From ba05e327896898eb73caec3ed710fe45d1e38732 Mon Sep 17 00:00:00 2001
From: w-e-w <40751091+w-e-w@users.noreply.github.com>
Date: Sat, 2 Sep 2023 14:12:59 +0900
Subject: update cmd arg description

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

(limited to 'modules/cmd_args.py')

diff --git a/modules/cmd_args.py b/modules/cmd_args.py
index aab62286..a77c7e77 100644
--- a/modules/cmd_args.py
+++ b/modules/cmd_args.py
@@ -112,8 +112,8 @@ parser.add_argument("--skip-version-check", action='store_true', help="Do not ch
 parser.add_argument("--no-hashing", action='store_true', help="disable sha256 hashing of checkpoints to help loading performance", default=False)
 parser.add_argument("--no-download-sd-model", action='store_true', help="don't download SD1.5 model even if no model is found in --ckpt-dir", default=False)
 parser.add_argument('--subpath', type=str, help='customize the subpath for gradio, use with reverse proxy')
-parser.add_argument('--add-stop-route', action='store_true', help='add /_stop route to stop server')
+parser.add_argument('--add-stop-route', action='store_true', help='does not do anything')
 parser.add_argument('--api-server-stop', action='store_true', help='enable server stop/restart/kill via api')
 parser.add_argument('--timeout-keep-alive', type=int, default=30, help='set timeout_keep_alive for uvicorn')
 parser.add_argument("--disable-all-extensions", action='store_true', help="prevent all extensions from running regardless of any other settings", default=False)
-parser.add_argument("--disable-extra-extensions", action='store_true', help=" prevent all extensions except built-in from running regardless of any other settings", default=False)
+parser.add_argument("--disable-extra-extensions", action='store_true', help="prevent all extensions except built-in from running regardless of any other settings", default=False)
-- 
cgit v1.2.3


From 46ef1857098df7610c36e73903731e486feca927 Mon Sep 17 00:00:00 2001
From: w-e-w <40751091+w-e-w@users.noreply.github.com>
Date: Sat, 9 Sep 2023 15:53:10 +0900
Subject: deprecate --enable-console-prompts

use --enable-console-prompts as the default value for shared.opts.enable_console_prompts
---
 modules/cmd_args.py       | 2 +-
 modules/img2img.py        | 2 +-
 modules/shared_options.py | 2 +-
 modules/txt2img.py        | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'modules/cmd_args.py')

diff --git a/modules/cmd_args.py b/modules/cmd_args.py
index aab62286..fe4d4ecc 100644
--- a/modules/cmd_args.py
+++ b/modules/cmd_args.py
@@ -90,7 +90,7 @@ parser.add_argument("--autolaunch", action='store_true', help="open the webui UR
 parser.add_argument("--theme", type=str, help="launches the UI with light or dark theme", default=None)
 parser.add_argument("--use-textbox-seed", action='store_true', help="use textbox for seeds in UI (no up/down, but possible to input long seeds)", default=False)
 parser.add_argument("--disable-console-progressbars", action='store_true', help="do not output progressbars to console", default=False)
-parser.add_argument("--enable-console-prompts", action='store_true', help="print prompts to console when generating with txt2img and img2img", default=False)
+parser.add_argument("--enable-console-prompts", action='store_true', help="does not do anything", default=False)  # Legacy compatibility, use as default value shared.opts.enable_console_prompts
 parser.add_argument('--vae-path', type=str, help='Checkpoint to use as VAE; setting this argument disables all settings related to VAE', default=None)
 parser.add_argument("--disable-safe-unpickle", action='store_true', help="disable checking pytorch models for malicious code", default=False)
 parser.add_argument("--api", action='store_true', help="use api=True to launch the API together with the webui (use --nowebui instead for only the API)")
diff --git a/modules/img2img.py b/modules/img2img.py
index cbd80bac..72ee7bc2 100644
--- a/modules/img2img.py
+++ b/modules/img2img.py
@@ -199,7 +199,7 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
 
     p.user = request.username
 
-    if shared.opts.enable_console_prompts or shared.cmd_opts.enable_console_prompts:
+    if shared.opts.enable_console_prompts:
         print(f"\nimg2img: {prompt}", file=shared.progress_print_out)
 
     if mask:
diff --git a/modules/shared_options.py b/modules/shared_options.py
index 44fb1670..1ea5c8f8 100644
--- a/modules/shared_options.py
+++ b/modules/shared_options.py
@@ -100,7 +100,7 @@ options_templates.update(options_section(('face-restoration', "Face restoration"
 
 options_templates.update(options_section(('system', "System"), {
     "auto_launch_browser": OptionInfo("Local", "Automatically open webui in browser on startup", gr.Radio, lambda: {"choices": ["Disable", "Local", "Remote"]}),
-    "enable_console_prompts": OptionInfo(False, "Print prompts to console when generating with txt2img and img2img."),
+    "enable_console_prompts": OptionInfo(shared.cmd_opts.enable_console_prompts, "Print prompts to console when generating with txt2img and img2img."),
     "show_warnings": OptionInfo(False, "Show warnings in console.").needs_reload_ui(),
     "show_gradio_deprecation_warnings": OptionInfo(True, "Show gradio deprecation warnings in console.").needs_reload_ui(),
     "memmon_poll_rate": OptionInfo(8, "VRAM usage polls per second during generation.", gr.Slider, {"minimum": 0, "maximum": 40, "step": 1}).info("0 = disable"),
diff --git a/modules/txt2img.py b/modules/txt2img.py
index 379ef859..721206dd 100644
--- a/modules/txt2img.py
+++ b/modules/txt2img.py
@@ -45,7 +45,7 @@ def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, step
 
     p.user = request.username
 
-    if shared.opts.enable_console_prompts or cmd_opts.enable_console_prompts:
+    if shared.opts.enable_console_prompts:
         print(f"\ntxt2img: {prompt}", file=shared.progress_print_out)
 
     with closing(p):
-- 
cgit v1.2.3


From ab3d3528a18ea1a81f1af22ea71bfc0d8c710dde Mon Sep 17 00:00:00 2001
From: Leon <yongliang.zhao@happyelements.com>
Date: Thu, 14 Sep 2023 18:42:56 +0800
Subject: add --skip-load-model-at-start

---
 modules/cmd_args.py   | 1 +
 modules/initialize.py | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'modules/cmd_args.py')

diff --git a/modules/cmd_args.py b/modules/cmd_args.py
index 5be879dd..4e602a84 100644
--- a/modules/cmd_args.py
+++ b/modules/cmd_args.py
@@ -117,3 +117,4 @@ parser.add_argument('--api-server-stop', action='store_true', help='enable serve
 parser.add_argument('--timeout-keep-alive', type=int, default=30, help='set timeout_keep_alive for uvicorn')
 parser.add_argument("--disable-all-extensions", action='store_true', help="prevent all extensions from running regardless of any other settings", default=False)
 parser.add_argument("--disable-extra-extensions", action='store_true', help="prevent all extensions except built-in from running regardless of any other settings", default=False)
+parser.add_argument("--skip-load-model-at-start", action='store_true', help="if load a model at web start, only take effect when --nowebui", )
diff --git a/modules/initialize.py b/modules/initialize.py
index f24f7637..ac95fc6f 100644
--- a/modules/initialize.py
+++ b/modules/initialize.py
@@ -151,8 +151,8 @@ def initialize_rest(*, reload_script_modules=False):
 
         from modules import devices
         devices.first_time_calculation()
-
-    Thread(target=load_model).start()
+    if not shared.cmd_opts.skip_load_model_at_start:
+        Thread(target=load_model).start()
 
     from modules import shared_items
     shared_items.reload_hypernetworks()
-- 
cgit v1.2.3


From 2b06cefe66684ed2648d3221efbc36aeaae99a2f Mon Sep 17 00:00:00 2001
From: gibiee <37574274+gibiee@users.noreply.github.com>
Date: Sun, 5 Nov 2023 11:37:23 +0900
Subject: correct a typo

modify "defaul" to "default"
---
 modules/cmd_args.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'modules/cmd_args.py')

diff --git a/modules/cmd_args.py b/modules/cmd_args.py
index 4e602a84..a9fb9bfa 100644
--- a/modules/cmd_args.py
+++ b/modules/cmd_args.py
@@ -107,7 +107,7 @@ parser.add_argument("--tls-certfile", type=str, help="Partially enables TLS, req
 parser.add_argument("--disable-tls-verify", action="store_false", help="When passed, enables the use of self-signed certificates.", default=None)
 parser.add_argument("--server-name", type=str, help="Sets hostname of server", default=None)
 parser.add_argument("--gradio-queue", action='store_true', help="does not do anything", default=True)
-parser.add_argument("--no-gradio-queue", action='store_true', help="Disables gradio queue; causes the webpage to use http requests instead of websockets; was the defaul in earlier versions")
+parser.add_argument("--no-gradio-queue", action='store_true', help="Disables gradio queue; causes the webpage to use http requests instead of websockets; was the default in earlier versions")
 parser.add_argument("--skip-version-check", action='store_true', help="Do not check versions of torch and xformers")
 parser.add_argument("--no-hashing", action='store_true', help="disable sha256 hashing of checkpoints to help loading performance", default=False)
 parser.add_argument("--no-download-sd-model", action='store_true', help="don't download SD1.5 model even if no model is found in --ckpt-dir", default=False)
-- 
cgit v1.2.3


From 7499148ad4dbd3444215c843d02453f68c459707 Mon Sep 17 00:00:00 2001
From: Nuullll <vfirst218@gmail.com>
Date: Sat, 2 Dec 2023 14:00:46 +0800
Subject: Disable ipex autocast due to its bad perf

---
 modules/cmd_args.py     |  1 +
 modules/devices.py      | 20 +++++++++++++-------
 modules/xpu_specific.py | 28 ++++++++++++++++++----------
 webui-ipex-user.bat     | 19 +++++++++++++++++++
 4 files changed, 51 insertions(+), 17 deletions(-)
 create mode 100644 webui-ipex-user.bat

(limited to 'modules/cmd_args.py')

diff --git a/modules/cmd_args.py b/modules/cmd_args.py
index a9fb9bfa..da93eb26 100644
--- a/modules/cmd_args.py
+++ b/modules/cmd_args.py
@@ -70,6 +70,7 @@ parser.add_argument("--opt-sdp-no-mem-attention", action='store_true', help="pre
 parser.add_argument("--disable-opt-split-attention", action='store_true', help="prefer no cross-attention layer optimization for automatic choice of optimization")
 parser.add_argument("--disable-nan-check", action='store_true', help="do not check if produced images/latent spaces have nans; useful for running without a checkpoint in CI")
 parser.add_argument("--use-cpu", nargs='+', help="use CPU as torch device for specified modules", default=[], type=str.lower)
+parser.add_argument("--use-ipex", action="store_true", help="use Intel XPU as torch device")
 parser.add_argument("--disable-model-loading-ram-optimization", action='store_true', help="disable an optimization that reduces RAM use when loading a model")
 parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
 parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)
diff --git a/modules/devices.py b/modules/devices.py
index be599736..37ecca78 100644
--- a/modules/devices.py
+++ b/modules/devices.py
@@ -3,11 +3,18 @@ import contextlib
 from functools import lru_cache
 
 import torch
-from modules import errors, shared, xpu_specific
+from modules import errors, shared
 
 if sys.platform == "darwin":
     from modules import mac_specific
 
+if shared.cmd_opts.use_ipex:
+    from modules import xpu_specific
+
+
+def has_xpu() -> bool:
+    return shared.cmd_opts.use_ipex and xpu_specific.has_xpu
+
 
 def has_mps() -> bool:
     if sys.platform != "darwin":
@@ -30,7 +37,7 @@ def get_optimal_device_name():
     if has_mps():
         return "mps"
 
-    if xpu_specific.has_ipex:
+    if has_xpu():
         return xpu_specific.get_xpu_device_string()
 
     return "cpu"
@@ -57,6 +64,9 @@ def torch_gc():
     if has_mps():
         mac_specific.torch_mps_gc()
 
+    if has_xpu():
+        xpu_specific.torch_xpu_gc()
+
 
 def enable_tf32():
     if torch.cuda.is_available():
@@ -103,15 +113,11 @@ def autocast(disable=False):
     if dtype == torch.float32 or shared.cmd_opts.precision == "full":
         return contextlib.nullcontext()
 
-    if xpu_specific.has_xpu:
-        return torch.autocast("xpu")
-
     return torch.autocast("cuda")
 
 
 def without_autocast(disable=False):
-    device_type = "xpu" if xpu_specific.has_xpu else "cuda"
-    return torch.autocast(device_type, enabled=False) if torch.is_autocast_enabled() and not disable else contextlib.nullcontext()
+    return torch.autocast("cuda", enabled=False) if torch.is_autocast_enabled() and not disable else contextlib.nullcontext()
 
 
 class NansException(Exception):
diff --git a/modules/xpu_specific.py b/modules/xpu_specific.py
index 6417dd2d..2df68665 100644
--- a/modules/xpu_specific.py
+++ b/modules/xpu_specific.py
@@ -1,4 +1,3 @@
-import contextlib
 from modules import shared
 from modules.sd_hijack_utils import CondFunc
 
@@ -10,33 +9,42 @@ try:
 except Exception:
     pass
 
-def check_for_xpu():
-    if not has_ipex:
-        return False
 
-    return hasattr(torch, 'xpu') and torch.xpu.is_available()
+def check_for_xpu():
+    return has_ipex and hasattr(torch, 'xpu') and torch.xpu.is_available()
 
-has_xpu = check_for_xpu()
 
 def get_xpu_device_string():
     if shared.cmd_opts.device_id is not None:
         return f"xpu:{shared.cmd_opts.device_id}"
     return "xpu"
 
-def return_null_context(*args, **kwargs): # pylint: disable=unused-argument
-    return contextlib.nullcontext()
+
+def torch_xpu_gc():
+    with torch.xpu.device(get_xpu_device_string()):
+        torch.xpu.empty_cache()
+
+
+has_xpu = check_for_xpu()
 
 if has_xpu:
+    # W/A for https://github.com/intel/intel-extension-for-pytorch/issues/452: torch.Generator API doesn't support XPU device
     CondFunc('torch.Generator',
         lambda orig_func, device=None: torch.xpu.Generator(device),
-        lambda orig_func, device=None: device is not None and device != torch.device("cpu") and device != "cpu")
+        lambda orig_func, device=None: device is not None and device.type == "xpu")
 
+    # W/A for some OPs that could not handle different input dtypes
     CondFunc('torch.nn.functional.layer_norm',
         lambda orig_func, input, normalized_shape=None, weight=None, *args, **kwargs:
         orig_func(input.to(weight.data.dtype), normalized_shape, weight, *args, **kwargs),
         lambda orig_func, input, normalized_shape=None, weight=None, *args, **kwargs:
         weight is not None and input.dtype != weight.data.dtype)
-
     CondFunc('torch.nn.modules.GroupNorm.forward',
         lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
         lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
+    CondFunc('torch.nn.modules.linear.Linear.forward',
+        lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
+        lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
+    CondFunc('torch.nn.modules.conv.Conv2d.forward',
+        lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
+        lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
diff --git a/webui-ipex-user.bat b/webui-ipex-user.bat
new file mode 100644
index 00000000..ab25a040
--- /dev/null
+++ b/webui-ipex-user.bat
@@ -0,0 +1,19 @@
+@echo off
+
+set PYTHON=
+@REM The "Nuullll/intel-extension-for-pytorch" wheels were built from IPEX source for Intel Arc GPU: https://github.com/intel/intel-extension-for-pytorch/tree/xpu-main
+@REM This is NOT an Intel official release so please use it at your own risk!!
+@REM See https://github.com/Nuullll/intel-extension-for-pytorch/releases/tag/v2.0.110%2Bxpu-master%2Bdll-bundle for details.
+@REM 
+@REM Strengths (over official IPEX 2.0.110 windows release):
+@REM   - AOT build (for Arc GPU only) to eliminate JIT compilation overhead: https://github.com/intel/intel-extension-for-pytorch/issues/399
+@REM   - Bundles minimal oneAPI 2023.2 dependencies into the python wheels, so users don't need to install oneAPI for the whole system.
+@REM   - Provides a compatible torchvision wheel: https://github.com/intel/intel-extension-for-pytorch/issues/465
+@REM Limitation:
+@REM   - Only works for python 3.10
+set "TORCH_COMMAND=pip install https://github.com/Nuullll/intel-extension-for-pytorch/releases/download/v2.0.110%%2Bxpu-master%%2Bdll-bundle/torch-2.0.0a0+gite9ebda2-cp310-cp310-win_amd64.whl https://github.com/Nuullll/intel-extension-for-pytorch/releases/download/v2.0.110%%2Bxpu-master%%2Bdll-bundle/torchvision-0.15.2a0+fa99a53-cp310-cp310-win_amd64.whl https://github.com/Nuullll/intel-extension-for-pytorch/releases/download/v2.0.110%%2Bxpu-master%%2Bdll-bundle/intel_extension_for_pytorch-2.0.110+gitc6ea20b-cp310-cp310-win_amd64.whl"
+set GIT=
+set VENV_DIR=
+set "COMMANDLINE_ARGS=--use-ipex --skip-torch-cuda-test --skip-version-check --opt-sdp-attention"
+
+call webui.bat
-- 
cgit v1.2.3