aboutsummaryrefslogtreecommitdiff
path: root/modules
diff options
context:
space:
mode:
Diffstat (limited to 'modules')
-rw-r--r--modules/api/api.py105
-rw-r--r--modules/api/models.py4
-rw-r--r--modules/devices.py60
-rw-r--r--modules/errors.py4
-rw-r--r--modules/generation_parameters_copypaste.py91
-rw-r--r--modules/images.py1
-rw-r--r--modules/initialize_util.py2
-rw-r--r--modules/launch_utils.py6
-rw-r--r--modules/paths_internal.py1
-rw-r--r--modules/processing.py102
-rw-r--r--modules/processing_scripts/refiner.py7
-rw-r--r--modules/processing_scripts/seed.py13
-rw-r--r--modules/progress.py22
-rw-r--r--modules/scripts.py70
-rw-r--r--modules/sd_models.py49
-rw-r--r--modules/sd_models_xl.py2
-rw-r--r--modules/sd_samplers_cfg_denoiser.py21
-rw-r--r--modules/shared_options.py21
-rw-r--r--modules/ui.py46
-rw-r--r--modules/ui_gradio_extensions.py11
-rw-r--r--modules/ui_toprow.py4
-rw-r--r--modules/util.py12
22 files changed, 533 insertions, 121 deletions
diff --git a/modules/api/api.py b/modules/api/api.py
index b3d74e51..2918f785 100644
--- a/modules/api/api.py
+++ b/modules/api/api.py
@@ -31,7 +31,7 @@ from typing import Any
import piexif
import piexif.helper
from contextlib import closing
-
+from modules.progress import create_task_id, add_task_to_queue, start_task, finish_task, current_task
def script_name_to_index(name, scripts):
try:
@@ -312,8 +312,13 @@ class Api:
script_args[script.args_from:script.args_to] = ui_default_values
return script_args
- def init_script_args(self, request, default_script_args, selectable_scripts, selectable_idx, script_runner):
+ def init_script_args(self, request, default_script_args, selectable_scripts, selectable_idx, script_runner, *, input_script_args=None):
script_args = default_script_args.copy()
+
+ if input_script_args is not None:
+ for index, value in input_script_args.items():
+ script_args[index] = value
+
# position 0 in script_arg is the idx+1 of the selectable script that is going to be run when using scripts.scripts_*2img.run()
if selectable_scripts:
script_args[selectable_scripts.args_from:selectable_scripts.args_to] = request.script_args
@@ -335,11 +340,86 @@ class Api:
script_args[alwayson_script.args_from + idx] = request.alwayson_scripts[alwayson_script_name]["args"][idx]
return script_args
+ def apply_infotext(self, request, tabname, *, script_runner=None, mentioned_script_args=None):
+ """Processes `infotext` field from the `request`, and sets other fields of the `request` accoring to what's in infotext.
+
+ If request already has a field set, and that field is encountered in infotext too, the value from infotext is ignored.
+
+ Additionally, fills `mentioned_script_args` dict with index: value pairs for script arguments read from infotext.
+ """
+
+ if not request.infotext:
+ return {}
+
+ possible_fields = generation_parameters_copypaste.paste_fields[tabname]["fields"]
+ set_fields = request.model_dump(exclude_unset=True) if hasattr(request, "request") else request.dict(exclude_unset=True) # pydantic v1/v2 have differenrt names for this
+ params = generation_parameters_copypaste.parse_generation_parameters(request.infotext)
+
+ def get_field_value(field, params):
+ value = field.function(params) if field.function else params.get(field.label)
+ if value is None:
+ return None
+
+ if field.api in request.__fields__:
+ target_type = request.__fields__[field.api].type_
+ else:
+ target_type = type(field.component.value)
+
+ if target_type == type(None):
+ return None
+
+ if isinstance(value, dict) and value.get('__type__') == 'generic_update': # this is a gradio.update rather than a value
+ value = value.get('value')
+
+ if value is not None and not isinstance(value, target_type):
+ value = target_type(value)
+
+ return value
+
+ for field in possible_fields:
+ if not field.api:
+ continue
+
+ if field.api in set_fields:
+ continue
+
+ value = get_field_value(field, params)
+ if value is not None:
+ setattr(request, field.api, value)
+
+ if request.override_settings is None:
+ request.override_settings = {}
+
+ overriden_settings = generation_parameters_copypaste.get_override_settings(params)
+ for _, setting_name, value in overriden_settings:
+ if setting_name not in request.override_settings:
+ request.override_settings[setting_name] = value
+
+ if script_runner is not None and mentioned_script_args is not None:
+ indexes = {v: i for i, v in enumerate(script_runner.inputs)}
+ script_fields = ((field, indexes[field.component]) for field in possible_fields if field.component in indexes)
+
+ for field, index in script_fields:
+ value = get_field_value(field, params)
+
+ if value is None:
+ continue
+
+ mentioned_script_args[index] = value
+
+ return params
+
def text2imgapi(self, txt2imgreq: models.StableDiffusionTxt2ImgProcessingAPI):
+ task_id = txt2imgreq.force_task_id or create_task_id("txt2img")
+
script_runner = scripts.scripts_txt2img
if not script_runner.scripts:
script_runner.initialize_scripts(False)
ui.create_ui()
+
+ infotext_script_args = {}
+ self.apply_infotext(txt2imgreq, "txt2img", script_runner=script_runner, mentioned_script_args=infotext_script_args)
+
if not self.default_script_arg_txt2img:
self.default_script_arg_txt2img = self.init_default_script_args(script_runner)
selectable_scripts, selectable_script_idx = self.get_selectable_script(txt2imgreq.script_name, script_runner)
@@ -356,12 +436,15 @@ class Api:
args.pop('script_name', None)
args.pop('script_args', None) # will refeed them to the pipeline directly after initializing them
args.pop('alwayson_scripts', None)
+ args.pop('infotext', None)
- script_args = self.init_script_args(txt2imgreq, self.default_script_arg_txt2img, selectable_scripts, selectable_script_idx, script_runner)
+ script_args = self.init_script_args(txt2imgreq, self.default_script_arg_txt2img, selectable_scripts, selectable_script_idx, script_runner, input_script_args=infotext_script_args)
send_images = args.pop('send_images', True)
args.pop('save_images', None)
+ add_task_to_queue(task_id)
+
with self.queue_lock:
with closing(StableDiffusionProcessingTxt2Img(sd_model=shared.sd_model, **args)) as p:
p.is_api = True
@@ -371,12 +454,14 @@ class Api:
try:
shared.state.begin(job="scripts_txt2img")
+ start_task(task_id)
if selectable_scripts is not None:
p.script_args = script_args
processed = scripts.scripts_txt2img.run(p, *p.script_args) # Need to pass args as list here
else:
p.script_args = tuple(script_args) # Need to pass args as tuple here
processed = process_images(p)
+ finish_task(task_id)
finally:
shared.state.end()
shared.total_tqdm.clear()
@@ -386,6 +471,8 @@ class Api:
return models.TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js())
def img2imgapi(self, img2imgreq: models.StableDiffusionImg2ImgProcessingAPI):
+ task_id = img2imgreq.force_task_id or create_task_id("img2img")
+
init_images = img2imgreq.init_images
if init_images is None:
raise HTTPException(status_code=404, detail="Init image not found")
@@ -398,6 +485,10 @@ class Api:
if not script_runner.scripts:
script_runner.initialize_scripts(True)
ui.create_ui()
+
+ infotext_script_args = {}
+ self.apply_infotext(img2imgreq, "img2img", script_runner=script_runner, mentioned_script_args=infotext_script_args)
+
if not self.default_script_arg_img2img:
self.default_script_arg_img2img = self.init_default_script_args(script_runner)
selectable_scripts, selectable_script_idx = self.get_selectable_script(img2imgreq.script_name, script_runner)
@@ -417,11 +508,13 @@ class Api:
args.pop('script_args', None) # will refeed them to the pipeline directly after initializing them
args.pop('alwayson_scripts', None)
- script_args = self.init_script_args(img2imgreq, self.default_script_arg_img2img, selectable_scripts, selectable_script_idx, script_runner)
+ script_args = self.init_script_args(img2imgreq, self.default_script_arg_img2img, selectable_scripts, selectable_script_idx, script_runner, input_script_args=infotext_script_args)
send_images = args.pop('send_images', True)
args.pop('save_images', None)
+ add_task_to_queue(task_id)
+
with self.queue_lock:
with closing(StableDiffusionProcessingImg2Img(sd_model=shared.sd_model, **args)) as p:
p.init_images = [decode_base64_to_image(x) for x in init_images]
@@ -432,12 +525,14 @@ class Api:
try:
shared.state.begin(job="scripts_img2img")
+ start_task(task_id)
if selectable_scripts is not None:
p.script_args = script_args
processed = scripts.scripts_img2img.run(p, *p.script_args) # Need to pass args as list here
else:
p.script_args = tuple(script_args) # Need to pass args as tuple here
processed = process_images(p)
+ finish_task(task_id)
finally:
shared.state.end()
shared.total_tqdm.clear()
@@ -511,7 +606,7 @@ class Api:
if shared.state.current_image and not req.skip_current_image:
current_image = encode_pil_to_base64(shared.state.current_image)
- return models.ProgressResponse(progress=progress, eta_relative=eta_relative, state=shared.state.dict(), current_image=current_image, textinfo=shared.state.textinfo)
+ return models.ProgressResponse(progress=progress, eta_relative=eta_relative, state=shared.state.dict(), current_image=current_image, textinfo=shared.state.textinfo, current_task=current_task)
def interrogateapi(self, interrogatereq: models.InterrogateRequest):
image_b64 = interrogatereq.image
diff --git a/modules/api/models.py b/modules/api/models.py
index 33894b3e..16edf11c 100644
--- a/modules/api/models.py
+++ b/modules/api/models.py
@@ -107,6 +107,8 @@ StableDiffusionTxt2ImgProcessingAPI = PydanticModelGenerator(
{"key": "send_images", "type": bool, "default": True},
{"key": "save_images", "type": bool, "default": False},
{"key": "alwayson_scripts", "type": dict, "default": {}},
+ {"key": "force_task_id", "type": str, "default": None},
+ {"key": "infotext", "type": str, "default": None},
]
).generate_model()
@@ -124,6 +126,8 @@ StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator(
{"key": "send_images", "type": bool, "default": True},
{"key": "save_images", "type": bool, "default": False},
{"key": "alwayson_scripts", "type": dict, "default": {}},
+ {"key": "force_task_id", "type": str, "default": None},
+ {"key": "infotext", "type": str, "default": None},
]
).generate_model()
diff --git a/modules/devices.py b/modules/devices.py
index ea1f712f..c956207f 100644
--- a/modules/devices.py
+++ b/modules/devices.py
@@ -23,6 +23,23 @@ def has_mps() -> bool:
return mac_specific.has_mps
+def cuda_no_autocast(device_id=None) -> bool:
+ if device_id is None:
+ device_id = get_cuda_device_id()
+ return (
+ torch.cuda.get_device_capability(device_id) == (7, 5)
+ and torch.cuda.get_device_name(device_id).startswith("NVIDIA GeForce GTX 16")
+ )
+
+
+def get_cuda_device_id():
+ return (
+ int(shared.cmd_opts.device_id)
+ if shared.cmd_opts.device_id is not None and shared.cmd_opts.device_id.isdigit()
+ else 0
+ ) or torch.cuda.current_device()
+
+
def get_cuda_device_string():
if shared.cmd_opts.device_id is not None:
return f"cuda:{shared.cmd_opts.device_id}"
@@ -73,8 +90,7 @@ def enable_tf32():
# enabling benchmark option seems to enable a range of cards to do fp16 when they otherwise can't
# see https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/4407
- device_id = (int(shared.cmd_opts.device_id) if shared.cmd_opts.device_id is not None and shared.cmd_opts.device_id.isdigit() else 0) or torch.cuda.current_device()
- if torch.cuda.get_device_capability(device_id) == (7, 5) and torch.cuda.get_device_name(device_id).startswith("NVIDIA GeForce GTX 16"):
+ if cuda_no_autocast():
torch.backends.cudnn.benchmark = True
torch.backends.cuda.matmul.allow_tf32 = True
@@ -84,6 +100,7 @@ def enable_tf32():
errors.run(enable_tf32, "Enabling TF32")
cpu: torch.device = torch.device("cpu")
+fp8: bool = False
device: torch.device = None
device_interrogate: torch.device = None
device_gfpgan: torch.device = None
@@ -104,12 +121,51 @@ def cond_cast_float(input):
nv_rng = None
+patch_module_list = [
+ torch.nn.Linear,
+ torch.nn.Conv2d,
+ torch.nn.MultiheadAttention,
+ torch.nn.GroupNorm,
+ torch.nn.LayerNorm,
+]
+
+
+def manual_cast_forward(self, *args, **kwargs):
+ org_dtype = next(self.parameters()).dtype
+ self.to(dtype)
+ args = [arg.to(dtype) if isinstance(arg, torch.Tensor) else arg for arg in args]
+ kwargs = {k: v.to(dtype) if isinstance(v, torch.Tensor) else v for k, v in kwargs.items()}
+ result = self.org_forward(*args, **kwargs)
+ self.to(org_dtype)
+ return result
+
+
+@contextlib.contextmanager
+def manual_cast():
+ for module_type in patch_module_list:
+ org_forward = module_type.forward
+ module_type.forward = manual_cast_forward
+ module_type.org_forward = org_forward
+ try:
+ yield None
+ finally:
+ for module_type in patch_module_list:
+ module_type.forward = module_type.org_forward
def autocast(disable=False):
if disable:
return contextlib.nullcontext()
+ if fp8 and device==cpu:
+ return torch.autocast("cpu", dtype=torch.bfloat16, enabled=True)
+
+ if fp8 and (dtype == torch.float32 or shared.cmd_opts.precision == "full" or cuda_no_autocast()):
+ return manual_cast()
+
+ if has_mps() and shared.cmd_opts.precision != "full":
+ return manual_cast()
+
if dtype == torch.float32 or shared.cmd_opts.precision == "full":
return contextlib.nullcontext()
diff --git a/modules/errors.py b/modules/errors.py
index eb234a83..48aa13a1 100644
--- a/modules/errors.py
+++ b/modules/errors.py
@@ -107,8 +107,8 @@ def check_versions():
import torch
import gradio
- expected_torch_version = "2.0.0"
- expected_xformers_version = "0.0.20"
+ expected_torch_version = "2.1.2"
+ expected_xformers_version = "0.0.23.post1"
expected_gradio_version = "3.41.2"
if version.parse(torch.__version__) < version.parse(expected_torch_version):
diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py
index 4efe53e0..86a36c32 100644
--- a/modules/generation_parameters_copypaste.py
+++ b/modules/generation_parameters_copypaste.py
@@ -28,6 +28,19 @@ class ParamBinding:
self.paste_field_names = paste_field_names or []
+class PasteField(tuple):
+ def __new__(cls, component, target, *, api=None):
+ return super().__new__(cls, (component, target))
+
+ def __init__(self, component, target, *, api=None):
+ super().__init__()
+
+ self.api = api
+ self.component = component
+ self.label = target if isinstance(target, str) else None
+ self.function = target if callable(target) else None
+
+
paste_fields: dict[str, dict] = {}
registered_param_bindings: list[ParamBinding] = []
@@ -84,6 +97,12 @@ def image_from_url_text(filedata):
def add_paste_fields(tabname, init_img, fields, override_settings_component=None):
+
+ if fields:
+ for i in range(len(fields)):
+ if not isinstance(fields[i], PasteField):
+ fields[i] = PasteField(*fields[i])
+
paste_fields[tabname] = {"init_img": init_img, "fields": fields, "override_settings_component": override_settings_component}
# backwards compatibility for existing extensions
@@ -314,6 +333,12 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
if "VAE Decoder" not in res:
res["VAE Decoder"] = "Full"
+ if "FP8 weight" not in res:
+ res["FP8 weight"] = "Disable"
+
+ if "Cache FP16 weight for LoRA" not in res and res["FP8 weight"] != "Disable":
+ res["Cache FP16 weight for LoRA"] = False
+
skip = set(shared.opts.infotext_skip_pasting)
res = {k: v for k, v in res.items() if k not in skip}
@@ -365,6 +390,48 @@ def create_override_settings_dict(text_pairs):
return res
+def get_override_settings(params, *, skip_fields=None):
+ """Returns a list of settings overrides from the infotext parameters dictionary.
+
+ This function checks the `params` dictionary for any keys that correspond to settings in `shared.opts` and returns
+ a list of tuples containing the parameter name, setting name, and new value cast to correct type.
+
+ It checks for conditions before adding an override:
+ - ignores settings that match the current value
+ - ignores parameter keys present in skip_fields argument.
+
+ Example input:
+ {"Clip skip": "2"}
+
+ Example output:
+ [("Clip skip", "CLIP_stop_at_last_layers", 2)]
+ """
+
+ res = []
+
+ mapping = [(info.infotext, k) for k, info in shared.opts.data_labels.items() if info.infotext]
+ for param_name, setting_name in mapping + infotext_to_setting_name_mapping:
+ if param_name in (skip_fields or {}):
+ continue
+
+ v = params.get(param_name, None)
+ if v is None:
+ continue
+
+ if setting_name == "sd_model_checkpoint" and shared.opts.disable_weights_auto_swap:
+ continue
+
+ v = shared.opts.cast_value(setting_name, v)
+ current_value = getattr(shared.opts, setting_name, None)
+
+ if v == current_value:
+ continue
+
+ res.append((param_name, setting_name, v))
+
+ return res
+
+
def connect_paste(button, paste_fields, input_comp, override_settings_component, tabname):
def paste_func(prompt):
if not prompt and not shared.cmd_opts.hide_ui_dir_config:
@@ -406,29 +473,9 @@ def connect_paste(button, paste_fields, input_comp, override_settings_component,
already_handled_fields = {key: 1 for _, key in paste_fields}
def paste_settings(params):
- vals = {}
-
- mapping = [(info.infotext, k) for k, info in shared.opts.data_labels.items() if info.infotext]
- for param_name, setting_name in mapping + infotext_to_setting_name_mapping:
- if param_name in already_handled_fields:
- continue
-
- v = params.get(param_name, None)
- if v is None:
- continue
-
- if setting_name == "sd_model_checkpoint" and shared.opts.disable_weights_auto_swap:
- continue
-
- v = shared.opts.cast_value(setting_name, v)
- current_value = getattr(shared.opts, setting_name, None)
-
- if v == current_value:
- continue
-
- vals[param_name] = v
+ vals = get_override_settings(params, skip_fields=already_handled_fields)
- vals_pairs = [f"{k}: {v}" for k, v in vals.items()]
+ vals_pairs = [f"{infotext_text}: {value}" for infotext_text, setting_name, value in vals]
return gr.Dropdown.update(value=vals_pairs, choices=vals_pairs, visible=bool(vals_pairs))
diff --git a/modules/images.py b/modules/images.py
index daf4eebe..16f9ae7c 100644
--- a/modules/images.py
+++ b/modules/images.py
@@ -791,3 +791,4 @@ def flatten(img, bgcolor):
img = background
return img.convert('RGB')
+
diff --git a/modules/initialize_util.py b/modules/initialize_util.py
index 2e9b6d89..b6767138 100644
--- a/modules/initialize_util.py
+++ b/modules/initialize_util.py
@@ -177,6 +177,8 @@ def configure_opts_onchange():
shared.opts.onchange("temp_dir", ui_tempdir.on_tmpdir_changed)
shared.opts.onchange("gradio_theme", shared.reload_gradio_theme)
shared.opts.onchange("cross_attention_optimization", wrap_queued_call(lambda: sd_hijack.model_hijack.redo_hijack(shared.sd_model)), call=False)
+ shared.opts.onchange("fp8_storage", wrap_queued_call(lambda: sd_models.reload_model_weights()), call=False)
+ shared.opts.onchange("cache_fp16_weight", wrap_queued_call(lambda: sd_models.reload_model_weights(forced_reload=True)), call=False)
startup_timer.record("opts onchange")
diff --git a/modules/launch_utils.py b/modules/launch_utils.py
index 29506f24..dabef0f5 100644
--- a/modules/launch_utils.py
+++ b/modules/launch_utils.py
@@ -314,8 +314,8 @@ def requirements_met(requirements_file):
def prepare_environment():
- torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://download.pytorch.org/whl/cu118")
- torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.0.1 torchvision==0.15.2 --extra-index-url {torch_index_url}")
+ torch_index_url = os.environ.get('TORCH_INDEX_URL', "https://download.pytorch.org/whl/cu121")
+ torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.1.2 torchvision==0.16.2 --extra-index-url {torch_index_url}")
if args.use_ipex:
if platform.system() == "Windows":
# 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
@@ -338,7 +338,7 @@ def prepare_environment():
torch_command = os.environ.get('TORCH_COMMAND', f"pip install torch==2.0.0a0 intel-extension-for-pytorch==2.0.110+gitba7f6c1 --extra-index-url {torch_index_url}")
requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt")
- xformers_package = os.environ.get('XFORMERS_PACKAGE', 'xformers==0.0.20')
+ xformers_package = os.environ.get('XFORMERS_PACKAGE', 'xformers==0.0.23.post1')
clip_package = os.environ.get('CLIP_PACKAGE', "https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip")
openclip_package = os.environ.get('OPENCLIP_PACKAGE', "https://github.com/mlfoundations/open_clip/archive/bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b.zip")
diff --git a/modules/paths_internal.py b/modules/paths_internal.py
index 89131a54..b86ecd7f 100644
--- a/modules/paths_internal.py
+++ b/modules/paths_internal.py
@@ -28,5 +28,6 @@ models_path = os.path.join(data_path, "models")
extensions_dir = os.path.join(data_path, "extensions")
extensions_builtin_dir = os.path.join(script_path, "extensions-builtin")
config_states_dir = os.path.join(script_path, "config_states")
+default_output_dir = os.path.join(data_path, "output")
roboto_ttf_file = os.path.join(modules_path, 'Roboto-Regular.ttf')
diff --git a/modules/processing.py b/modules/processing.py
index c05e608a..7789f9a4 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -62,18 +62,22 @@ def apply_color_correction(correction, original_image):
return image.convert('RGB')
-def apply_overlay(image, paste_loc, index, overlays):
- if overlays is None or index >= len(overlays):
- return image
+def uncrop(image, dest_size, paste_loc):
+ x, y, w, h = paste_loc
+ base_image = Image.new('RGBA', dest_size)
+ image = images.resize_image(1, image, w, h)
+ base_image.paste(image, (x, y))
+ image = base_image
+
+ return image
- overlay = overlays[index]
+
+def apply_overlay(image, paste_loc, overlay):
+ if overlay is None:
+ return image
if paste_loc is not None:
- x, y, w, h = paste_loc
- base_image = Image.new('RGBA', (overlay.width, overlay.height))
- image = images.resize_image(1, image, w, h)
- base_image.paste(image, (x, y))
- image = base_image
+ image = uncrop(image, (overlay.width, overlay.height), paste_loc)
image = image.convert('RGBA')
image.alpha_composite(overlay)
@@ -81,9 +85,12 @@ def apply_overlay(image, paste_loc, index, overlays):
return image
-def create_binary_mask(image):
+def create_binary_mask(image, round=True):
if image.mode == 'RGBA' and image.getextrema()[-1] != (255, 255):
- image = image.split()[-1].convert("L").point(lambda x: 255 if x > 128 else 0)
+ if round:
+ image = image.split()[-1].convert("L").point(lambda x: 255 if x > 128 else 0)
+ else:
+ image = image.split()[-1].convert("L")
else:
image = image.convert('L')
return image
@@ -323,7 +330,7 @@ class StableDiffusionProcessing:
c_adm = torch.cat((c_adm, noise_level_emb), 1)
return c_adm
- def inpainting_image_conditioning(self, source_image, latent_image, image_mask=None):
+ def inpainting_image_conditioning(self, source_image, latent_image, image_mask=None, round_image_mask=True):
self.is_using_inpainting_conditioning = True
# Handle the different mask inputs
@@ -335,8 +342,10 @@ class StableDiffusionProcessing:
conditioning_mask = conditioning_mask.astype(np.float32) / 255.0
conditioning_mask = torch.from_numpy(conditioning_mask[None, None])
- # Inpainting model uses a discretized mask as input, so we round to either 1.0 or 0.0
- conditioning_mask = torch.round(conditioning_mask)
+ if round_image_mask:
+ # Caller is requesting a discretized mask as input, so we round to either 1.0 or 0.0
+ conditioning_mask = torch.round(conditioning_mask)
+
else:
conditioning_mask = source_image.new_ones(1, 1, *source_image.shape[-2:])
@@ -360,7 +369,7 @@ class StableDiffusionProcessing:
return image_conditioning
- def img2img_image_conditioning(self, source_image, latent_image, image_mask=None):
+ def img2img_image_conditioning(self, source_image, latent_image, image_mask=None, round_image_mask=True):
source_image = devices.cond_cast_float(source_image)
# HACK: Using introspection as the Depth2Image model doesn't appear to uniquely
@@ -372,7 +381,7 @@ class StableDiffusionProcessing:
return self.edit_image_conditioning(source_image)
if self.sampler.conditioning_key in {'hybrid', 'concat'}:
- return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask)
+ return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask, round_image_mask=round_image_mask)
if self.sampler.conditioning_key == "crossattn-adm":
return self.unclip_image_conditioning(source_image)
@@ -443,6 +452,8 @@ class StableDiffusionProcessing:
opts.sdxl_crop_top,
self.width,
self.height,
+ opts.fp8_storage,
+ opts.cache_fp16_weight,
)
def get_conds_with_caching(self, function, required_prompts, steps, caches, extra_network_data, hires_steps=None):
@@ -700,6 +711,8 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter
"Size": f"{p.width}x{p.height}",
"Model hash": p.sd_model_hash if opts.add_model_hash_to_info else None,
"Model": p.sd_model_name if opts.add_model_name_to_info else None,
+ "FP8 weight": opts.fp8_storage if devices.fp8 else None,
+ "Cache FP16 weight for LoRA": opts.cache_fp16_weight if devices.fp8 else None,
"VAE hash": p.sd_vae_hash if opts.add_vae_hash_to_info else None,
"VAE": p.sd_vae_name if opts.add_vae_name_to_info else None,
"Variation seed": (None if p.subseed_strength == 0 else (p.all_subseeds[0] if use_main_prompt else all_subseeds[index])),
@@ -888,6 +901,11 @@ 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)
+ if p.scripts is not None:
+ ps = scripts.PostSampleArgs(samples_ddim)
+ p.scripts.post_sample(p, ps)
+ samples_ddim = ps.samples
+
if getattr(samples_ddim, 'already_decoded', False):
x_samples_ddim = samples_ddim
else:
@@ -943,13 +961,31 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
pp = scripts.PostprocessImageArgs(image)
p.scripts.postprocess_image(p, pp)
image = pp.image
+
+ mask_for_overlay = getattr(p, "mask_for_overlay", None)
+ overlay_image = p.overlay_images[i] if getattr(p, "overlay_images", None) is not None and i < len(p.overlay_images) else None
+
+ if p.scripts is not None:
+ ppmo = scripts.PostProcessMaskOverlayArgs(i, mask_for_overlay, overlay_image)
+ p.scripts.postprocess_maskoverlay(p, ppmo)
+ mask_for_overlay, overlay_image = ppmo.mask_for_overlay, ppmo.overlay_image
+
if p.color_corrections is not None and i < len(p.color_corrections):
if save_samples and opts.save_images_before_color_correction:
- image_without_cc = apply_overlay(image, p.paste_to, i, p.overlay_images)
+ image_without_cc = apply_overlay(image, p.paste_to, overlay_image)
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 the intention is to show the output from the model
+ # that is being composited over the original image,
+ # we need to keep the original image around
+ # and use it in the composite step.
+ original_denoised_image = image.copy()
+
+ if p.paste_to is not None:
+ original_denoised_image = uncrop(original_denoised_image, (overlay_image.width, overlay_image.height), p.paste_to)
+
+ image = apply_overlay(image, p.paste_to, overlay_image)
if save_samples:
images.save_image(image, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p)
@@ -959,16 +995,17 @@ 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:
+
+ if mask_for_overlay is not None:
if opts.return_mask or opts.save_mask:
- image_mask = p.mask_for_overlay.convert('RGB')
+ image_mask = mask_for_overlay.convert('RGB')
if save_samples and opts.save_mask:
images.save_image(image_mask, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-mask")
if opts.return_mask:
output_images.append(image_mask)
if opts.return_mask_composite or opts.save_mask_composite:
- 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')
+ image_mask_composite = Image.composite(original_denoised_image.convert('RGBA').convert('RGBa'), Image.new('RGBa', image.size), images.resize_image(2, mask_for_overlay, image.width, image.height).convert('L')).convert('RGBA')
if save_samples and opts.save_mask_composite:
images.save_image(image_mask_composite, p.outpath_samples, "", p.seeds[i], p.prompts[i], opts.samples_format, info=infotext(i), p=p, suffix="-mask-composite")
if opts.return_mask_composite:
@@ -1046,6 +1083,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
hr_sampler_name: str = None
hr_prompt: str = ''
hr_negative_prompt: str = ''
+ force_task_id: str = None
cached_hr_uc = [None, None]
cached_hr_c = [None, None]
@@ -1118,7 +1156,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
def init(self, all_prompts, all_seeds, all_subseeds):
if self.enable_hr:
- if self.hr_checkpoint_name:
+ if self.hr_checkpoint_name and self.hr_checkpoint_name != 'Use same checkpoint':
self.hr_checkpoint_info = sd_models.get_closet_checkpoint_match(self.hr_checkpoint_name)
if self.hr_checkpoint_info is None:
@@ -1372,12 +1410,14 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
mask_blur_x: int = 4
mask_blur_y: int = 4
mask_blur: int = None
+ mask_round: bool = True
inpainting_fill: int = 0
inpaint_full_res: bool = True
inpaint_full_res_padding: int = 0
inpainting_mask_invert: int = 0
initial_noise_multiplier: float = None
latent_mask: Image = None
+ force_task_id: str = None
image_mask: Any = field(default=None, init=False)
@@ -1417,7 +1457,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
if image_mask is not None:
# image_mask is passed in as RGBA by Gradio to support alpha masks,
# but we still want to support binary masks.
- image_mask = create_binary_mask(image_mask)
+ image_mask = create_binary_mask(image_mask, round=self.mask_round)
if self.inpainting_mask_invert:
image_mask = ImageOps.invert(image_mask)
@@ -1463,7 +1503,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
# Save init image
if opts.save_init_img:
self.init_img_hash = hashlib.md5(img.tobytes()).hexdigest()
- images.save_image(img, path=opts.outdir_init_images, basename=None, forced_filename=self.init_img_hash, save_to_dirs=False)
+ images.save_image(img, path=opts.outdir_init_images, basename=None, forced_filename=self.init_img_hash, save_to_dirs=False, existing_info=img.info)
image = images.flatten(img, opts.img2img_background_color)
@@ -1524,7 +1564,8 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
latmask = init_mask.convert('RGB').resize((self.init_latent.shape[3], self.init_latent.shape[2]))
latmask = np.moveaxis(np.array(latmask, dtype=np.float32), 2, 0) / 255
latmask = latmask[0]
- latmask = np.around(latmask)
+ if self.mask_round:
+ latmask = np.around(latmask)
latmask = np.tile(latmask[None], (4, 1, 1))
self.mask = torch.asarray(1.0 - latmask).to(shared.device).type(self.sd_model.dtype)
@@ -1536,7 +1577,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
elif self.inpainting_fill == 3:
self.init_latent = self.init_latent * self.mask
- self.image_conditioning = self.img2img_image_conditioning(image * 2 - 1, self.init_latent, image_mask)
+ self.image_conditioning = self.img2img_image_conditioning(image * 2 - 1, self.init_latent, image_mask, self.mask_round)
def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, prompts):
x = self.rng.next()
@@ -1548,7 +1589,14 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
samples = self.sampler.sample_img2img(self, self.init_latent, x, conditioning, unconditional_conditioning, image_conditioning=self.image_conditioning)
if self.mask is not None:
- samples = samples * self.nmask + self.init_latent * self.mask
+ blended_samples = samples * self.nmask + self.init_latent * self.mask
+
+ if self.scripts is not None:
+ mba = scripts.MaskBlendArgs(samples, self.nmask, self.init_latent, self.mask, blended_samples)
+ self.scripts.on_mask_blend(self, mba)
+ blended_samples = mba.blended_latent
+
+ samples = blended_samples
del x
devices.torch_gc()
diff --git a/modules/processing_scripts/refiner.py b/modules/processing_scripts/refiner.py
index 29ccb78f..cefad32b 100644
--- a/modules/processing_scripts/refiner.py
+++ b/modules/processing_scripts/refiner.py
@@ -1,6 +1,7 @@
import gradio as gr
from modules import scripts, sd_models
+from modules.generation_parameters_copypaste import PasteField
from modules.ui_common import create_refresh_button
from modules.ui_components import InputAccordion
@@ -31,9 +32,9 @@ class ScriptRefiner(scripts.ScriptBuiltinUI):
return None if info is None else info.title
self.infotext_fields = [
- (enable_refiner, lambda d: 'Refiner' in d),
- (refiner_checkpoint, lambda d: lookup_checkpoint(d.get('Refiner'))),
- (refiner_switch_at, 'Refiner switch at'),
+ PasteField(enable_refiner, lambda d: 'Refiner' in d),
+ PasteField(refiner_checkpoint, lambda d: lookup_checkpoint(d.get('Refiner')), api="refiner_checkpoint"),
+ PasteField(refiner_switch_at, 'Refiner switch at', api="refiner_switch_at"),
]
return enable_refiner, refiner_checkpoint, refiner_switch_at
diff --git a/modules/processing_scripts/seed.py b/modules/processing_scripts/seed.py
index dc9c2da5..a3e16a12 100644
--- a/modules/processing_scripts/seed.py
+++ b/modules/processing_scripts/seed.py
@@ -3,6 +3,7 @@ import json
import gradio as gr
from modules import scripts, ui, errors
+from modules.generation_parameters_copypaste import PasteField
from modules.shared import cmd_opts
from modules.ui_components import ToolButton
@@ -51,12 +52,12 @@ class ScriptSeed(scripts.ScriptBuiltinUI):
seed_checkbox.change(lambda x: gr.update(visible=x), show_progress=False, inputs=[seed_checkbox], outputs=[seed_extras])
self.infotext_fields = [
- (self.seed, "Seed"),
- (seed_checkbox, lambda d: "Variation seed" in d or "Seed resize from-1" in d),
- (subseed, "Variation seed"),
- (subseed_strength, "Variation seed strength"),
- (seed_resize_from_w, "Seed resize from-1"),
- (seed_resize_from_h, "Seed resize from-2"),
+ PasteField(self.seed, "Seed", api="seed"),
+ PasteField(seed_checkbox, lambda d: "Variation seed" in d or "Seed resize from-1" in d),
+ PasteField(subseed, "Variation seed", api="subseed"),
+ PasteField(subseed_strength, "Variation seed strength", api="subseed_strength"),
+ PasteField(seed_resize_from_w, "Seed resize from-1", api="seed_resize_from_h"),
+ PasteField(seed_resize_from_h, "Seed resize from-2", api="seed_resize_from_w"),
]
self.on_after_component(lambda x: connect_reuse_seed(self.seed, reuse_seed, x.component, False), elem_id=f'generation_info_{self.tabname}')
diff --git a/modules/progress.py b/modules/progress.py
index 69921de7..85255e82 100644
--- a/modules/progress.py
+++ b/modules/progress.py
@@ -8,10 +8,13 @@ from pydantic import BaseModel, Field
from modules.shared import opts
import modules.shared as shared
-
+from collections import OrderedDict
+import string
+import random
+from typing import List
current_task = None
-pending_tasks = {}
+pending_tasks = OrderedDict()
finished_tasks = []
recorded_results = []
recorded_results_limit = 2
@@ -34,6 +37,11 @@ def finish_task(id_task):
if len(finished_tasks) > 16:
finished_tasks.pop(0)
+def create_task_id(task_type):
+ N = 7
+ res = ''.join(random.choices(string.ascii_uppercase +
+ string.digits, k=N))
+ return f"task({task_type}-{res})"
def record_results(id_task, res):
recorded_results.append((id_task, res))
@@ -44,6 +52,9 @@ def record_results(id_task, res):
def add_task_to_queue(id_job):
pending_tasks[id_job] = time.time()
+class PendingTasksResponse(BaseModel):
+ size: int = Field(title="Pending task size")
+ tasks: List[str] = Field(title="Pending task ids")
class ProgressRequest(BaseModel):
id_task: str = Field(default=None, title="Task ID", description="id of the task to get progress for")
@@ -63,9 +74,16 @@ class ProgressResponse(BaseModel):
def setup_progress_api(app):
+ app.add_api_route("/internal/pending-tasks", get_pending_tasks, methods=["GET"])
return app.add_api_route("/internal/progress", progressapi, methods=["POST"], response_model=ProgressResponse)
+def get_pending_tasks():
+ pending_tasks_ids = list(pending_tasks)
+ pending_len = len(pending_tasks_ids)
+ return PendingTasksResponse(size=pending_len, tasks=pending_tasks_ids)
+
+
def progressapi(req: ProgressRequest):
active = req.id_task == current_task
queued = req.id_task in pending_tasks
diff --git a/modules/scripts.py b/modules/scripts.py
index 7f9454eb..b6fcf96e 100644
--- a/modules/scripts.py
+++ b/modules/scripts.py
@@ -11,11 +11,31 @@ from modules import shared, paths, script_callbacks, extensions, script_loading,
AlwaysVisible = object()
+class MaskBlendArgs:
+ def __init__(self, current_latent, nmask, init_latent, mask, blended_latent, denoiser=None, sigma=None):
+ self.current_latent = current_latent
+ self.nmask = nmask
+ self.init_latent = init_latent
+ self.mask = mask
+ self.blended_latent = blended_latent
+
+ self.denoiser = denoiser
+ self.is_final_blend = denoiser is None
+ self.sigma = sigma
+
+class PostSampleArgs:
+ def __init__(self, samples):
+ self.samples = samples
class PostprocessImageArgs:
def __init__(self, image):
self.image = image
+class PostProcessMaskOverlayArgs:
+ def __init__(self, index, mask_for_overlay, overlay_image):
+ self.index = index
+ self.mask_for_overlay = mask_for_overlay
+ self.overlay_image = overlay_image
class PostprocessBatchListArgs:
def __init__(self, images):
@@ -206,6 +226,25 @@ class Script:
pass
+ def on_mask_blend(self, p, mba: MaskBlendArgs, *args):
+ """
+ Called in inpainting mode when the original content is blended with the inpainted content.
+ This is called at every step in the denoising process and once at the end.
+ If is_final_blend is true, this is called for the final blending stage.
+ Otherwise, denoiser and sigma are defined and may be used to inform the procedure.
+ """
+
+ pass
+
+ def post_sample(self, p, ps: PostSampleArgs, *args):
+ """
+ Called after the samples have been generated,
+ but before they have been decoded by the VAE, if applicable.
+ Check getattr(samples, 'already_decoded', False) to test if the images are decoded.
+ """
+
+ pass
+
def postprocess_image(self, p, pp: PostprocessImageArgs, *args):
"""
Called for every image after it has been generated.
@@ -213,6 +252,13 @@ class Script:
pass
+ def postprocess_maskoverlay(self, p, ppmo: PostProcessMaskOverlayArgs, *args):
+ """
+ Called for every image after it has been generated.
+ """
+
+ pass
+
def postprocess(self, p, processed, *args):
"""
This function is called after processing ends for AlwaysVisible scripts.
@@ -767,6 +813,22 @@ class ScriptRunner:
except Exception:
errors.report(f"Error running postprocess_batch_list: {script.filename}", exc_info=True)
+ def post_sample(self, p, ps: PostSampleArgs):
+ for script in self.alwayson_scripts:
+ try:
+ script_args = p.script_args[script.args_from:script.args_to]
+ script.post_sample(p, ps, *script_args)
+ except Exception:
+ errors.report(f"Error running post_sample: {script.filename}", exc_info=True)
+
+ def on_mask_blend(self, p, mba: MaskBlendArgs):
+ for script in self.alwayson_scripts:
+ try:
+ script_args = p.script_args[script.args_from:script.args_to]
+ script.on_mask_blend(p, mba, *script_args)
+ except Exception:
+ errors.report(f"Error running post_sample: {script.filename}", exc_info=True)
+
def postprocess_image(self, p, pp: PostprocessImageArgs):
for script in self.alwayson_scripts:
try:
@@ -775,6 +837,14 @@ class ScriptRunner:
except Exception:
errors.report(f"Error running postprocess_image: {script.filename}", exc_info=True)
+ def postprocess_maskoverlay(self, p, ppmo: PostProcessMaskOverlayArgs):
+ for script in self.alwayson_scripts:
+ try:
+ script_args = p.script_args[script.args_from:script.args_to]
+ script.postprocess_maskoverlay(p, ppmo, *script_args)
+ except Exception:
+ errors.report(f"Error running postprocess_image: {script.filename}", exc_info=True)
+
def before_component(self, component, **kwargs):
for callback, script in self.on_before_component_elem_id.get(kwargs.get("elem_id"), []):
try:
diff --git a/modules/sd_models.py b/modules/sd_models.py
index 9355f1e1..d0046f88 100644
--- a/modules/sd_models.py
+++ b/modules/sd_models.py
@@ -348,10 +348,28 @@ class SkipWritingToConfig:
SkipWritingToConfig.skip = self.previous
+def check_fp8(model):
+ if model is None:
+ return None
+ if devices.get_optimal_device_name() == "mps":
+ enable_fp8 = False
+ elif shared.opts.fp8_storage == "Enable":
+ enable_fp8 = True
+ elif getattr(model, "is_sdxl", False) and shared.opts.fp8_storage == "Enable for SDXL":
+ enable_fp8 = True
+ else:
+ enable_fp8 = False
+ return enable_fp8
+
+
def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer):
sd_model_hash = checkpoint_info.calculate_shorthash()
timer.record("calculate hash")
+ if devices.fp8:
+ # prevent model to load state dict in fp8
+ model.half()
+
if not SkipWritingToConfig.skip:
shared.opts.data["sd_model_checkpoint"] = checkpoint_info.title
@@ -404,6 +422,28 @@ def load_model_weights(model, checkpoint_info: CheckpointInfo, state_dict, timer
devices.dtype_unet = torch.float16
timer.record("apply half()")
+ for module in model.modules():
+ if hasattr(module, 'fp16_weight'):
+ del module.fp16_weight
+ if hasattr(module, 'fp16_bias'):
+ del module.fp16_bias
+
+ if check_fp8(model):
+ devices.fp8 = True
+ first_stage = model.first_stage_model
+ model.first_stage_model = None
+ for module in model.modules():
+ if isinstance(module, (torch.nn.Conv2d, torch.nn.Linear)):
+ if shared.opts.cache_fp16_weight:
+ module.fp16_weight = module.weight.data.clone().cpu().half()
+ if module.bias is not None:
+ module.fp16_bias = module.bias.data.clone().cpu().half()
+ module.to(torch.float8_e4m3fn)
+ model.first_stage_model = first_stage
+ timer.record("apply fp8")
+ else:
+ devices.fp8 = False
+
devices.unet_needs_upcast = shared.cmd_opts.upcast_sampling and devices.dtype == torch.float16 and devices.dtype_unet == torch.float16
model.first_stage_model.to(devices.dtype_vae)
@@ -746,7 +786,7 @@ def reuse_model_from_already_loaded(sd_model, checkpoint_info, timer):
return None
-def reload_model_weights(sd_model=None, info=None):
+def reload_model_weights(sd_model=None, info=None, forced_reload=False):
checkpoint_info = info or select_checkpoint()
timer = Timer()
@@ -758,11 +798,14 @@ def reload_model_weights(sd_model=None, info=None):
current_checkpoint_info = None
else:
current_checkpoint_info = sd_model.sd_checkpoint_info
- if sd_model.sd_model_checkpoint == checkpoint_info.filename:
+ if check_fp8(sd_model) != devices.fp8:
+ # load from state dict again to prevent extra numerical errors
+ forced_reload = True
+ elif sd_model.sd_model_checkpoint == checkpoint_info.filename and not forced_reload:
return sd_model
sd_model = reuse_model_from_already_loaded(sd_model, checkpoint_info, timer)
- if sd_model is not None and sd_model.sd_checkpoint_info.filename == checkpoint_info.filename:
+ if not forced_reload and sd_model is not None and sd_model.sd_checkpoint_info.filename == checkpoint_info.filename:
return sd_model
if sd_model is not None:
diff --git a/modules/sd_models_xl.py b/modules/sd_models_xl.py
index 162d0fee..1de31b0d 100644
--- a/modules/sd_models_xl.py
+++ b/modules/sd_models_xl.py
@@ -99,7 +99,7 @@ def extend_sdxl(model):
model.parameterization = "v" if isinstance(model.denoiser.scaling, sgm.modules.diffusionmodules.denoiser_scaling.VScaling) else "eps"
discretization = sgm.modules.diffusionmodules.discretizer.LegacyDDPMDiscretization()
- model.alphas_cumprod = torch.asarray(discretization.alphas_cumprod, device=devices.device, dtype=dtype)
+ model.alphas_cumprod = torch.asarray(discretization.alphas_cumprod, device=devices.device, dtype=torch.float32)
model.conditioner.wrapped = torch.nn.Module()
diff --git a/modules/sd_samplers_cfg_denoiser.py b/modules/sd_samplers_cfg_denoiser.py
index b8101d38..eb9d5daf 100644
--- a/modules/sd_samplers_cfg_denoiser.py
+++ b/modules/sd_samplers_cfg_denoiser.py
@@ -56,6 +56,9 @@ class CFGDenoiser(torch.nn.Module):
self.sampler = sampler
self.model_wrap = None
self.p = None
+
+ # NOTE: masking before denoising can cause the original latents to be oversmoothed
+ # as the original latents do not have noise
self.mask_before_denoising = False
@property
@@ -105,8 +108,21 @@ class CFGDenoiser(torch.nn.Module):
assert not is_edit_model or all(len(conds) == 1 for conds in conds_list), "AND is not supported for InstructPix2Pix checkpoint (unless using Image CFG scale = 1.0)"
+ # If we use masks, blending between the denoised and original latent images occurs here.
+ def apply_blend(current_latent):
+ blended_latent = current_latent * self.nmask + self.init_latent * self.mask
+
+ if self.p.scripts is not None:
+ from modules import scripts
+ mba = scripts.MaskBlendArgs(current_latent, self.nmask, self.init_latent, self.mask, blended_latent, denoiser=self, sigma=sigma)
+ self.p.scripts.on_mask_blend(self.p, mba)
+ blended_latent = mba.blended_latent
+
+ return blended_latent
+
+ # Blend in the original latents (before)
if self.mask_before_denoising and self.mask is not None:
- x = self.init_latent * self.mask + self.nmask * x
+ x = apply_blend(x)
batch_size = len(conds_list)
repeats = [len(conds_list[i]) for i in range(batch_size)]
@@ -207,8 +223,9 @@ class CFGDenoiser(torch.nn.Module):
else:
denoised = self.combine_denoised(x_out, conds_list, uncond, cond_scale)
+ # Blend in the original latents (after)
if not self.mask_before_denoising and self.mask is not None:
- denoised = self.init_latent * self.mask + self.nmask * denoised
+ denoised = apply_blend(denoised)
self.sampler.last_latent = self.get_pred_x0(torch.cat([x_in[i:i + 1] for i in denoised_image_indexes]), torch.cat([x_out[i:i + 1] for i in denoised_image_indexes]), sigma)
diff --git a/modules/shared_options.py b/modules/shared_options.py
index d2e86ff1..752a4f12 100644
--- a/modules/shared_options.py
+++ b/modules/shared_options.py
@@ -1,7 +1,8 @@
+import os
import gradio as gr
-from modules import localization, ui_components, shared_items, shared, interrogate, shared_gradio_themes
-from modules.paths_internal import models_path, script_path, data_path, sd_configs_path, sd_default_config, sd_model_file, default_sd_model_file, extensions_dir, extensions_builtin_dir # noqa: F401
+from modules import localization, ui_components, shared_items, shared, interrogate, shared_gradio_themes, util
+from modules.paths_internal import models_path, script_path, data_path, sd_configs_path, sd_default_config, sd_model_file, default_sd_model_file, extensions_dir, extensions_builtin_dir, default_output_dir # noqa: F401
from modules.shared_cmd_options import cmd_opts
from modules.options import options_section, OptionInfo, OptionHTML, categories
@@ -74,14 +75,14 @@ options_templates.update(options_section(('saving-images', "Saving images/grids"
options_templates.update(options_section(('saving-paths', "Paths for saving", "saving"), {
"outdir_samples": OptionInfo("", "Output directory for images; if empty, defaults to three directories below", component_args=hide_dirs),
- "outdir_txt2img_samples": OptionInfo("outputs/txt2img-images", 'Output directory for txt2img images', component_args=hide_dirs),
- "outdir_img2img_samples": OptionInfo("outputs/img2img-images", 'Output directory for img2img images', component_args=hide_dirs),
- "outdir_extras_samples": OptionInfo("outputs/extras-images", 'Output directory for images from extras tab', component_args=hide_dirs),
+ "outdir_txt2img_samples": OptionInfo(util.truncate_path(os.path.join(default_output_dir, 'txt2img-images')), 'Output directory for txt2img images', component_args=hide_dirs),
+ "outdir_img2img_samples": OptionInfo(util.truncate_path(os.path.join(default_output_dir, 'img2img-images')), 'Output directory for img2img images', component_args=hide_dirs),
+ "outdir_extras_samples": OptionInfo(util.truncate_path(os.path.join(default_output_dir, 'extras-images')), 'Output directory for images from extras tab', component_args=hide_dirs),
"outdir_grids": OptionInfo("", "Output directory for grids; if empty, defaults to two directories below", component_args=hide_dirs),
- "outdir_txt2img_grids": OptionInfo("outputs/txt2img-grids", 'Output directory for txt2img grids', component_args=hide_dirs),
- "outdir_img2img_grids": OptionInfo("outputs/img2img-grids", 'Output directory for img2img grids', component_args=hide_dirs),
- "outdir_save": OptionInfo("log/images", "Directory for saving images using the Save button", component_args=hide_dirs),
- "outdir_init_images": OptionInfo("outputs/init-images", "Directory for saving init images when using img2img", component_args=hide_dirs),
+ "outdir_txt2img_grids": OptionInfo(util.truncate_path(os.path.join(default_output_dir, 'txt2img-grids')), 'Output directory for txt2img grids', component_args=hide_dirs),
+ "outdir_img2img_grids": OptionInfo(util.truncate_path(os.path.join(default_output_dir, 'img2img-grids')), 'Output directory for img2img grids', component_args=hide_dirs),
+ "outdir_save": OptionInfo(util.truncate_path(os.path.join(data_path, 'log', 'images')), "Directory for saving images using the Save button", component_args=hide_dirs),
+ "outdir_init_images": OptionInfo(util.truncate_path(os.path.join(default_output_dir, 'init-images')), "Directory for saving init images when using img2img", component_args=hide_dirs),
}))
options_templates.update(options_section(('saving-to-dirs', "Saving to a directory", "saving"), {
@@ -206,6 +207,8 @@ options_templates.update(options_section(('optimizations', "Optimizations", "sd"
"pad_cond_uncond": OptionInfo(False, "Pad prompt/negative prompt to be same length", infotext='Pad conds').info("improves performance when prompt and negative prompt have different lengths; changes seeds"),
"persistent_cond_cache": OptionInfo(True, "Persistent cond cache").info("do not recalculate conds from prompts if prompts have not changed since previous calculation"),
"batch_cond_uncond": OptionInfo(True, "Batch cond/uncond").info("do both conditional and unconditional denoising in one batch; uses a bit more VRAM during sampling, but improves speed; previously this was controlled by --always-batch-cond-uncond comandline argument"),
+ "fp8_storage": OptionInfo("Disable", "FP8 weight", gr.Radio, {"choices": ["Disable", "Enable for SDXL", "Enable"]}).info("Use FP8 to store Linear/Conv layers' weight. Require pytorch>=2.1.0."),
+ "cache_fp16_weight": OptionInfo(False, "Cache FP16 weight for LoRA").info("Cache fp16 weight when enabling FP8, will increase the quality of LoRA. Use more system ram."),
}))
options_templates.update(options_section(('compatibility', "Compatibility", "sd"), {
diff --git a/modules/ui.py b/modules/ui.py
index d80486dd..9db2407e 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -28,7 +28,7 @@ import modules.textual_inversion.textual_inversion as textual_inversion
import modules.shared as shared
from modules import prompt_parser
from modules.sd_hijack import model_hijack
-from modules.generation_parameters_copypaste import image_from_url_text
+from modules.generation_parameters_copypaste import image_from_url_text, PasteField
create_setting_component = ui_settings.create_setting_component
@@ -436,28 +436,28 @@ def create_ui():
)
txt2img_paste_fields = [
- (toprow.prompt, "Prompt"),
- (toprow.negative_prompt, "Negative prompt"),
- (steps, "Steps"),
- (sampler_name, "Sampler"),
- (cfg_scale, "CFG scale"),
- (width, "Size-1"),
- (height, "Size-2"),
- (batch_size, "Batch size"),
- (toprow.ui_styles.dropdown, lambda d: d["Styles array"] if isinstance(d.get("Styles array"), list) else gr.update()),
- (denoising_strength, "Denoising strength"),
- (enable_hr, lambda d: "Denoising strength" in d and ("Hires upscale" in d or "Hires upscaler" in d or "Hires resize-1" in d)),
- (hr_scale, "Hires upscale"),
- (hr_upscaler, "Hires upscaler"),
- (hr_second_pass_steps, "Hires steps"),
- (hr_resize_x, "Hires resize-1"),
- (hr_resize_y, "Hires resize-2"),
- (hr_checkpoint_name, "Hires checkpoint"),
- (hr_sampler_name, "Hires sampler"),
- (hr_sampler_container, lambda d: gr.update(visible=True) if d.get("Hires sampler", "Use same sampler") != "Use same sampler" or d.get("Hires checkpoint", "Use same checkpoint") != "Use same checkpoint" else gr.update()),
- (hr_prompt, "Hires prompt"),
- (hr_negative_prompt, "Hires negative prompt"),
- (hr_prompts_container, lambda d: gr.update(visible=True) if d.get("Hires prompt", "") != "" or d.get("Hires negative prompt", "") != "" else gr.update()),
+ PasteField(toprow.prompt, "Prompt", api="prompt"),
+ PasteField(toprow.negative_prompt, "Negative prompt", api="negative_prompt"),
+ PasteField(steps, "Steps", api="steps"),
+ PasteField(sampler_name, "Sampler", api="sampler_name"),
+ PasteField(cfg_scale, "CFG scale", api="cfg_scale"),
+ PasteField(width, "Size-1", api="width"),
+ PasteField(height, "Size-2", api="height"),
+ PasteField(batch_size, "Batch size", api="batch_size"),
+ PasteField(toprow.ui_styles.dropdown, lambda d: d["Styles array"] if isinstance(d.get("Styles array"), list) else gr.update(), api="styles"),
+ PasteField(denoising_strength, "Denoising strength", api="denoising_strength"),
+ PasteField(enable_hr, lambda d: "Denoising strength" in d and ("Hires upscale" in d or "Hires upscaler" in d or "Hires resize-1" in d), api="enable_hr"),
+ PasteField(hr_scale, "Hires upscale", api="hr_scale"),
+ PasteField(hr_upscaler, "Hires upscaler", api="hr_upscaler"),
+ PasteField(hr_second_pass_steps, "Hires steps", api="hr_second_pass_steps"),
+ PasteField(hr_resize_x, "Hires resize-1", api="hr_resize_x"),
+ PasteField(hr_resize_y, "Hires resize-2", api="hr_resize_y"),
+ PasteField(hr_checkpoint_name, "Hires checkpoint", api="hr_checkpoint_name"),
+ PasteField(hr_sampler_name, "Hires sampler", api="hr_sampler_name"),
+ PasteField(hr_sampler_container, lambda d: gr.update(visible=True) if d.get("Hires sampler", "Use same sampler") != "Use same sampler" or d.get("Hires checkpoint", "Use same checkpoint") != "Use same checkpoint" else gr.update()),
+ PasteField(hr_prompt, "Hires prompt", api="hr_prompt"),
+ PasteField(hr_negative_prompt, "Hires negative prompt", api="hr_negative_prompt"),
+ PasteField(hr_prompts_container, lambda d: gr.update(visible=True) if d.get("Hires prompt", "") != "" or d.get("Hires negative prompt", "") != "" else gr.update()),
*scripts.scripts_txt2img.infotext_fields
]
parameters_copypaste.add_paste_fields("txt2img", None, txt2img_paste_fields, override_settings)
diff --git a/modules/ui_gradio_extensions.py b/modules/ui_gradio_extensions.py
index 0d368f8b..a86c368e 100644
--- a/modules/ui_gradio_extensions.py
+++ b/modules/ui_gradio_extensions.py
@@ -1,17 +1,12 @@
import os
import gradio as gr
-from modules import localization, shared, scripts
-from modules.paths import script_path, data_path, cwd
+from modules import localization, shared, scripts, util
+from modules.paths import script_path, data_path
def webpath(fn):
- if fn.startswith(cwd):
- web_path = os.path.relpath(fn, cwd)
- else:
- web_path = os.path.abspath(fn)
-
- return f'file={web_path}?{os.path.getmtime(fn)}'
+ return f'file={util.truncate_path(fn)}?{os.path.getmtime(fn)}'
def javascript_html():
diff --git a/modules/ui_toprow.py b/modules/ui_toprow.py
index 88838f97..9caf8faa 100644
--- a/modules/ui_toprow.py
+++ b/modules/ui_toprow.py
@@ -79,11 +79,11 @@ class Toprow:
def create_prompts(self):
with gr.Column(elem_id=f"{self.id_part}_prompt_container", elem_classes=["prompt-container-compact"] if self.is_compact else [], scale=6):
with gr.Row(elem_id=f"{self.id_part}_prompt_row", elem_classes=["prompt-row"]):
- self.prompt = gr.Textbox(label="Prompt", elem_id=f"{self.id_part}_prompt", show_label=False, lines=3, placeholder="Prompt (press Ctrl+Enter or Alt+Enter to generate)", elem_classes=["prompt"])
+ self.prompt = gr.Textbox(label="Prompt", elem_id=f"{self.id_part}_prompt", show_label=False, lines=3, placeholder="Prompt\n(Press Ctrl+Enter to generate, Alt+Enter to skip, Esc to interrupt)", elem_classes=["prompt"])
self.prompt_img = gr.File(label="", elem_id=f"{self.id_part}_prompt_image", file_count="single", type="binary", visible=False)
with gr.Row(elem_id=f"{self.id_part}_neg_prompt_row", elem_classes=["prompt-row"]):
- self.negative_prompt = gr.Textbox(label="Negative prompt", elem_id=f"{self.id_part}_neg_prompt", show_label=False, lines=3, placeholder="Negative prompt (press Ctrl+Enter or Alt+Enter to generate)", elem_classes=["prompt"])
+ self.negative_prompt = gr.Textbox(label="Negative prompt", elem_id=f"{self.id_part}_neg_prompt", show_label=False, lines=3, placeholder="Negative prompt\n(Press Ctrl+Enter to generate, Alt+Enter to skip, Esc to interrupt)", elem_classes=["prompt"])
self.prompt_img.change(
fn=modules.images.image_data,
diff --git a/modules/util.py b/modules/util.py
index 60afc067..4861bcb0 100644
--- a/modules/util.py
+++ b/modules/util.py
@@ -2,7 +2,7 @@ import os
import re
from modules import shared
-from modules.paths_internal import script_path
+from modules.paths_internal import script_path, cwd
def natural_sort_key(s, regex=re.compile('([0-9]+)')):
@@ -56,3 +56,13 @@ def ldm_print(*args, **kwargs):
return
print(*args, **kwargs)
+
+
+def truncate_path(target_path, base_path=cwd):
+ abs_target, abs_base = os.path.abspath(target_path), os.path.abspath(base_path)
+ try:
+ if os.path.commonpath([abs_target, abs_base]) == abs_base:
+ return os.path.relpath(abs_target, abs_base)
+ except ValueError:
+ pass
+ return abs_target
generated by cgit v1.2.1 (git 2.18.0) at 2025-05-12 18:20:44 +0000