diff options
Diffstat (limited to 'modules')
36 files changed, 1096 insertions, 3283 deletions
diff --git a/modules/api/api.py b/modules/api/api.py index 7a567be3..89935a70 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -3,7 +3,8 @@ import io import time import uvicorn from threading import Lock -from gradio.processing_utils import encode_pil_to_base64, decode_base64_to_file, decode_base64_to_image +from io import BytesIO +from gradio.processing_utils import decode_base64_to_file from fastapi import APIRouter, Depends, FastAPI, HTTPException from fastapi.security import HTTPBasic, HTTPBasicCredentials from secrets import compare_digest @@ -13,7 +14,7 @@ from modules import sd_samplers, deepbooru from modules.api.models import * from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images from modules.extras import run_extras, run_pnginfo -from PIL import PngImagePlugin +from PIL import PngImagePlugin,Image from modules.sd_models import checkpoints_list from modules.realesrgan_model import get_realesrgan_models from typing import List @@ -40,6 +41,10 @@ def setUpscalers(req: dict): reqDict.pop('upscaler_2') return reqDict +def decode_base64_to_image(encoding): + if encoding.startswith("data:image/"): + encoding = encoding.split(";")[1].split(",")[1] + return Image.open(BytesIO(base64.b64decode(encoding))) def encode_pil_to_base64(image): with io.BytesIO() as output_bytes: @@ -107,11 +112,13 @@ class Api: def text2imgapi(self, txt2imgreq: StableDiffusionTxt2ImgProcessingAPI): populate = txt2imgreq.copy(update={ # Override __init__ params "sd_model": shared.sd_model, - "sampler_name": validate_sampler_name(txt2imgreq.sampler_index), + "sampler_name": validate_sampler_name(txt2imgreq.sampler_name or txt2imgreq.sampler_index), "do_not_save_samples": True, "do_not_save_grid": True } ) + if populate.sampler_name: + populate.sampler_index = None # prevent a warning later on p = StableDiffusionProcessingTxt2Img(**vars(populate)) # Override object param @@ -137,20 +144,20 @@ class Api: populate = img2imgreq.copy(update={ # Override __init__ params "sd_model": shared.sd_model, - "sampler_name": validate_sampler_name(img2imgreq.sampler_index), + "sampler_name": validate_sampler_name(img2imgreq.sampler_name or img2imgreq.sampler_index), "do_not_save_samples": True, "do_not_save_grid": True, "mask": mask } ) - p = StableDiffusionProcessingImg2Img(**vars(populate)) + if populate.sampler_name: + populate.sampler_index = None # prevent a warning later on - imgs = [] - for img in init_images: - img = decode_base64_to_image(img) - imgs = [img] * p.batch_size + args = vars(populate) + args.pop('include_init_images', None) # this is meant to be done by "exclude": True in model, but it's for a reason that I cannot determine. + p = StableDiffusionProcessingImg2Img(**args) - p.init_images = imgs + p.init_images = [decode_base64_to_image(x) for x in init_images] shared.state.begin() @@ -161,7 +168,7 @@ class Api: b64images = list(map(encode_pil_to_base64, processed.images)) - if (not img2imgreq.include_init_images): + if not img2imgreq.include_init_images: img2imgreq.init_images = None img2imgreq.mask = None @@ -305,7 +312,7 @@ class Api: styleList = [] for k in shared.prompt_styles.styles: style = shared.prompt_styles.styles[k] - styleList.append({"name":style[0], "prompt": style[1], "negative_prompr": style[2]}) + styleList.append({"name":style[0], "prompt": style[1], "negative_prompt": style[2]}) return styleList diff --git a/modules/call_queue.py b/modules/call_queue.py new file mode 100644 index 00000000..4cd49533 --- /dev/null +++ b/modules/call_queue.py @@ -0,0 +1,98 @@ +import html
+import sys
+import threading
+import traceback
+import time
+
+from modules import shared
+
+queue_lock = threading.Lock()
+
+
+def wrap_queued_call(func):
+ def f(*args, **kwargs):
+ with queue_lock:
+ res = func(*args, **kwargs)
+
+ return res
+
+ return f
+
+
+def wrap_gradio_gpu_call(func, extra_outputs=None):
+ def f(*args, **kwargs):
+
+ shared.state.begin()
+
+ with queue_lock:
+ res = func(*args, **kwargs)
+
+ shared.state.end()
+
+ return res
+
+ return wrap_gradio_call(f, extra_outputs=extra_outputs, add_stats=True)
+
+
+def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
+ def f(*args, extra_outputs_array=extra_outputs, **kwargs):
+ run_memmon = shared.opts.memmon_poll_rate > 0 and not shared.mem_mon.disabled and add_stats
+ if run_memmon:
+ shared.mem_mon.monitor()
+ t = time.perf_counter()
+
+ try:
+ res = list(func(*args, **kwargs))
+ except Exception as e:
+ # When printing out our debug argument list, do not print out more than a MB of text
+ max_debug_str_len = 131072 # (1024*1024)/8
+
+ print("Error completing request", file=sys.stderr)
+ argStr = f"Arguments: {str(args)} {str(kwargs)}"
+ print(argStr[:max_debug_str_len], file=sys.stderr)
+ if len(argStr) > max_debug_str_len:
+ print(f"(Argument list truncated at {max_debug_str_len}/{len(argStr)} characters)", file=sys.stderr)
+
+ print(traceback.format_exc(), file=sys.stderr)
+
+ shared.state.job = ""
+ shared.state.job_count = 0
+
+ if extra_outputs_array is None:
+ extra_outputs_array = [None, '']
+
+ res = extra_outputs_array + [f"<div class='error'>{html.escape(type(e).__name__+': '+str(e))}</div>"]
+
+ shared.state.skipped = False
+ shared.state.interrupted = False
+ shared.state.job_count = 0
+
+ if not add_stats:
+ return tuple(res)
+
+ elapsed = time.perf_counter() - t
+ elapsed_m = int(elapsed // 60)
+ elapsed_s = elapsed % 60
+ elapsed_text = f"{elapsed_s:.2f}s"
+ if elapsed_m > 0:
+ elapsed_text = f"{elapsed_m}m "+elapsed_text
+
+ if run_memmon:
+ mem_stats = {k: -(v//-(1024*1024)) for k, v in shared.mem_mon.stop().items()}
+ active_peak = mem_stats['active_peak']
+ reserved_peak = mem_stats['reserved_peak']
+ sys_peak = mem_stats['system_peak']
+ sys_total = mem_stats['total']
+ sys_pct = round(sys_peak/max(sys_total, 1) * 100, 2)
+
+ vram_html = f"<p class='vram'>Torch active/reserved: {active_peak}/{reserved_peak} MiB, <wbr>Sys VRAM: {sys_peak}/{sys_total} MiB ({sys_pct}%)</p>"
+ else:
+ vram_html = ''
+
+ # last item is always HTML
+ res[-1] += f"<div class='performance'><p class='time'>Time taken: <wbr>{elapsed_text}</p>{vram_html}</div>"
+
+ return tuple(res)
+
+ return f
+
diff --git a/modules/codeformer_model.py b/modules/codeformer_model.py index e6d9fa4f..ab40d842 100644 --- a/modules/codeformer_model.py +++ b/modules/codeformer_model.py @@ -36,6 +36,7 @@ def setup_model(dirname): from basicsr.utils.download_util import load_file_from_url
from basicsr.utils import imwrite, img2tensor, tensor2img
from facelib.utils.face_restoration_helper import FaceRestoreHelper
+ from facelib.detection.retinaface import retinaface
from modules.shared import cmd_opts
net_class = CodeFormer
@@ -65,6 +66,8 @@ def setup_model(dirname): net.load_state_dict(checkpoint)
net.eval()
+ if hasattr(retinaface, 'device'):
+ retinaface.device = devices.device_codeformer
face_helper = FaceRestoreHelper(1, face_size=512, crop_ratio=(1, 1), det_model='retinaface_resnet50', save_ext='png', use_parse=True, device=devices.device_codeformer)
self.net = net
diff --git a/modules/deepbooru.py b/modules/deepbooru.py index b9066d81..dfc83357 100644 --- a/modules/deepbooru.py +++ b/modules/deepbooru.py @@ -21,7 +21,7 @@ class DeepDanbooru: files = modelloader.load_models( model_path=os.path.join(paths.models_path, "torch_deepdanbooru"), model_url='https://github.com/AUTOMATIC1111/TorchDeepDanbooru/releases/download/v1/model-resnet_custom_v3.pt', - ext_filter=".pt", + ext_filter=[".pt"], download_name='model-resnet_custom_v3.pt', ) @@ -58,7 +58,7 @@ class DeepDanbooru: a = np.expand_dims(np.array(pic, dtype=np.float32), 0) / 255 with torch.no_grad(), devices.autocast(): - x = torch.from_numpy(a).cuda() + x = torch.from_numpy(a).to(devices.device) y = self.model(x)[0].detach().cpu().numpy() probability_dict = {} diff --git a/modules/devices.py b/modules/devices.py index 67165bf6..f8cffae1 100644 --- a/modules/devices.py +++ b/modules/devices.py @@ -2,9 +2,10 @@ import sys, os, shlex import contextlib import torch from modules import errors +from packaging import version -# has_mps is only available in nightly pytorch (for now) and MasOS 12.3+. +# has_mps is only available in nightly pytorch (for now) and macOS 12.3+. # check `getattr` and try it for compatibility def has_mps() -> bool: if not getattr(torch, 'has_mps', False): @@ -24,17 +25,18 @@ def extract_device_id(args, name): return None -def get_optimal_device(): - if torch.cuda.is_available(): - from modules import shared +def get_cuda_device_string(): + from modules import shared - device_id = shared.cmd_opts.device_id + if shared.cmd_opts.device_id is not None: + return f"cuda:{shared.cmd_opts.device_id}" - if device_id is not None: - cuda_device = f"cuda:{device_id}" - return torch.device(cuda_device) - else: - return torch.device("cuda") + return "cuda" + + +def get_optimal_device(): + if torch.cuda.is_available(): + return torch.device(get_cuda_device_string()) if has_mps(): return torch.device("mps") @@ -42,45 +44,53 @@ def get_optimal_device(): return cpu +def get_device_for(task): + from modules import shared + + if task in shared.cmd_opts.use_cpu: + return cpu + + return get_optimal_device() + + def torch_gc(): if torch.cuda.is_available(): - torch.cuda.empty_cache() - torch.cuda.ipc_collect() + with torch.cuda.device(get_cuda_device_string()): + torch.cuda.empty_cache() + torch.cuda.ipc_collect() def enable_tf32(): if torch.cuda.is_available(): + + # 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 + if any([torch.cuda.get_device_capability(devid) == (7, 5) for devid in range(0, torch.cuda.device_count())]): + torch.backends.cudnn.benchmark = True + torch.backends.cuda.matmul.allow_tf32 = True torch.backends.cudnn.allow_tf32 = True + errors.run(enable_tf32, "Enabling TF32") cpu = torch.device("cpu") -device = device_interrogate = device_gfpgan = device_swinir = device_esrgan = device_scunet = device_codeformer = None +device = device_interrogate = device_gfpgan = device_esrgan = device_codeformer = None dtype = torch.float16 dtype_vae = torch.float16 def randn(seed, shape): - # Pytorch currently doesn't handle setting randomness correctly when the metal backend is used. - if device.type == 'mps': - generator = torch.Generator(device=cpu) - generator.manual_seed(seed) - noise = torch.randn(shape, generator=generator, device=cpu).to(device) - return noise - torch.manual_seed(seed) + if device.type == 'mps': + return torch.randn(shape, device=cpu).to(device) return torch.randn(shape, device=device) def randn_without_seed(shape): - # Pytorch currently doesn't handle setting randomness correctly when the metal backend is used. if device.type == 'mps': - generator = torch.Generator(device=cpu) - noise = torch.randn(shape, generator=generator, device=cpu).to(device) - return noise - + return torch.randn(shape, device=cpu).to(device) return torch.randn(shape, device=device) @@ -97,9 +107,25 @@ def autocast(disable=False): # MPS workaround for https://github.com/pytorch/pytorch/issues/79383 -def mps_contiguous(input_tensor, device): - return input_tensor.contiguous() if device.type == 'mps' else input_tensor - - -def mps_contiguous_to(input_tensor, device): - return mps_contiguous(input_tensor, device).to(device) +orig_tensor_to = torch.Tensor.to +def tensor_to_fix(self, *args, **kwargs): + if self.device.type != 'mps' and \ + ((len(args) > 0 and isinstance(args[0], torch.device) and args[0].type == 'mps') or \ + (isinstance(kwargs.get('device'), torch.device) and kwargs['device'].type == 'mps')): + self = self.contiguous() + return orig_tensor_to(self, *args, **kwargs) + + +# MPS workaround for https://github.com/pytorch/pytorch/issues/80800 +orig_layer_norm = torch.nn.functional.layer_norm +def layer_norm_fix(*args, **kwargs): + if len(args) > 0 and isinstance(args[0], torch.Tensor) and args[0].device.type == 'mps': + args = list(args) + args[0] = args[0].contiguous() + return orig_layer_norm(*args, **kwargs) + + +# PyTorch 1.13 doesn't need these fixes but unfortunately is slower and has regressions that prevent training from working +if has_mps() and version.parse(torch.__version__) < version.parse("1.13"): + torch.Tensor.to = tensor_to_fix + torch.nn.functional.layer_norm = layer_norm_fix diff --git a/modules/esrgan_model.py b/modules/esrgan_model.py index c61669b4..9a9c38f1 100644 --- a/modules/esrgan_model.py +++ b/modules/esrgan_model.py @@ -199,7 +199,7 @@ def upscale_without_tiling(model, img): img = img[:, :, ::-1]
img = np.ascontiguousarray(np.transpose(img, (2, 0, 1))) / 255
img = torch.from_numpy(img).float()
- img = devices.mps_contiguous_to(img.unsqueeze(0), devices.device_esrgan)
+ img = img.unsqueeze(0).to(devices.device_esrgan)
with torch.no_grad():
output = model(img)
output = output.squeeze().float().cpu().clamp_(0, 1).numpy()
diff --git a/modules/extensions.py b/modules/extensions.py index db9c4200..b522125c 100644 --- a/modules/extensions.py +++ b/modules/extensions.py @@ -8,6 +8,7 @@ from modules import paths, shared extensions = []
extensions_dir = os.path.join(paths.script_path, "extensions")
+extensions_builtin_dir = os.path.join(paths.script_path, "extensions-builtin")
def active():
@@ -15,12 +16,13 @@ def active(): class Extension:
- def __init__(self, name, path, enabled=True):
+ def __init__(self, name, path, enabled=True, is_builtin=False):
self.name = name
self.path = path
self.enabled = enabled
self.status = ''
self.can_update = False
+ self.is_builtin = is_builtin
repo = None
try:
@@ -79,11 +81,19 @@ def list_extensions(): if not os.path.isdir(extensions_dir):
return
- for dirname in sorted(os.listdir(extensions_dir)):
- path = os.path.join(extensions_dir, dirname)
- if not os.path.isdir(path):
- continue
+ paths = []
+ for dirname in [extensions_dir, extensions_builtin_dir]:
+ if not os.path.isdir(dirname):
+ return
- extension = Extension(name=dirname, path=path, enabled=dirname not in shared.opts.disabled_extensions)
+ for extension_dirname in sorted(os.listdir(dirname)):
+ path = os.path.join(dirname, extension_dirname)
+ if not os.path.isdir(path):
+ continue
+
+ paths.append((extension_dirname, path, dirname == extensions_builtin_dir))
+
+ for dirname, path, is_builtin in paths:
+ extension = Extension(name=dirname, path=path, enabled=dirname not in shared.opts.disabled_extensions, is_builtin=is_builtin)
extensions.append(extension)
diff --git a/modules/extras.py b/modules/extras.py index 71b93a06..bc349d5e 100644 --- a/modules/extras.py +++ b/modules/extras.py @@ -1,6 +1,8 @@ from __future__ import annotations
import math
import os
+import sys
+import traceback
import numpy as np
from PIL import Image
@@ -12,7 +14,7 @@ from typing import Callable, List, OrderedDict, Tuple from functools import partial
from dataclasses import dataclass
-from modules import processing, shared, images, devices, sd_models
+from modules import processing, shared, images, devices, sd_models, sd_samplers
from modules.shared import opts
import modules.gfpgan_model
from modules.ui import plaintext_to_html
@@ -20,7 +22,7 @@ import modules.codeformer_model import piexif
import piexif.helper
import gradio as gr
-
+import safetensors.torch
class LruCache(OrderedDict):
@dataclass(frozen=True)
@@ -213,25 +215,8 @@ def run_pnginfo(image): if image is None:
return '', '', ''
- items = image.info
- geninfo = ''
-
- if "exif" in image.info:
- exif = piexif.load(image.info["exif"])
- exif_comment = (exif or {}).get("Exif", {}).get(piexif.ExifIFD.UserComment, b'')
- try:
- exif_comment = piexif.helper.UserComment.load(exif_comment)
- except ValueError:
- exif_comment = exif_comment.decode('utf8', errors="ignore")
-
- items['exif comment'] = exif_comment
- geninfo = exif_comment
-
- for field in ['jfif', 'jfif_version', 'jfif_unit', 'jfif_density', 'dpi', 'exif',
- 'loop', 'background', 'timestamp', 'duration']:
- items.pop(field, None)
-
- geninfo = items.get('parameters', geninfo)
+ geninfo, items = images.read_info_from_image(image)
+ items = {**{'parameters': geninfo}, **items}
info = ''
for key, text in items.items():
@@ -249,7 +234,7 @@ def run_pnginfo(image): return '', geninfo, info
-def run_modelmerger(primary_model_name, secondary_model_name, teritary_model_name, interp_method, multiplier, save_as_half, custom_name):
+def run_modelmerger(primary_model_name, secondary_model_name, teritary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format):
def weighted_sum(theta0, theta1, alpha):
return ((1 - alpha) * theta0) + (alpha * theta1)
@@ -262,21 +247,18 @@ def run_modelmerger(primary_model_name, secondary_model_name, teritary_model_nam primary_model_info = sd_models.checkpoints_list[primary_model_name]
secondary_model_info = sd_models.checkpoints_list[secondary_model_name]
teritary_model_info = sd_models.checkpoints_list.get(teritary_model_name, None)
+ result_is_inpainting_model = False
print(f"Loading {primary_model_info.filename}...")
- primary_model = torch.load(primary_model_info.filename, map_location='cpu')
- theta_0 = sd_models.get_state_dict_from_checkpoint(primary_model)
+ theta_0 = sd_models.read_state_dict(primary_model_info.filename, map_location='cpu')
print(f"Loading {secondary_model_info.filename}...")
- secondary_model = torch.load(secondary_model_info.filename, map_location='cpu')
- theta_1 = sd_models.get_state_dict_from_checkpoint(secondary_model)
+ theta_1 = sd_models.read_state_dict(secondary_model_info.filename, map_location='cpu')
if teritary_model_info is not None:
print(f"Loading {teritary_model_info.filename}...")
- teritary_model = torch.load(teritary_model_info.filename, map_location='cpu')
- theta_2 = sd_models.get_state_dict_from_checkpoint(teritary_model)
+ theta_2 = sd_models.read_state_dict(teritary_model_info.filename, map_location='cpu')
else:
- teritary_model = None
theta_2 = None
theta_funcs = {
@@ -295,12 +277,26 @@ def run_modelmerger(primary_model_name, secondary_model_name, teritary_model_nam theta_1[key] = theta_func1(theta_1[key], t2)
else:
theta_1[key] = torch.zeros_like(theta_1[key])
- del theta_2, teritary_model
+ del theta_2
for key in tqdm.tqdm(theta_0.keys()):
if 'model' in key and key in theta_1:
+ a = theta_0[key]
+ b = theta_1[key]
+
+ # this enables merging an inpainting model (A) with another one (B);
+ # where normal model would have 4 channels, for latenst space, inpainting model would
+ # have another 4 channels for unmasked picture's latent space, plus one channel for mask, for a total of 9
+ if a.shape != b.shape and a.shape[0:1] + a.shape[2:] == b.shape[0:1] + b.shape[2:]:
+ if a.shape[1] == 4 and b.shape[1] == 9:
+ raise RuntimeError("When merging inpainting model with a normal one, A must be the inpainting model.")
- theta_0[key] = theta_func2(theta_0[key], theta_1[key], multiplier)
+ assert a.shape[1] == 9 and b.shape[1] == 4, f"Bad dimensions for merged layer {key}: A={a.shape}, B={b.shape}"
+
+ theta_0[key][:, 0:4, :, :] = theta_func2(a[:, 0:4, :, :], b, multiplier)
+ result_is_inpainting_model = True
+ else:
+ theta_0[key] = theta_func2(a, b, multiplier)
if save_as_half:
theta_0[key] = theta_0[key].half()
@@ -314,12 +310,25 @@ def run_modelmerger(primary_model_name, secondary_model_name, teritary_model_nam ckpt_dir = shared.cmd_opts.ckpt_dir or sd_models.model_path
- filename = primary_model_info.model_name + '_' + str(round(1-multiplier, 2)) + '-' + secondary_model_info.model_name + '_' + str(round(multiplier, 2)) + '-' + interp_method.replace(" ", "_") + '-merged.ckpt'
- filename = filename if custom_name == '' else (custom_name + '.ckpt')
+ filename = \
+ primary_model_info.model_name + '_' + str(round(1-multiplier, 2)) + '-' + \
+ secondary_model_info.model_name + '_' + str(round(multiplier, 2)) + '-' + \
+ interp_method.replace(" ", "_") + \
+ '-merged.' + \
+ ("inpainting." if result_is_inpainting_model else "") + \
+ checkpoint_format
+
+ filename = filename if custom_name == '' else (custom_name + '.' + checkpoint_format)
+
output_modelname = os.path.join(ckpt_dir, filename)
print(f"Saving to {output_modelname}...")
- torch.save(primary_model, output_modelname)
+
+ _, extension = os.path.splitext(output_modelname)
+ if extension.lower() == ".safetensors":
+ safetensors.torch.save_file(theta_0, output_modelname, metadata={"format": "pt"})
+ else:
+ torch.save(theta_0, output_modelname)
sd_models.list_models()
diff --git a/modules/generation_parameters_copypaste.py b/modules/generation_parameters_copypaste.py index 1408ea05..44fe1a6c 100644 --- a/modules/generation_parameters_copypaste.py +++ b/modules/generation_parameters_copypaste.py @@ -2,6 +2,8 @@ import base64 import io
import os
import re
+from pathlib import Path
+
import gradio as gr
from modules.shared import script_path
from modules import shared
@@ -35,9 +37,8 @@ def quote(text): def image_from_url_text(filedata):
if type(filedata) == dict and filedata["is_file"]:
filename = filedata["name"]
- tempdir = os.path.normpath(tempfile.gettempdir())
- normfn = os.path.normpath(filename)
- assert normfn.startswith(tempdir), 'trying to open image file not in temporary directory'
+ is_in_right_dir = any(Path(temp_dir).resolve() in Path(filename).resolve().parents for temp_dir in shared.demo.temp_dirs)
+ assert is_in_right_dir, 'trying to open image file outside of allowed directories'
return Image.open(filename)
@@ -75,6 +76,7 @@ def integrate_settings_paste_fields(component_dict): 'CLIP_stop_at_last_layers': 'Clip skip',
'inpainting_mask_weight': 'Conditional mask weight',
'sd_model_checkpoint': 'Model hash',
+ 'eta_noise_seed_delta': 'ENSD',
}
settings_paste_fields = [
(component_dict[k], lambda d, k=k, v=v: ui.apply_setting(k, d.get(v, None)))
@@ -182,6 +184,10 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model else:
res[k] = v
+ # Missing CLIP skip means it was set to 1 (the default)
+ if "Clip skip" not in res:
+ res["Clip skip"] = "1"
+
return res
diff --git a/modules/gfpgan_model.py b/modules/gfpgan_model.py index a9452dce..1e2dbc32 100644 --- a/modules/gfpgan_model.py +++ b/modules/gfpgan_model.py @@ -36,7 +36,9 @@ def gfpgann(): else:
print("Unable to load gfpgan model!")
return None
- model = gfpgan_constructor(model_path=model_file, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None)
+ if hasattr(facexlib.detection.retinaface, 'device'):
+ facexlib.detection.retinaface.device = devices.device_gfpgan
+ model = gfpgan_constructor(model_path=model_file, upscale=1, arch='clean', channel_multiplier=2, bg_upsampler=None, device=devices.device_gfpgan)
loaded_gfpgan_model = model
return model
diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py index fbb87dd1..c406ffb3 100644 --- a/modules/hypernetworks/hypernetwork.py +++ b/ |