaler_steps=
 #
 ####################
 #
@@ -479,7 +482,7 @@ base_model_names_object = {
 #        - Valid from November 12th to December 29th.
 #          Base model was changed from 3.6 to 3.7.5: "circulus/canvers-real-v3.7.5"
 #
-#          http://127.0.0.1:7860/?model=photoreal&model_config=photoreal_3-7-5&scheduler=model_default&width=768&height=768&guidance=7&steps=50&prompt=&neg_prompt=&seed=&add_seed=no&refiner=no&denoise_start=0.95&refiner_steps=&use_denoise_end=no&latent_space_before_refiner=no&upscaler=no&upscaler_steps=
+#          http://127.0.0.1:7860/?model=photoreal&model_config=photoreal_3-7-5&scheduler=model_default&width=768&height=768&guidance=7&steps=50&prompt=&neg_prompt=&seed=&add_seed=no&use_torch_manual_seed_but_not_in_generator=yes&refiner=no&denoise_start=0.95&refiner_steps=&use_denoise_end=no&latent_space_before_refiner=no&upscaler=no&upscaler_steps=
 #
 ####################
 #
@@ -489,7 +492,7 @@ base_model_names_object = {
 #          "circulus/canvers-realistic-v3.6" was already in effect.
 #          But there were changes on this date.
 #
-#          http://127.0.0.1:7860/?model=photoreal&model_config=photoreal_3-6&scheduler=model_default&width=768&height=768&guidance=7&steps=50&prompt=&neg_prompt=&seed=&add_seed=no&refiner=no&denoise_start=0.95&refiner_steps=&use_denoise_end=no&latent_space_before_refiner=no&upscaler=no&upscaler_steps=
+#          http://127.0.0.1:7860/?model=photoreal&model_config=photoreal_3-6&scheduler=model_default&width=768&height=768&guidance=7&steps=50&prompt=&neg_prompt=&seed=&add_seed=no&use_torch_manual_seed_but_not_in_generator=yes&refiner=no&denoise_start=0.95&refiner_steps=&use_denoise_end=no&latent_space_before_refiner=no&upscaler=no&upscaler_steps=
 #
 ####################
 
@@ -949,10 +952,8 @@ number_of_reserved_tokens = 2
 generate_image_button_normal_text = "Generate Image"
 generate_image_button_in_progress_text = "Generating..."
 
-cancel_image_in_queue_button_text = "Cancel"
-
-cancel_image_in_progress_button_normal_text = "Cancel Processing"
-cancel_image_in_progress_button_in_progress_text = "Cancelling..."
+cancel_image_button_text = "Cancel"
+cancel_image_button_in_progress_text = "Cancelling..."
 
 
 
@@ -961,6 +962,12 @@ gradio_image_gallery_component_height = 350
 
 
 
+canceled_image_in_queue_message = "Due to how the queue works in this app, you need to reload the page after canceling an image. Otherwise, you will not be able to generate another image until you reach the position in the queue you were in originally. At that time, the button to generate an image will appear again."
+
+canceled_image_in_process_of_being_generated = "<div style=\"text-align: center;\">Image generation will be canceled once the current step completes.</div>"
+
+
+
 ###############################################################################
 ###############################################################################
 #
@@ -975,6 +982,12 @@ gradio_image_gallery_component_height = 350
 
 
 
+if default_add_seed_into_pipe == 1:
+
+    default_use_torch_manual_seed_but_do_not_add_to_pipe = 0
+
+
+
 if script_being_run_on_hugging_face == 1:
 
     #    If on HuggingFace, I change some things.
@@ -1384,6 +1397,14 @@ if default_add_seed_into_pipe == 1:
 
 
 
+default_use_torch_manual_seed_but_do_not_add_to_pipe_is_selected = False
+
+if default_use_torch_manual_seed_but_do_not_add_to_pipe == 1:
+
+    default_use_torch_manual_seed_but_do_not_add_to_pipe_is_selected = True
+
+
+
 default_save_base_image_when_using_refiner_is_selected = False
 
 if default_save_base_image_when_using_refiner == 1:
@@ -1445,6 +1466,10 @@ current_preview_image_user_id = 0
 
 
 
+current_image_generation_id_in_progress = 0
+
+
+
 cancel_image_generation_ids_object = {}
 cancel_image_generation_times_object = {}
 seconds_to_store_cancellations_in_cancel_image_generation_times_object = 86400
@@ -2897,17 +2922,6 @@ def load_image_preview (
 
     user_id_state_value = user_id_state.value
 
-
-
-
-
-
-#    print ("constant ... user_id_state_value: ", user_id_state_value)
-
-
-
-
-
 #    print ("Image preview check run", current_preview_image_user_id, user_id_state_value)
 
     if (
@@ -2982,10 +2996,6 @@ def before_create_image_function ():
 
 
 
-    #print ("before_create_image_function: ", image_generation_id)
-
-
-
     before_create_image_object = {
         generate_image_button: generate_image_button_update,
         output_text_field: output_text_field_update,
@@ -3018,22 +3028,17 @@ def before_create_image_function ():
 
     if enable_image_generation_cancellation == 1:
 
-        cancel_image_buttons_group_update = gr.Group(
+        cancel_image_button_row_update = gr.Row(
             visible = True
         )
 
-        cancel_image_in_queue_button_update = gr.Button(
-            interactive = True
-        )
-
-        cancel_image_in_progress_button_update = gr.Button(
+        cancel_image_button_update = gr.Button(
             interactive = True
         )
 
         before_create_image_object.update({
-            cancel_image_buttons_group: cancel_image_buttons_group_update,
-            cancel_image_in_queue_button: cancel_image_in_queue_button_update,
-            cancel_image_in_progress_button: cancel_image_in_progress_button_update
+            cancel_image_button_row: cancel_image_button_row_update,
+            cancel_image_button: cancel_image_button_update
         })
 
     return before_create_image_object
@@ -3054,8 +3059,6 @@ def before_create_image_function ():
 
 def after_create_image_function ():
 
-    #print ("after_create_image_function")
-
     generate_image_button_update = gr.Button(
         value = generate_image_button_normal_text,
         variant = "primary",
@@ -3097,30 +3100,29 @@ def after_create_image_function ():
             visible = True
         )
 
-        cancel_image_buttons_group_update = gr.Group(
+        cancel_image_button_row_update = gr.Row(
             visible = False
         )
 
-        cancel_image_in_queue_button_update = gr.Button(
-            value = cancel_image_in_queue_button_text,
+        cancel_image_button_update = gr.Button(
+            value = cancel_image_button_text,
             interactive = False
         )
 
-        cancel_image_in_progress_button_update = gr.Button(
-            value = cancel_image_in_progress_button_normal_text,
-            interactive = False
+        cancel_image_message_field_row_update = gr.Button(
+            visible = False
         )
 
-        cancel_image_in_progress_message_field_row_update = gr.Button(
-            visible = False
+        cancel_image_message_field_update = gr.Button(
+            value = ""
         )
 
         after_create_image_object.update({
             generate_image_button_row: generate_image_button_row_update,
-            cancel_image_buttons_group: cancel_image_buttons_group_update,
-            cancel_image_in_queue_button: cancel_image_in_queue_button_update,
-            cancel_image_in_progress_button: cancel_image_in_progress_button_update,
-            cancel_image_in_progress_message_field_row: cancel_image_in_progress_message_field_row_update
+            cancel_image_button_row: cancel_image_button_row_update,
+            cancel_image_button: cancel_image_button_update,
+            cancel_image_message_field_row: cancel_image_message_field_row_update,
+            cancel_image_message_field: cancel_image_message_field_update
         })
 
     return after_create_image_object
@@ -3144,11 +3146,6 @@ def remove_from_cancel_object (
     image_generation_id_state_value
 ):
 
-    #print ("remove_from_cancel_object")
-
-    #print (cancel_image_generation_ids_object)
-    #print (cancel_image_generation_times_object)
-
     if (
         (user_id_state_value in cancel_image_generation_ids_object) and
         (image_generation_id_state_value in cancel_image_generation_ids_object[user_id_state_value])
@@ -3156,24 +3153,14 @@ def remove_from_cancel_object (
 
         cancel_image_generation_ids_object[user_id_state_value].remove(image_generation_id_state_value)
 
-    #print (len(cancel_image_generation_ids_object[user_id_state_value]))
-
     if len(cancel_image_generation_ids_object[user_id_state_value]) == 0:
 
         cancel_image_generation_ids_object.pop(user_id_state_value, None)
 
-    #print ("after1")
-    #print (cancel_image_generation_ids_object)
-    #print (cancel_image_generation_times_object)
-
     if image_generation_id_state_value in cancel_image_generation_times_object:
 
         cancel_image_generation_times_object.pop(image_generation_id_state_value, None)
 
-    #print ("after2")
-    #print (cancel_image_generation_ids_object)
-    #print (cancel_image_generation_times_object)
-
 
 
 
@@ -3384,6 +3371,7 @@ def create_image_function (
     base_model_steps_field_for_sdxl_turbo,
     actual_seed,
     add_seed_into_pipe,
+    use_torch_manual_seed_but_do_not_add_to_pipe_field,
 
     refining_selection_field_value,
     refining_denoise_start_field_value,
@@ -3421,6 +3409,10 @@ def create_image_function (
     image_generation_id_state_value = image_generation_id_state.value
     user_id_state_value = user_id_state.value
 
+    global current_image_generation_id_in_progress
+
+    current_image_generation_id_in_progress = image_generation_id_state_value
+
 
 
     global cancel_image_generation_ids_object
@@ -3434,19 +3426,6 @@ def create_image_function (
 
 
 
-
-
-
-#here
-
-    #print ("create_image_function ---", prompt_text)
-    #print ("image_generation_id_state_value: ", image_generation_id_state_value)
-    #print ("canceled_images_array_state: ", canceled_images_array_state)
-    #print ("user_id_state_value: ", user_id_state_value)
-    #print ("cancel_image_generation_ids_object: ", cancel_image_generation_ids_object)
-    #print ("cancel_image_generation_times_object: ", cancel_image_generation_times_object)
-    print ("-------------------------")
-
     if image_processing_is_canceled(user_id_state_value, image_generation_id_state_value):
 
         #    User likely canceled while waiting in queue
@@ -3554,6 +3533,7 @@ def create_image_function (
 
 
     add_seed_into_pipe = numerical_bool(add_seed_into_pipe)
+    use_torch_manual_seed_but_do_not_add_to_pipe_field = numerical_bool(use_torch_manual_seed_but_do_not_add_to_pipe_field)
 
 
 
@@ -3750,7 +3730,15 @@ def create_image_function (
 
 
 
-    if add_seed_into_pipe == 0:
+    if add_seed_into_pipe == 1:
+
+        generator = torch.manual_seed(actual_seed)
+
+    else:
+
+        if use_torch_manual_seed_but_do_not_add_to_pipe_field == 1:
+
+            torch.manual_seed(actual_seed)
 
         generator = None
 
@@ -3862,7 +3850,8 @@ def create_image_function (
             (
                 ((int(callback_step_index) % image_preview_step_interval) == 0) or
                 (seconds_per_step >= image_preview_seconds_interval)
-            )
+            ) and
+            (callback_step_number < current_estimated_total_base_model_steps)
         ):
 
             latents = callback_kwargs["latents"]
@@ -3871,6 +3860,16 @@ def create_image_function (
 
             model_to_use = base_model_name_value
 
+            is_final_image = 0
+
+            pil_image = create_image_from_latents(
+                model_to_use,
+                pipe,
+                latents,
+                generator,
+                is_final_image
+            )
+
             create_preview_image(
                 model_to_use,
                 user_id_state_value,
@@ -3902,7 +3901,10 @@ def create_image_function (
                 is_final_image
             )
 
-        if show_image_creation_progress_log == 1:
+        if (
+            (show_image_creation_progress_log == 1) and
+            (callback_step_number <= current_estimated_total_base_model_steps)
+        ):
 
             progress(
                 progress = (
@@ -3965,7 +3967,8 @@ def create_image_function (
                 (
                     ((int(callback_step_index) % image_preview_step_interval) == 0) or
                     (seconds_per_step >= image_preview_seconds_interval)
-                )
+                ) and
+                (callback_step_number < current_estimated_total_refiner_steps)
             ):
 
                 latents = callback_kwargs["latents"]
@@ -3983,7 +3986,10 @@ def create_image_function (
                     temporary_extra
                 )
 
-            if show_image_creation_progress_log == 1:
+            if (
+                (show_image_creation_progress_log == 1) and
+                (callback_step_number <= current_estimated_total_refiner_steps)
+            ):
 
                 progress(
                     progress = (
@@ -4043,7 +4049,8 @@ def create_image_function (
                 (
                     ((int(callback_step_index) % image_preview_step_interval) == 0) or
                     (seconds_per_step >= image_preview_seconds_interval)
-                )
+                ) and
+                (callback_step_number < current_estimated_total_upscaler_steps)
             ):
 
                 latents = callback_latents
@@ -4061,7 +4068,10 @@ def create_image_function (
                     temporary_extra
                 )
 
-            if show_image_creation_progress_log == 1:
+            if (
+                (show_image_creation_progress_log == 1) and
+                (callback_step_number <= current_estimated_total_upscaler_steps)
+            ):
 
                 progress(
                     progress = (
@@ -4104,10 +4114,6 @@ def create_image_function (
 
 
 
-    generator = torch.manual_seed(actual_seed)
-
-
-
     if image_processing_is_canceled(user_id_state_value, image_generation_id_state_value):
 
         if show_messages_in_command_prompt == 1:
@@ -4686,14 +4692,13 @@ def create_image_function (
 
 #####################
 #
-#    Cancel Image In Queue Function
+#    Cancel Image Function
 #
 #        Image generation has not yet started and we need to cancel it.
 #
 #####################
 
-def cancel_image_in_queue_function(
-    confirm_cancel_image_field_value,
+def cancel_image_function(
     user_id_state,
     image_generation_id_state
 ):
@@ -4701,22 +4706,6 @@ def cancel_image_in_queue_function(
     user_id_state_value = user_id_state.value
     image_generation_id_state_value = image_generation_id_state.value
 
-    confirm_cancel_image_field_value = numerical_bool(confirm_cancel_image_field_value)
-
-    #print ("confirm_cancel_image_field_value: ", confirm_cancel_image_field_value)
-
-    if confirm_cancel_image_field_value == 0:
-
-        #    User has not confirmed cancellation
-
-        confirm_cancel_image_field_row_update = gr.Row(
-            visible = True
-        )
-
-        return {
-            confirm_cancel_image_field_row: confirm_cancel_image_field_row_update
-        }
-
 
 
     global image_generation_ids_object
@@ -4729,155 +4718,90 @@ def cancel_image_in_queue_function(
     cancel_image_generation_ids_object[user_id_state_value].append(image_generation_id_state_value) 
     cancel_image_generation_times_object[image_generation_id_state_value] = time.time()
 
-    generate_image_button_row_update = gr.Row(
-        visible = True
-    )
-
-    generate_image_button_update = gr.Button(
-        value = generate_image_button_normal_text,
-        variant = "primary",
-        interactive = True
-    )
-
-    output_text_field_update = gr.Textbox(
-        visible = True
-    )
 
-    output_image_preview_field_row_update = gr.Row(
-        visible = False
-    )
 
-    cancel_image_buttons_group_update = gr.Group(
-        visible = False
-    )
-
-    cancel_image_in_queue_button_update = gr.Button(
-        value = cancel_image_in_queue_button_text,
-        interactive = False
-    )
-
-    cancel_image_in_progress_button_update = gr.Button(
-        value = cancel_image_in_progress_button_normal_text,
+    cancel_image_button_update = gr.Button(
+        value = cancel_image_button_in_progress_text,
         interactive = False
     )
 
-    cancel_image_in_progress_message_field_row_update = gr.Row(
-        visible = False
-    )
-
-    confirm_cancel_image_field_row_update = gr.Row(
-        visible = False
-    )
-
-    confirm_cancel_image_field_update = gr.Checkbox(
-        value = 0
+    cancel_image_message_field_row_update = gr.Row(
+        visible = True
     )
 
+    cancel_image_object = {}
 
+    if image_generation_id_state_value == current_image_generation_id_in_progress:
 
-    return {
-        generate_image_button_row: generate_image_button_row_update,
-        generate_image_button: generate_image_button_update,
-        output_text_field: output_text_field_update,
-        output_image_preview_field_row: output_image_preview_field_row_update,
-        cancel_image_buttons_group: cancel_image_buttons_group_update,
-        cancel_image_in_queue_button: cancel_image_in_queue_button_update,
-        cancel_image_in_progress_button: cancel_image_in_progress_button_update,
-        cancel_image_in_progress_message_field_row: cancel_image_in_progress_message_field_row_update,
-        confirm_cancel_image_field_row: confirm_cancel_image_field_row_update,
-        confirm_cancel_image_field: confirm_cancel_image_field_update
-    }
+        #    If they cancel the image that is currently being generated, we will
+        #    stop it after the next step is complete and return the image to
+        #    them. They will not need to reload the page again to create another
+        #    image.
 
+        cancel_image_message_field_html = canceled_image_in_process_of_being_generated
 
 
 
+        show_message("Your image generation is being canceled. After the current step in the process is complete, the cancellation will be complete.")
 
 
 
-#####################
-#
-#    Cancel Image In Progress Function
-#
-#        Image generation has already started and we need to cancel it.
-#
-#####################
+        generate_image_button_row_update = gr.Row(
+            visible = False
+        )
 
-def cancel_image_in_progress_function(
-    confirm_cancel_image_field_value,
-    user_id_state,
-    image_generation_id_state
-):
+        cancel_image_object.update({
+            generate_image_button_row: generate_image_button_row_update,
+            cancel_image_message_field_row: cancel_image_message_field_row_update
+        })
 
-    user_id_state_value = user_id_state.value
-    image_generation_id_state_value = image_generation_id_state.value
+    else:
 
-    confirm_cancel_image_field_value = numerical_bool(confirm_cancel_image_field_value)
+        #    If they cancel there place in the queue, we have to make them
+        #    reload the page if they want to generate another image.
 
-    if confirm_cancel_image_field_value == 0:
+        cancel_image_message_field_html = canceled_image_in_queue_message
 
-        #    User has not confirmed cancellation
+        generate_image_button_update = gr.Button(
+            value = generate_image_button_normal_text,
+            interactive = False
+        )
 
-        confirm_cancel_image_field_row_update = gr.Row(
+        output_text_field_update = gr.Textbox(
             visible = True
         )
 
-        return {
-            confirm_cancel_image_field_row: confirm_cancel_image_field_row_update
-        }
-
-
-
-    show_message("Your image generation is being canceled. After the current step in the process is complete, the cancellation will be complete.")
-
-
-
-    #    We need to save this cancellation to an object that we check. We save
-    #    the time as the cancellation might be applied later in the queue and
-    #    there may have been multiple cancellations by others. We will remove
-    #    older cancellations eventually from it by checking the time.
-
-
-
-    global image_generation_ids_object
-    global cancel_image_generation_times_object
-
-    if (user_id_state_value not in cancel_image_generation_ids_object):
-
-        cancel_image_generation_ids_object[user_id_state_value] = []
+        output_image_preview_field_row_update = gr.Row(
+            visible = False
+        )
 
-    cancel_image_generation_ids_object[user_id_state_value].append(image_generation_id_state_value) 
-    cancel_image_generation_times_object[image_generation_id_state_value] = time.time()
+        cancel_image_button_row_update = gr.Row(
+            visible = False
+        )
 
+        cancel_image_object.update({
+            generate_image_button: generate_image_button_update,
+            output_text_field: output_text_field_update,
+            output_image_preview_field_row: output_image_preview_field_row_update,
+            cancel_image_button_row: cancel_image_button_row_update,
+            cancel_image_message_field_row: cancel_image_message_field_row_update
+        })
 
 
-    generate_image_button_row_update = gr.Row(
-        visible = False
-    )
 
-    cancel_image_in_progress_button_update = gr.Button(
-        value = "Cancelling...",
-        interactive = False
+    cancel_image_message_field_update = gr.Button(
+        value = cancel_image_message_field_html
     )
 
-    cancel_image_in_progress_message_field_row_update = gr.Row(
-        visible = True
-    )
+    cancel_image_object.update({
+        cancel_image_button: cancel_image_button_update,
+        cancel_image_message_field_row: cancel_image_message_field_row_update,
+        cancel_image_message_field: cancel_image_message_field_update
+    })
 
-    confirm_cancel_image_field_update = gr.Checkbox(
-        value = 0
-    )
 
-    confirm_cancel_image_field_row_update = gr.Row(
-        visible = False
-    )
 
-    return {
-        generate_image_button_row: generate_image_button_row_update,
-        cancel_image_in_progress_button: cancel_image_in_progress_button_update,
-        confirm_cancel_image_field_row: confirm_cancel_image_field_row_update,
-        confirm_cancel_image_field: confirm_cancel_image_field_update,
-        cancel_image_in_progress_message_field_row: cancel_image_in_progress_message_field_row_update
-    }
+    return cancel_image_object
 
 
 
@@ -5223,6 +5147,8 @@ def get_query_params(
 
     add_seed_key_in_url = "add_seed"
 
+    add_seed_to_generation = None
+
     if add_seed_key_in_url in url_object:
 
         add_seed_in_url = url_object[add_seed_key_in_url].lower()
@@ -5242,6 +5168,34 @@ def get_query_params(
 
 
 
+    use_torch_manual_seed_but_not_in_generator_key_in_url = "use_torch_manual_seed_but_not_in_generator"
+
+    if use_torch_manual_seed_but_not_in_generator_key_in_url in url_object:
+
+        use_torch_manual_seed_but_not_in_generator_in_url = url_object[use_torch_manual_seed_but_not_in_generator_key_in_url].lower()
+
+        use_torch_manual_seed_but_not_in_generator_to_generation = False
+
+        if (
+            (use_torch_manual_seed_but_not_in_generator_in_url == "1") or
+            (use_torch_manual_seed_but_not_in_generator_in_url == "y") or
+            (use_torch_manual_seed_but_not_in_generator_in_url == "yes") or
+            (use_torch_manual_seed_but_not_in_generator_in_url == "true")
+        ):
+
+            use_torch_manual_seed_but_not_in_generator_to_generation = True
+
+        if (
+            add_seed_to_generation and
+            add_seed_to_generation == True
+        ):
+
+            use_torch_manual_seed_but_not_in_generator_to_generation = False
+
+        field_object.update({use_torch_manual_seed_but_do_not_add_to_pipe_field: use_torch_manual_seed_but_not_in_generator_to_generation})
+
+
+
     refiner_key_in_url = "refiner"
 
     if refiner_key_in_url in url_object:
@@ -5600,49 +5554,22 @@ with gr.Blocks(
                     interactive = False
                 )
 
-            with gr.Group(
+            with gr.Row(
                 visible = False
-            ) as cancel_image_buttons_group:
-
-                with gr.Row(
-                    elem_id = "cancel_image_in_queue_button_row_id",
-                    visible = True
-                ):
-
-                    cancel_image_in_queue_button = gr.Button(
-                        value = cancel_image_in_queue_button_text,
-                        variant = "stop",
-                        interactive = False
-                    )
-
-                with gr.Row(
-                    elem_id = "cancel_image_in_progress_button_row_id",
-                    visible = True
-                ):
-
-                    cancel_image_in_progress_button = gr.Button(
-                        value = cancel_image_in_progress_button_normal_text,
-                        variant = "stop",
-                        interactive = False
-                    )
-
-                with gr.Row(
-                    visible = False
-                ) as confirm_cancel_image_field_row:
+            ) as cancel_image_button_row:
 
-                    confirm_cancel_image_field = gr.Checkbox(
-                        label = "Check to confirm & click button again",
-                        value = 0,
-                        interactive = True,
-                        container = True
-                    )
+                cancel_image_button = gr.Button(
+                    value = cancel_image_button_text,
+                    variant = "stop",
+                    interactive = False
+                )
 
             with gr.Row(
                 visible = False
-            ) as cancel_image_in_progress_message_field_row:
+            ) as cancel_image_message_field_row:
 
                 cancel_image_message_field = gr.HTML(
-                    value = "<div style=\"text-align: center;\">Image generation will be canceled once the current step completes.</div>"
+                    value = ""
                 )
 
             with gr.Group():
@@ -6058,8 +5985,16 @@ with gr.Blocks(
                 visible = False
             ) as output_image_preview_field_row:
 
+                output_image_preview_field_every_value = None
+
+                if enable_image_preview == 1:
+
+                    output_image_preview_field_every_value = load_image_preview_frequency_in_seconds
+
                 output_image_preview_field = gr.Image(
                     elem_id = "image_preview_id",
+#                    value = load_image_preview(user_id_state),
+#                    every = output_image_preview_field_every_value,
                     label = "Preview",
                     type = "pil",
                     interactive = False,
@@ -6162,6 +6097,16 @@ with gr.Blocks(
                 elem_classes = "sp_checkbox"
             )
 
+        with gr.Row():
+
+            use_torch_manual_seed_but_do_not_add_to_pipe_field = gr.Checkbox(
+                label = "Use torch.manual_seed, but don't actually add seed to generation (ignored if \"Add seed to generation\" is checked. This is to maintain compatibility with PhotoReal site)",
+                value = default_use_torch_manual_seed_but_do_not_add_to_pipe_is_selected,
+                interactive = True,
+                container = False,
+                elem_classes = "sp_checkbox"
+            )
+
         with gr.Row():
 
             save_or_display_word_text_for_save_base_image = "Display"
@@ -6529,6 +6474,7 @@ async (
         base_model_steps_field_for_sdxl_turbo_field,
         seed_field,
         add_seed_into_pipe_field,
+        use_torch_manual_seed_but_do_not_add_to_pipe_field,
 
         refining_selection_field,
         refining_denoise_start_field,
@@ -6579,11 +6525,10 @@ async (
             prompt_truncated_field,
             negative_prompt_truncated_field_group,
             negative_prompt_truncated_field,
-            cancel_image_buttons_group,
-            confirm_cancel_image_field,
-            cancel_image_in_queue_button,
-            cancel_image_in_progress_button,
-            cancel_image_in_progress_message_field_row,
+            cancel_image_button_row,
+            cancel_image_button,
+            cancel_image_message_field_row,
+            cancel_image_message_field,
             error_text_field,
             image_generation_id_state
         ],
@@ -6620,12 +6565,10 @@ async (
             output_text_field,
             output_image_preview_field_row,
             generate_image_button_row,
-            cancel_image_buttons_group,
-            confirm_cancel_image_field_row,
-            confirm_cancel_image_field,
-            cancel_image_in_queue_button,
-            cancel_image_in_progress_button,
-            cancel_image_in_progress_message_field_row
+            cancel_image_button_row,
+            cancel_image_button,
+            cancel_image_message_field_row,
+            cancel_image_message_field
         ],
         show_progress = "hidden",
         queue = True
@@ -6688,50 +6631,25 @@ async (
 
 
 
-        cancel_image_in_queue_click_event = cancel_image_in_queue_button.click(
-            fn = cancel_image_in_queue_function,
+        cancel_image_click_event = cancel_image_button.click(
+            fn = cancel_image_function,
             inputs = [
-                confirm_cancel_image_field,
                 user_id_state,
                 image_generation_id_state
             ],
             outputs = [
+                generate_image_button_row,
                 generate_image_button,
-                output_image_field,
-                output_image_gallery_field,
                 output_text_field,
                 output_image_preview_field_row,
-                generate_image_button_row,
-                cancel_image_buttons_group,
-                confirm_cancel_image_field_row,
-                confirm_cancel_image_field,
-                cancel_image_in_queue_button,
-                cancel_image_in_progress_button,
-                cancel_image_in_progress_message_field_row
+                cancel_image_button_row,
+                cancel_image_button,
+                cancel_image_message_field_row,
+                cancel_image_message_field
             ],
             show_progress = "hidden",
-            cancels = generate_image_button_click_event,
-            queue = False
-        )
-
-
-
-        cancel_image_in_progress_click_event = cancel_image_in_progress_button.click(
-            fn = cancel_image_in_progress_function,
-            inputs = [
-                confirm_cancel_image_field,
-                user_id_state,
-                image_generation_id_state
-            ],
-            outputs = [
-                generate_image_button_row,
-                cancel_image_in_progress_button,
-                confirm_cancel_image_field_row,
-                confirm_cancel_image_field,
-                cancel_image_in_progress_message_field_row
-            ],
-            show_progress = "hidden",
-            queue = False
+            cancels = [generate_image_button_click_event],
+            queue = True
         )