Unverified Commit 0831ab47 authored by zhaohu xing's avatar zhaohu xing Committed by GitHub

Merge branch 'master' into master

parents ee3f5ea3 4b3c5bc2
name: Run basic features tests on CPU with empty SD model
on:
- push
- pull_request
jobs:
test:
runs-on: ubuntu-latest
steps:
- name: Checkout Code
uses: actions/checkout@v3
- name: Set up Python 3.10
uses: actions/setup-python@v4
with:
python-version: 3.10.6
- uses: actions/cache@v3
with:
path: ~/.cache/pip
key: ${{ runner.os }}-pip-${{ hashFiles('**/requirements.txt') }}
restore-keys: ${{ runner.os }}-pip-
- name: Run tests
run: python launch.py --tests basic_features --no-half --disable-opt-split-attention --use-cpu all --skip-torch-cuda-test
- name: Upload main app stdout-stderr
uses: actions/upload-artifact@v3
if: always()
with:
name: stdout-stderr
path: |
test/stdout.txt
test/stderr.txt
__pycache__
*.ckpt
*.safetensors
*.pth
/ESRGAN/*
/SwinIR/*
......
......@@ -84,26 +84,7 @@ Check the [custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-web
- API
- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML.
- via extension: [Aesthetic Gradients](https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients), a way to generate images with a specific aesthetic by using clip images embds (implementation of [https://github.com/vicgalle/stable-diffusion-aesthetic-gradients](https://github.com/vicgalle/stable-diffusion-aesthetic-gradients))
## Where are Aesthetic Gradients?!?!
Aesthetic Gradients are now an extension. You can install it using git:
```commandline
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients extensions/aesthetic-gradients
```
After running this command, make sure that you have `aesthetic-gradients` dir in webui's `extensions` directory and restart
the UI. The interface for Aesthetic Gradients should appear exactly the same as it was.
## Where is History/Image browser?!?!
Image browser is now an extension. You can install it using git:
```commandline
git clone https://github.com/yfszzx/stable-diffusion-webui-images-browser extensions/images-browser
```
After running this command, make sure that you have `images-browser` dir in webui's `extensions` directory and restart
the UI. The interface for Image browser should appear exactly the same as it was.
- [Stable Diffusion 2.0](https://github.com/Stability-AI/stablediffusion) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20) for instructions
## Installation and Running
Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
......
......@@ -62,8 +62,8 @@ titles = {
"Interrogate": "Reconstruct prompt from existing image and put it into the prompt field.",
"Images filename pattern": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
"Directory name pattern": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
"Images filename pattern": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
"Directory name pattern": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
"Max prompt words": "Set the maximum number of words to be used in the [prompt_words] option; ATTENTION: If the words are too long, they may exceed the maximum length of the file path that the system can handle",
"Loopback": "Process an image, use it as an input, repeat.",
......
......@@ -23,7 +23,7 @@ function check_progressbar(id_part, id_progressbar, id_progressbar_span, id_skip
if(opts.show_progress_in_title && progressbar && progressbar.offsetParent){
if(progressbar.innerText){
let newtitle = 'Stable Diffusion - ' + progressbar.innerText
let newtitle = '[' + progressbar.innerText.trim() + '] Stable Diffusion';
if(document.title != newtitle){
document.title = newtitle;
}
......
......@@ -8,8 +8,8 @@ function set_theme(theme){
}
function selected_gallery_index(){
var buttons = gradioApp().querySelectorAll('[style="display: block;"].tabitem .gallery-item')
var button = gradioApp().querySelector('[style="display: block;"].tabitem .gallery-item.\\!ring-2')
var buttons = gradioApp().querySelectorAll('[style="display: block;"].tabitem div[id$=_gallery] .gallery-item')
var button = gradioApp().querySelector('[style="display: block;"].tabitem div[id$=_gallery] .gallery-item.\\!ring-2')
var result = -1
buttons.forEach(function(v, i){ if(v==button) { result = i } })
......
......@@ -5,6 +5,8 @@ import sys
import importlib.util
import shlex
import platform
import argparse
import json
dir_repos = "repositories"
dir_extensions = "extensions"
......@@ -17,6 +19,19 @@ def extract_arg(args, name):
return [x for x in args if x != name], name in args
def extract_opt(args, name):
opt = None
is_present = False
if name in args:
is_present = True
idx = args.index(name)
del args[idx]
if idx < len(args) and args[idx][0] != "-":
opt = args[idx]
del args[idx]
return args, is_present, opt
def run(command, desc=None, errdesc=None, custom_env=None):
if desc is not None:
print(desc)
......@@ -119,11 +134,26 @@ def run_extension_installer(extension_dir):
print(e, file=sys.stderr)
def run_extensions_installers():
def list_extensions(settings_file):
settings = {}
try:
if os.path.isfile(settings_file):
with open(settings_file, "r", encoding="utf8") as file:
settings = json.load(file)
except Exception as e:
print(e, file=sys.stderr)
disabled_extensions = set(settings.get('disabled_extensions', []))
return [x for x in os.listdir(dir_extensions) if x not in disabled_extensions]
def run_extensions_installers(settings_file):
if not os.path.isdir(dir_extensions):
return
for dirname_extension in os.listdir(dir_extensions):
for dirname_extension in list_extensions(settings_file):
run_extension_installer(os.path.join(dir_extensions, dirname_extension))
......@@ -134,28 +164,32 @@ def prepare_enviroment():
gfpgan_package = os.environ.get('GFPGAN_PACKAGE', "git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379")
clip_package = os.environ.get('CLIP_PACKAGE', "git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1")
openclip_package = os.environ.get('OPENCLIP_PACKAGE', "git+https://github.com/mlfoundations/open_clip.git@bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b")
xformers_windows_package = os.environ.get('XFORMERS_WINDOWS_PACKAGE', 'https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/f/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl')
stable_diffusion_repo = os.environ.get('STABLE_DIFFUSION_REPO', "https://github.com/CompVis/stable-diffusion.git")
stable_diffusion_repo = os.environ.get('STABLE_DIFFUSION_REPO', "https://github.com/Stability-AI/stablediffusion.git")
taming_transformers_repo = os.environ.get('TAMING_TRANSFORMERS_REPO', "https://github.com/CompVis/taming-transformers.git")
k_diffusion_repo = os.environ.get('K_DIFFUSION_REPO', 'https://github.com/crowsonkb/k-diffusion.git')
codeformer_repo = os.environ.get('CODEFORMER_REPO', 'https://github.com/sczhou/CodeFormer.git')
blip_repo = os.environ.get('BLIP_REPO', 'https://github.com/salesforce/BLIP.git')
stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "69ae4b35e0a0f6ee1af8bb9a5d0016ccb27e36dc")
stable_diffusion_commit_hash = os.environ.get('STABLE_DIFFUSION_COMMIT_HASH', "47b6b607fdd31875c9279cd2f4f16b92e4ea958e")
taming_transformers_commit_hash = os.environ.get('TAMING_TRANSFORMERS_COMMIT_HASH', "24268930bf1dce879235a7fddd0b2355b84d7ea6")
k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "60e5042ca0da89c14d1dd59d73883280f8fce991")
k_diffusion_commit_hash = os.environ.get('K_DIFFUSION_COMMIT_HASH', "5b3af030dd83e0297272d861c19477735d0317ec")
codeformer_commit_hash = os.environ.get('CODEFORMER_COMMIT_HASH', "c5b4593074ba6214284d6acd5f1719b6c5d739af")
blip_commit_hash = os.environ.get('BLIP_COMMIT_HASH', "48211a1594f1321b00f14c9f7a5b4813144b2fb9")
sys.argv += shlex.split(commandline_args)
test_argv = [x for x in sys.argv if x != '--tests']
parser = argparse.ArgumentParser()
parser.add_argument("--ui-settings-file", type=str, help="filename to use for ui settings", default='config.json')
args, _ = parser.parse_known_args(sys.argv)
sys.argv, skip_torch_cuda_test = extract_arg(sys.argv, '--skip-torch-cuda-test')
sys.argv, reinstall_xformers = extract_arg(sys.argv, '--reinstall-xformers')
sys.argv, update_check = extract_arg(sys.argv, '--update-check')
sys.argv, run_tests = extract_arg(sys.argv, '--tests')
sys.argv, run_tests, test_dir = extract_opt(sys.argv, '--tests')
xformers = '--xformers' in sys.argv
ngrok = '--ngrok' in sys.argv
......@@ -179,6 +213,9 @@ def prepare_enviroment():
if not is_installed("clip"):
run_pip(f"install {clip_package}", "clip")
if not is_installed("open_clip"):
run_pip(f"install {openclip_package}", "open_clip")
if (not is_installed("xformers") or reinstall_xformers) and xformers:
if platform.system() == "Windows":
if platform.python_version().startswith("3.10"):
......@@ -196,7 +233,7 @@ def prepare_enviroment():
os.makedirs(dir_repos, exist_ok=True)
git_clone(stable_diffusion_repo, repo_dir('stable-diffusion'), "Stable Diffusion", stable_diffusion_commit_hash)
git_clone(stable_diffusion_repo, repo_dir('stable-diffusion-stability-ai'), "Stable Diffusion", stable_diffusion_commit_hash)
git_clone(taming_transformers_repo, repo_dir('taming-transformers'), "Taming Transformers", taming_transformers_commit_hash)
git_clone(k_diffusion_repo, repo_dir('k-diffusion'), "K-diffusion", k_diffusion_commit_hash)
git_clone(codeformer_repo, repo_dir('CodeFormer'), "CodeFormer", codeformer_commit_hash)
......@@ -207,7 +244,7 @@ def prepare_enviroment():
run_pip(f"install -r {requirements_file}", "requirements for Web UI")
run_extensions_installers()
run_extensions_installers(settings_file=args.ui_settings_file)
if update_check:
version_check(commit)
......@@ -217,24 +254,30 @@ def prepare_enviroment():
exit(0)
if run_tests:
tests(test_argv)
exit(0)
exitcode = tests(test_dir)
exit(exitcode)
def tests(argv):
if "--api" not in argv:
argv.append("--api")
def tests(test_dir):
if "--api" not in sys.argv:
sys.argv.append("--api")
if "--ckpt" not in sys.argv:
sys.argv.append("--ckpt")
sys.argv.append("./test/test_files/empty.pt")
if "--skip-torch-cuda-test" not in sys.argv:
sys.argv.append("--skip-torch-cuda-test")
print(f"Launching Web UI in another process for testing with arguments: {' '.join(argv[1:])}")
print(f"Launching Web UI in another process for testing with arguments: {' '.join(sys.argv[1:])}")
with open('test/stdout.txt', "w", encoding="utf8") as stdout, open('test/stderr.txt', "w", encoding="utf8") as stderr:
proc = subprocess.Popen([sys.executable, *argv], stdout=stdout, stderr=stderr)
proc = subprocess.Popen([sys.executable, *sys.argv], stdout=stdout, stderr=stderr)
import test.server_poll
test.server_poll.run_tests()
exitcode = test.server_poll.run_tests(proc, test_dir)
print(f"Stopping Web UI process with id {proc.pid}")
proc.kill()
return exitcode
def start():
......
......@@ -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
......@@ -137,12 +144,14 @@ 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
}
)
if populate.sampler_name:
populate.sampler_index = None # prevent a warning later on
p = StableDiffusionProcessingImg2Img(**vars(populate))
imgs = []
......@@ -305,7 +314,7 @@ 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
......
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
......@@ -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
......
......@@ -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 = {}
......
......@@ -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")
......@@ -44,8 +46,9 @@ def 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():
......@@ -97,9 +100,25 @@ 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
......@@ -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()
......
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)
......@@ -264,19 +249,15 @@ def run_modelmerger(primary_model_name, secondary_model_name, teritary_model_nam
teritary_model_info = sd_models.checkpoints_list.get(teritary_model_name, None)
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 = {
......@@ -295,7 +276,7 @@ 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:
......@@ -314,12 +295,17 @@ 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.' + 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()
......
......@@ -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)))
......
......@@ -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
......
This diff is collapsed.
......@@ -15,6 +15,7 @@ import piexif.helper
from PIL import Image, ImageFont, ImageDraw, PngImagePlugin
from fonts.ttf import Roboto
import string
import json
from modules import sd_samplers, shared, script_callbacks
from modules.shared import opts, cmd_opts
......@@ -305,6 +306,7 @@ class FilenameGenerator:
'styles': lambda self: self.p and sanitize_filename_part(", ".join([style for style in self.p.styles if not style == "None"]) or "None", replace_spaces=False),
'sampler': lambda self: self.p and sanitize_filename_part(self.p.sampler_name, replace_spaces=False),
'model_hash': lambda self: getattr(self.p, "sd_model_hash", shared.sd_model.sd_model_hash),
'model_name': lambda self: sanitize_filename_part(shared.sd_model.sd_checkpoint_info.model_name, replace_spaces=False),
'date': lambda self: datetime.datetime.now().strftime('%Y-%m-%d'),
'datetime': lambda self, *args: self.datetime(*args), # accepts formats: [datetime], [datetime<Format>], [datetime<Format><Time Zone>]
'job_timestamp': lambda self: getattr(self.p, "job_timestamp", shared.state.job_timestamp),
......@@ -524,6 +526,8 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
else:
image.save(fullfn, quality=opts.jpeg_quality)
image.already_saved_as = fullfn
target_side_length = 4000
oversize = image.width > target_side_length or image.height > target_side_length
if opts.export_for_4chan and (oversize or os.stat(fullfn).st_size > 4 * 1024 * 1024):
......@@ -550,10 +554,45 @@ def save_image(image, path, basename, seed=None, prompt=None, extension='png', i
return fullfn, txt_fullfn
def read_info_from_image(image):
items = image.info or {}
geninfo = items.pop('parameters', None)
if "exif" in items:
exif = piexif.load(items["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)
if items.get("Software", None) == "NovelAI":
try:
json_info = json.loads(items["Comment"])
sampler = sd_samplers.samplers_map.get(json_info["sampler"], "Euler a")
geninfo = f"""{items["Description"]}
Negative prompt: {json_info["uc"]}
Steps: {json_info["steps"]}, Sampler: {sampler}, CFG scale: {json_info["scale"]}, Seed: {json_info["seed"]}, Size: {image.width}x{image.height}, Clip skip: 2, ENSD: 31337"""
except Exception:
print(f"Error parsing NovelAI iamge generation parameters:", file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)
return geninfo, items
def image_data(data):
try:
image = Image.open(io.BytesIO(data))
textinfo = image.text["parameters"]
textinfo, _ = read_info_from_image(image)
return textinfo, None
except Exception:
pass
......
......@@ -99,7 +99,7 @@ def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, pro
seed_resize_from_h=seed_resize_from_h,
seed_resize_from_w=seed_resize_from_w,
seed_enable_extras=seed_enable_extras,
sampler_index=sd_samplers.samplers_for_img2img[sampler_index].name,
sampler_name=sd_samplers.samplers_for_img2img[sampler_index].name,
batch_size=batch_size,
n_iter=n_iter,
steps=steps,
......
......@@ -51,6 +51,10 @@ def setup_for_low_vram(sd_model, use_medvram):
send_me_to_gpu(first_stage_model, None)
return first_stage_model_decode(z)
# for SD1, cond_stage_model is CLIP and its NN is in the tranformer frield, but for SD2, it's open clip, and it's in model field
if hasattr(sd_model.cond_stage_model, 'model'):
sd_model.cond_stage_model.transformer = sd_model.cond_stage_model.model
# remove three big modules, cond, first_stage, and unet from the model and then
# send the model to GPU. Then put modules back. the modules will be in CPU.
stored = sd_model.cond_stage_model.transformer, sd_model.first_stage_model, sd_model.model
......@@ -65,6 +69,10 @@ def setup_for_low_vram(sd_model, use_medvram):
sd_model.first_stage_model.decode = first_stage_model_decode_wrap
parents[sd_model.cond_stage_model.transformer] = sd_model.cond_stage_model
if hasattr(sd_model.cond_stage_model, 'model'):
sd_model.cond_stage_model.model = sd_model.cond_stage_model.transformer
del sd_model.cond_stage_model.transformer
if use_medvram:
sd_model.model.register_forward_pre_hook(send_me_to_gpu)
else:
......
......@@ -82,6 +82,7 @@ def cleanup_models():
src_path = models_path
dest_path = os.path.join(models_path, "Stable-diffusion")
move_files(src_path, dest_path, ".ckpt")
move_files(src_path, dest_path, ".safetensors")
src_path = os.path.join(root_path, "ESRGAN")
dest_path = os.path.join(models_path, "ESRGAN")
move_files(src_path, dest_path)
......
......@@ -15,9 +15,9 @@ def connect(token, port, region):
)
try:
if account == None:
public_url = ngrok.connect(port, pyngrok_config=config).public_url
public_url = ngrok.connect(port, pyngrok_config=config, bind_tls=True).public_url
else:
public_url = ngrok.connect(port, pyngrok_config=config, auth=account).public_url
public_url = ngrok.connect(port, pyngrok_config=config, bind_tls=True, auth=account).public_url
except exception.PyngrokNgrokError:
print(f'Invalid ngrok authtoken, ngrok connection aborted.\n'
f'Your token: {token}, get the right one on https://dashboard.ngrok.com/get-started/your-authtoken')
......
......@@ -9,7 +9,7 @@ sys.path.insert(0, script_path)
# search for directory of stable diffusion in following places
sd_path = None
possible_sd_paths = [os.path.join(script_path, 'repositories/stable-diffusion'), '.', os.path.dirname(script_path)]
possible_sd_paths = [os.path.join(script_path, 'repositories/stable-diffusion-stability-ai'), '.', os.path.dirname(script_path)]
for possible_sd_path in possible_sd_paths:
if os.path.exists(os.path.join(possible_sd_path, 'ldm/models/diffusion/ddpm.py')):
sd_path = os.path.abspath(possible_sd_path)
......
......@@ -74,7 +74,7 @@ class StableDiffusionProcessing():
"""
def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str = "", styles: List[str] = None, seed: int = -1, subseed: int = -1, subseed_strength: float = 0, seed_resize_from_h: int = -1, seed_resize_from_w: int = -1, seed_enable_extras: bool = True, sampler_name: str = None, batch_size: int = 1, n_iter: int = 1, steps: int = 50, cfg_scale: float = 7.0, width: int = 512, height: int = 512, restore_faces: bool = False, tiling: bool = False, do_not_save_samples: bool = False, do_not_save_grid: bool = False, extra_generation_params: Dict[Any, Any] = None, overlay_images: Any = None, negative_prompt: str = None, eta: float = None, do_not_reload_embeddings: bool = False, denoising_strength: float = 0, ddim_discretize: str = None, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0, override_settings: Dict[str, Any] = None, sampler_index: int = None):
if sampler_index is not None:
warnings.warn("sampler_index argument for StableDiffusionProcessing does not do anything; use sampler_name")
print("sampler_index argument for StableDiffusionProcessing does not do anything; use sampler_name", file=sys.stderr)
self.sd_model = sd_model
self.outpath_samples: str = outpath_samples
......
......@@ -54,7 +54,7 @@ class UpscalerScuNET(modules.upscaler.Upscaler):
img = img[:, :, ::-1]
img = np.moveaxis(img, 2, 0) / 255
img = torch.from_numpy(img).float()
img = devices.mps_contiguous_to(img.unsqueeze(0), device)
img = img.unsqueeze(0).to(device)
with torch.no_grad():
output = model(img)
......
This diff is collapsed.
from torch.utils.checkpoint import checkpoint
def BasicTransformerBlock_forward(self, x, context=None):
return checkpoint(self._forward, x, context)
def AttentionBlock_forward(self, x):
return checkpoint(self._forward, x)
def ResBlock_forward(self, x, emb):
return checkpoint(self._forward, x, emb)
\ No newline at end of file
This diff is collapsed.
......@@ -199,8 +199,8 @@ def sample_plms(self,
@torch.no_grad()
def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
unconditional_guidance_scale=1., unconditional_conditioning=None, old_eps=None, t_next=None):
temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
unconditional_guidance_scale=1., unconditional_conditioning=None, old_eps=None, t_next=None, dynamic_threshold=None):
b, *_, device = *x.shape, x.device
def get_model_output(x, t):
......@@ -249,6 +249,8 @@ def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=F
pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt()
if quantize_denoised:
pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0)
if dynamic_threshold is not None:
pred_x0 = norm_thresholding(pred_x0, dynamic_threshold)
# direction pointing to x_t
dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t
noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature
......@@ -321,12 +323,16 @@ def should_hijack_inpainting(checkpoint_info):
def do_inpainting_hijack():
ldm.models.diffusion.ddpm.get_unconditional_conditioning = get_unconditional_conditioning
# most of this stuff seems to no longer be needed because it is already included into SD2.0
# LatentInpaintDiffusion remains because SD2.0's LatentInpaintDiffusion can't be loaded without specifying a checkpoint
# p_sample_plms is needed because PLMS can't work with dicts as conditionings
# this file should be cleaned up later if weverything tuens out to work fine
# ldm.models.diffusion.ddpm.get_unconditional_conditioning = get_unconditional_conditioning
ldm.models.diffusion.ddpm.LatentInpaintDiffusion = LatentInpaintDiffusion
ldm.models.diffusion.ddim.DDIMSampler.p_sample_ddim = p_sample_ddim
ldm.models.diffusion.ddim.DDIMSampler.sample = sample_ddim
# ldm.models.diffusion.ddim.DDIMSampler.p_sample_ddim = p_sample_ddim
# ldm.models.diffusion.ddim.DDIMSampler.sample = sample_ddim
ldm.models.diffusion.plms.PLMSSampler.p_sample_plms = p_sample_plms
ldm.models.diffusion.plms.PLMSSampler.sample = sample_plms
# ldm.models.diffusion.plms.PLMSSampler.sample = sample_plms
import open_clip.tokenizer
import torch
from modules import sd_hijack_clip, devices
from modules.shared import opts
tokenizer = open_clip.tokenizer._tokenizer
class FrozenOpenCLIPEmbedderWithCustomWords(sd_hijack_clip.FrozenCLIPEmbedderWithCustomWordsBase):
def __init__(self, wrapped, hijack):
super().__init__(wrapped, hijack)
self.comma_token = [v for k, v in tokenizer.encoder.items() if k == ',</w>'][0]
self.id_start = tokenizer.encoder["<start_of_text>"]
self.id_end = tokenizer.encoder["<end_of_text>"]
self.id_pad = 0
def tokenize(self, texts):
assert not opts.use_old_emphasis_implementation, 'Old emphasis implementation not supported for Open Clip'
tokenized = [tokenizer.encode(text) for text in texts]
return tokenized
def encode_with_transformers(self, tokens):
# set self.wrapped.layer_idx here according to opts.CLIP_stop_at_last_layers
z = self.wrapped.encode_with_transformer(tokens)
return z
def encode_embedding_init_text(self, init_text, nvpt):
ids = tokenizer.encode(init_text)
ids = torch.asarray([ids], device=devices.device, dtype=torch.int)
embedded = self.wrapped.model.token_embedding.wrapped(ids).squeeze(0)
return embedded
......@@ -5,6 +5,7 @@ import gc
from collections import namedtuple
import torch
import re
import safetensors.torch
from omegaconf import OmegaConf
from ldm.util import instantiate_from_config
......@@ -45,7 +46,7 @@ def checkpoint_tiles():
def list_models():
checkpoints_list.clear()
model_list = modelloader.load_models(model_path=model_path, command_path=shared.cmd_opts.ckpt_dir, ext_filter=[".ckpt"])
model_list = modelloader.load_models(model_path=model_path, command_path=shared.cmd_opts.ckpt_dir, ext_filter=[".ckpt", ".safetensors"])
def modeltitle(path, shorthash):
abspath = os.path.abspath(path)
......@@ -143,8 +144,8 @@ def transform_checkpoint_dict_key(k):
def get_state_dict_from_checkpoint(pl_sd):
if "state_dict" in pl_sd:
pl_sd = pl_sd["state_dict"]
pl_sd = pl_sd.pop("state_dict", pl_sd)
pl_sd.pop("state_dict", None)
sd = {}
for k, v in pl_sd.items():
......@@ -159,6 +160,20 @@ def get_state_dict_from_checkpoint(pl_sd):
return pl_sd
def read_state_dict(checkpoint_file, print_global_state=False, map_location=None):
_, extension = os.path.splitext(checkpoint_file)
if extension.lower() == ".safetensors":
pl_sd = safetensors.torch.load_file(checkpoint_file, device=map_location or shared.weight_load_location)
else:
pl_sd = torch.load(checkpoint_file, map_location=map_location or shared.weight_load_location)
if print_global_state and "global_step" in pl_sd:
print(f"Global Step: {pl_sd['global_step']}")
sd = get_state_dict_from_checkpoint(pl_sd)
return sd
def load_model_weights(model, checkpoint_info, vae_file="auto"):
checkpoint_file = checkpoint_info.filename
sd_model_hash = checkpoint_info.hash
......@@ -173,12 +188,7 @@ def load_model_weights(model, checkpoint_info, vae_file="auto"):
# load from file
print(f"Loading weights [{sd_model_hash}] from {checkpoint_file}")
pl_sd = torch.load(checkpoint_file, map_location=shared.weight_load_location)
if "global_step" in pl_sd:
print(f"Global Step: {pl_sd['global_step']}")
sd = get_state_dict_from_checkpoint(pl_sd)
del pl_sd
sd = read_state_dict(checkpoint_file)
model.load_state_dict(sd, strict=False)
del sd
......@@ -244,6 +254,9 @@ def load_model(checkpoint_info=None):
do_inpainting_hijack()
if shared.cmd_opts.no_half:
sd_config.model.params.unet_config.params.use_fp16 = False
sd_model = instantiate_from_config(sd_config.model)
load_model_weights(sd_model, checkpoint_info)
......
from collections import namedtuple
from collections import namedtuple, deque
import numpy as np
from math import floor
import torch
......@@ -18,7 +18,7 @@ from modules.script_callbacks import CFGDenoiserParams, cfg_denoiser_callback
SamplerData = namedtuple('SamplerData', ['name', 'constructor', 'aliases', 'options'])
samplers_k_diffusion = [
('Euler a', 'sample_euler_ancestral', ['k_euler_a'], {}),
('Euler a', 'sample_euler_ancestral', ['k_euler_a', 'k_euler_ancestral'], {}),
('Euler', 'sample_euler', ['k_euler'], {}),
('LMS', 'sample_lms', ['k_lms'], {}),
('Heun', 'sample_heun', ['k_heun'], {}),
......@@ -26,6 +26,7 @@ samplers_k_diffusion = [
('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {}),
('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}),
('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}),
('DPM++ SDE', 'sample_dpmpp_sde', ['k_dpmpp_sde'], {}),
('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {}),
('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {}),
('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}),
......@@ -33,6 +34,7 @@ samplers_k_diffusion = [
('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras'}),
('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}),
('DPM++ 2M Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}),
('DPM++ SDE Karras', 'sample_dpmpp_sde', ['k_dpmpp_sde_ka'], {'scheduler': 'karras'}),
]
samplers_data_k_diffusion = [
......@@ -50,6 +52,7 @@ all_samplers_map = {x.name: x for x in all_samplers}
samplers = []
samplers_for_img2img = []
samplers_map = {}
def create_sampler(name, model):
......@@ -75,6 +78,12 @@ def set_samplers():
samplers = [x for x in all_samplers if x.name not in hidden]
samplers_for_img2img = [x for x in all_samplers if x.name not in hidden_img2img]
samplers_map.clear()
for sampler in all_samplers:
samplers_map[sampler.name.lower()] = sampler.name
for alias in sampler.aliases:
samplers_map[alias.lower()] = sampler.name
set_samplers()
......@@ -127,7 +136,8 @@ class InterruptedException(BaseException):
class VanillaStableDiffusionSampler:
def __init__(self, constructor, sd_model):
self.sampler = constructor(sd_model)
self.orig_p_sample_ddim = self.sampler.p_sample_ddim if hasattr(self.sampler, 'p_sample_ddim') else self.sampler.p_sample_plms
self.is_plms = hasattr(self.sampler, 'p_sample_plms')
self.orig_p_sample_ddim = self.sampler.p_sample_plms if self.is_plms else self.sampler.p_sample_ddim
self.mask = None
self.nmask = None
self.init_latent = None
......@@ -218,7 +228,6 @@ class VanillaStableDiffusionSampler:
self.mask = p.mask if hasattr(p, 'mask') else None
self.nmask = p.nmask if hasattr(p, 'nmask') else None
def adjust_steps_if_invalid(self, p, num_steps):
if (self.config.name == 'DDIM' and p.ddim_discretize == 'uniform') or (self.config.name == 'PLMS'):
valid_step = 999 / (1000 // num_steps)
......@@ -227,7 +236,6 @@ class VanillaStableDiffusionSampler:
return num_steps
def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
steps, t_enc = setup_img2img_steps(p, steps)
steps = self.adjust_steps_if_invalid(p, steps)
......@@ -260,9 +268,10 @@ class VanillaStableDiffusionSampler:
steps = self.adjust_steps_if_invalid(p, steps or p.steps)
# Wrap the conditioning models with additional image conditioning for inpainting model
# dummy_for_plms is needed because PLMS code checks the first item in the dict to have the right shape
if image_conditioning is not None:
conditioning = {"c_concat": [image_conditioning], "c_crossattn": [conditioning]}
unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
conditioning = {"dummy_for_plms": np.zeros((conditioning.shape[0],)), "c_crossattn": [conditioning], "c_concat": [image_conditioning]}
unconditional_conditioning = {"c_crossattn": [unconditional_conditioning], "c_concat": [image_conditioning]}
samples_ddim = self.launch_sampling(steps, lambda: self.sampler.sample(S=steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)[0])
......@@ -335,28 +344,39 @@ class CFGDenoiser(torch.nn.Module):
class TorchHijack:
def __init__(self, kdiff_sampler):
self.kdiff_sampler = kdiff_sampler
def __init__(self, sampler_noises):
# Using a deque to efficiently receive the sampler_noises in the same order as the previous index-based
# implementation.
self.sampler_noises = deque(sampler_noises)
def __getattr__(self, item):
if item == 'randn_like':
return self.kdiff_sampler.randn_like
return self.randn_like
if hasattr(torch, item):
return getattr(torch, item)
raise AttributeError("'{}' object has no attribute '{}'".format(type(self).__name__, item))
def randn_like(self, x):
if self.sampler_noises:
noise = self.sampler_noises.popleft()
if noise.shape == x.shape:
return noise
return torch.randn_like(x)
class KDiffusionSampler:
def __init__(self, funcname, sd_model):
self.model_wrap = k_diffusion.external.CompVisDenoiser(sd_model, quantize=shared.opts.enable_quantization)
denoiser = k_diffusion.external.CompVisVDenoiser if sd_model.parameterization == "v" else k_diffusion.external.CompVisDenoiser
self.model_wrap = denoiser(sd_model, quantize=shared.opts.enable_quantization)
self.funcname = funcname
self.func = getattr(k_diffusion.sampling, self.funcname)
self.extra_params = sampler_extra_params.get(funcname, [])
self.model_wrap_cfg = CFGDenoiser(self.model_wrap)
self.sampler_noises = None
self.sampler_noise_index = 0
self.stop_at = None
self.eta = None
self.default_eta = 1.0
......@@ -389,26 +409,14 @@ class KDiffusionSampler:
def number_of_needed_noises(self, p):
return p.steps
def randn_like(self, x):
noise = self.sampler_noises[self.sampler_noise_index] if self.sampler_noises is not None and self.sampler_noise_index < len(self.sampler_noises) else None
if noise is not None and x.shape == noise.shape:
res = noise
else:
res = torch.randn_like(x)
self.sampler_noise_index += 1
return res
def initialize(self, p):
self.model_wrap_cfg.mask = p.mask if hasattr(p, 'mask') else None
self.model_wrap_cfg.nmask = p.nmask if hasattr(p, 'nmask') else None
self.model_wrap.step = 0
self.sampler_noise_index = 0
self.eta = p.eta or opts.eta_ancestral
if self.sampler_noises is not None:
k_diffusion.sampling.torch = TorchHijack(self)
k_diffusion.sampling.torch = TorchHijack(self.sampler_noises)
extra_params_kwargs = {}
for param_name in self.extra_params:
......
......@@ -11,13 +11,14 @@ import tqdm
import modules.artists
import modules.interrogate
import modules.memmon
import modules.sd_models
import modules.styles
import modules.devices as devices
from modules import sd_samplers, sd_models, localization, sd_vae, extensions, script_loading
from modules.hypernetworks import hypernetwork
from modules import localization, sd_vae, extensions, script_loading
from modules.paths import models_path, script_path, sd_path
demo = None
sd_model_file = os.path.join(script_path, 'model.ckpt')
default_sd_model_file = sd_model_file
parser = argparse.ArgumentParser()
......@@ -80,13 +81,14 @@ parser.add_argument("--disable-console-progressbars", action='store_true', help=
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('--vae-path', type=str, help='Path to Variational Autoencoders model', 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 with the webui")
parser.add_argument("--api-auth", type=str, help='Set authentication for api like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"', default=None)
parser.add_argument("--nowebui", action='store_true', help="use api=True to launch the api instead of the webui")
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)")
parser.add_argument("--api-auth", type=str, help='Set authentication for API like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"', default=None)
parser.add_argument("--nowebui", action='store_true', help="use api=True to launch the API instead of the webui")
parser.add_argument("--ui-debug-mode", action='store_true', help="Don't load model to quickly launch UI")
parser.add_argument("--device-id", type=str, help="Select the default CUDA device to use (export CUDA_VISIBLE_DEVICES=0,1,etc might be needed before)", default=None)
parser.add_argument("--administrator", action='store_true', help="Administrator rights", default=False)
parser.add_argument("--cors-allow-origins", type=str, help="Allowed CORS origins", default=None)
parser.add_argument("--cors-allow-origins", type=str, help="Allowed CORS origin(s) in the form of a comma-separated list (no spaces)", default=None)
parser.add_argument("--cors-allow-origins-regex", type=str, help="Allowed CORS origin(s) in the form of a single regular expression", default=None)
parser.add_argument("--tls-keyfile", type=str, help="Partially enables TLS, requires --tls-certfile to fully function", default=None)
parser.add_argument("--tls-certfile", type=str, help="Partially enables TLS, requires --tls-keyfile to fully function", default=None)
parser.add_argument("--server-name", type=str, help="Sets hostname of server", default=None)
......@@ -125,10 +127,12 @@ xformers_available = False
config_filename = cmd_opts.ui_settings_file
os.makedirs(cmd_opts.hypernetwork_dir, exist_ok=True)
hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir)
hypernetworks = {}
loaded_hypernetwork = None
def reload_hypernetworks():
from modules.hypernetworks import hypernetwork
global hypernetworks
hypernetworks = hypernetwork.list_hypernetworks(cmd_opts.hypernetwork_dir)
......@@ -210,10 +214,11 @@ class State:
if self.current_latent is None:
return
import modules.sd_samplers
if opts.show_progress_grid:
self.current_image = sd_samplers.samples_to_image_grid(self.current_latent)
self.current_image = modules.sd_samplers.samples_to_image_grid(self.current_latent)
else:
self.current_image = sd_samplers.sample_to_image(self.current_latent)
self.current_image = modules.sd_samplers.sample_to_image(self.current_latent)
self.current_image_sampling_step = self.sampling_step
......@@ -252,6 +257,21 @@ def options_section(section_identifier, options_dict):
return options_dict
def list_checkpoint_tiles():
import modules.sd_models
return modules.sd_models.checkpoint_tiles()
def refresh_checkpoints():
import modules.sd_models
return modules.sd_models.list_models()
def list_samplers():
import modules.sd_samplers
return modules.sd_samplers.all_samplers
hide_dirs = {"visible": not cmd_opts.hide_ui_dir_config}
options_templates = {}
......@@ -280,6 +300,10 @@ options_templates.update(options_section(('saving-images', "Saving images/grids"
"use_original_name_batch": OptionInfo(False, "Use original name for output filename during batch process in extras tab"),
"save_selected_only": OptionInfo(True, "When using 'Save' button, only save a single selected image"),
"do_not_add_watermark": OptionInfo(False, "Do not add watermark to images"),
"temp_dir": OptionInfo("", "Directory for temporary images; leave empty for default"),
"clean_temp_dir_at_start": OptionInfo(False, "Cleanup non-default temporary directory when starting webui"),
}))
options_templates.update(options_section(('saving-paths', "Paths for saving"), {
......@@ -304,7 +328,7 @@ options_templates.update(options_section(('saving-to-dirs', "Saving to a directo
options_templates.update(options_section(('upscaling', "Upscaling"), {
"ESRGAN_tile": OptionInfo(192, "Tile size for ESRGAN upscalers. 0 = no tiling.", gr.Slider, {"minimum": 0, "maximum": 512, "step": 16}),
"ESRGAN_tile_overlap": OptionInfo(8, "Tile overlap, in pixels for ESRGAN upscalers. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}),
"realesrgan_enabled_models": OptionInfo(["R-ESRGAN x4+", "R-ESRGAN x4+ Anime6B"], "Select which Real-ESRGAN models to show in the web UI. (Requires restart)", gr.CheckboxGroup, lambda: {"choices": realesrgan_models_names()}),
"realesrgan_enabled_models": OptionInfo(["R-ESRGAN 4x+", "R-ESRGAN 4x+ Anime6B"], "Select which Real-ESRGAN models to show in the web UI. (Requires restart)", gr.CheckboxGroup, lambda: {"choices": realesrgan_models_names()}),
"SWIN_tile": OptionInfo(192, "Tile size for all SwinIR.", gr.Slider, {"minimum": 16, "maximum": 512, "step": 16}),
"SWIN_tile_overlap": OptionInfo(8, "Tile overlap, in pixels for SwinIR. Low values = visible seam.", gr.Slider, {"minimum": 0, "maximum": 48, "step": 1}),
"ldsr_steps": OptionInfo(100, "LDSR processing steps. Lower = faster", gr.Slider, {"minimum": 1, "maximum": 200, "step": 1}),
......@@ -326,8 +350,7 @@ options_templates.update(options_section(('system', "System"), {
options_templates.update(options_section(('training', "Training"), {
"unload_models_when_training": OptionInfo(False, "Move VAE and CLIP to RAM when training if possible. Saves VRAM."),
"shuffle_tags": OptionInfo(False, "Shuffleing tags by ',' when create texts."),
"tag_drop_out": OptionInfo(0, "Dropout tags when create texts", gr.Slider, {"minimum": 0, "maximum": 1, "step": 0.1}),
"pin_memory": OptionInfo(False, "Turn on pin_memory for DataLoader. Makes training slightly faster but can increase memory usage."),
"save_optimizer_state": OptionInfo(False, "Saves Optimizer state as separate *.optim file. Training can be resumed with HN itself and matching optim file."),
"dataset_filename_word_regex": OptionInfo("", "Filename word regex"),
"dataset_filename_join_string": OptionInfo(" ", "Filename join string"),
......@@ -337,7 +360,7 @@ options_templates.update(options_section(('training', "Training"), {
}))
options_templates.update(options_section(('sd', "Stable Diffusion"), {
"sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, refresh=sd_models.list_models),
"sd_model_checkpoint": OptionInfo(None, "Stable Diffusion checkpoint", gr.Dropdown, lambda: {"choices": list_checkpoint_tiles()}, refresh=refresh_checkpoints),
"sd_checkpoint_cache": OptionInfo(0, "Checkpoints to cache in RAM", gr.Slider, {"minimum": 0, "maximum": 10, "step": 1}),
"sd_vae": OptionInfo("auto", "SD VAE", gr.Dropdown, lambda: {"choices": sd_vae.vae_list}, refresh=sd_vae.refresh_vae_list),
"sd_vae_as_default": OptionInfo(False, "Ignore selected VAE for stable diffusion checkpoints that have their own .vae.pt next to them"),
......@@ -389,7 +412,7 @@ options_templates.update(options_section(('ui', "User interface"), {
}))
options_templates.update(options_section(('sampler-params', "Sampler parameters"), {
"hide_samplers": OptionInfo([], "Hide samplers in user interface (requires restart)", gr.CheckboxGroup, lambda: {"choices": [x.name for x in sd_samplers.all_samplers]}),
"hide_samplers": OptionInfo([], "Hide samplers in user interface (requires restart)", gr.CheckboxGroup, lambda: {"choices": [x.name for x in list_samplers()]}),
"eta_ddim": OptionInfo(0.0, "eta (noise multiplier) for DDIM", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
"eta_ancestral": OptionInfo(1.0, "eta (noise multiplier) for ancestral samplers", gr.Slider, {"minimum": 0.0, "maximum": 1.0, "step": 0.01}),
"ddim_discretize": OptionInfo('uniform', "img2img DDIM discretize", gr.Radio, {"choices": ['uniform', 'quad']}),
......
......@@ -111,7 +111,7 @@ def upscale(
img = img[:, :, ::-1]
img = np.moveaxis(img, 2, 0) / 255
img = torch.from_numpy(img).float()
img = devices.mps_contiguous_to(img.unsqueeze(0), devices.device_swinir)
img = img.unsqueeze(0).to(devices.device_swinir)
with torch.no_grad(), precision_scope("cuda"):
_, _, h_old, w_old = img.size()
h_pad = (h_old // window_size + 1) * window_size - h_old
......
......@@ -3,7 +3,7 @@ import numpy as np
import PIL
import torch
from PIL import Image
from torch.utils.data import Dataset
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms
import random
......@@ -11,25 +11,28 @@ import tqdm
from modules import devices, shared
import re
from ldm.modules.distributions.distributions import DiagonalGaussianDistribution
re_numbers_at_start = re.compile(r"^[-\d]+\s*")
class DatasetEntry:
def __init__(self, filename=None, latent=None, filename_text=None):
def __init__(self, filename=None, filename_text=None, latent_dist=None, latent_sample=None, cond=None, cond_text=None, pixel_values=None):
self.filename = filename
self.latent = latent
self.filename_text = filename_text
self.cond = None
self.cond_text = None
self.latent_dist = latent_dist
self.latent_sample = latent_sample
self.cond = cond
self.cond_text = cond_text
self.pixel_values = pixel_values
class PersonalizedBase(Dataset):
def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, device=None, template_file=None, include_cond=False, batch_size=1):
def __init__(self, data_root, width, height, repeats, flip_p=0.5, placeholder_token="*", model=None, cond_model=None, device=None, template_file=None, include_cond=False, batch_size=1, gradient_step=1, shuffle_tags=False, tag_drop_out=0, latent_sampling_method='once'):
re_word = re.compile(shared.opts.dataset_filename_word_regex) if len(shared.opts.dataset_filename_word_regex) > 0 else None
self.placeholder_token = placeholder_token
self.batch_size = batch_size
self.width = width
self.height = height
self.flip = transforms.RandomHorizontalFlip(p=flip_p)
......@@ -45,11 +48,16 @@ class PersonalizedBase(Dataset):
assert os.path.isdir(data_root), "Dataset directory doesn't exist"
assert os.listdir(data_root), "Dataset directory is empty"
cond_model = shared.sd_model.cond_stage_model
self.image_paths = [os.path.join(data_root, file_path) for file_path in os.listdir(data_root)]
self.shuffle_tags = shuffle_tags
self.tag_drop_out = tag_drop_out
print("Preparing dataset...")
for path in tqdm.tqdm(self.image_paths):
if shared.state.interrupted:
raise Exception("inturrupted")
try:
image = Image.open(path).convert('RGB').resize((self.width, self.height), PIL.Image.BICUBIC)
except Exception:
......@@ -71,58 +79,94 @@ class PersonalizedBase(Dataset):
npimage = np.array(image).astype(np.uint8)
npimage = (npimage / 127.5 - 1.0).astype(np.float32)
torchdata = torch.from_numpy(npimage).to(device=device, dtype=torch.float32)
torchdata = torch.moveaxis(torchdata, 2, 0)
init_latent = model.get_first_stage_encoding(model.encode_first_stage(torchdata.unsqueeze(dim=0))).squeeze()
init_latent = init_latent.to(devices.cpu)
entry = DatasetEntry(filename=path, filename_text=filename_text, latent=init_latent)
if include_cond:
torchdata = torch.from_numpy(npimage).permute(2, 0, 1).to(device=device, dtype=torch.float32)
latent_sample = None
with torch.autocast("cuda"):
latent_dist = model.encode_first_stage(torchdata.unsqueeze(dim=0))
if latent_sampling_method == "once" or (latent_sampling_method == "deterministic" and not isinstance(latent_dist, DiagonalGaussianDistribution)):
latent_sample = model.get_first_stage_encoding(latent_dist).squeeze().to(devices.cpu)
latent_sampling_method = "once"
entry = DatasetEntry(filename=path, filename_text=filename_text, latent_sample=latent_sample)
elif latent_sampling_method == "deterministic":
# Works only for DiagonalGaussianDistribution
latent_dist.std = 0
latent_sample = model.get_first_stage_encoding(latent_dist).squeeze().to(devices.cpu)
entry = DatasetEntry(filename=path, filename_text=filename_text, latent_sample=latent_sample)
elif latent_sampling_method == "random":
entry = DatasetEntry(filename=path, filename_text=filename_text, latent_dist=latent_dist)
if not (self.tag_drop_out != 0 or self.shuffle_tags):
entry.cond_text = self.create_text(filename_text)
entry.cond = cond_model([entry.cond_text]).to(devices.cpu).squeeze(0)
self.dataset.append(entry)
assert len(self.dataset) > 0, "No images have been found in the dataset."
self.length = len(self.dataset) * repeats // batch_size
if include_cond and not (self.tag_drop_out != 0 or self.shuffle_tags):
with torch.autocast("cuda"):
entry.cond = cond_model([entry.cond_text]).to(devices.cpu).squeeze(0)
self.dataset_length = len(self.dataset)
self.indexes = None
self.shuffle()
self.dataset.append(entry)
del torchdata
del latent_dist
del latent_sample
def shuffle(self):
self.indexes = np.random.permutation(self.dataset_length)
self.length = len(self.dataset)
assert self.length > 0, "No images have been found in the dataset."
self.batch_size = min(batch_size, self.length)
self.gradient_step = min(gradient_step, self.length // self.batch_size)
self.latent_sampling_method = latent_sampling_method
def create_text(self, filename_text):
text = random.choice(self.lines)
text = text.replace("[name]", self.placeholder_token)
tags = filename_text.split(',')
if shared.opts.tag_drop_out != 0:
tags = [t for t in tags if random.random() > shared.opts.tag_drop_out]
if shared.opts.shuffle_tags:
if self.tag_drop_out != 0:
tags = [t for t in tags if random.random() > self.tag_drop_out]
if self.shuffle_tags:
random.shuffle(tags)
text = text.replace("[filewords]", ','.join(tags))
text = text.replace("[name]", self.placeholder_token)
return text
def __len__(self):
return self.length
def __getitem__(self, i):
res = []
for j in range(self.batch_size):
position = i * self.batch_size + j
if position % len(self.indexes) == 0:
self.shuffle()
index = self.indexes[position % len(self.indexes)]
entry = self.dataset[index]
if entry.cond is None:
entry.cond_text = self.create_text(entry.filename_text)
res.append(entry)
return res
entry = self.dataset[i]
if self.tag_drop_out != 0 or self.shuffle_tags:
entry.cond_text = self.create_text(entry.filename_text)
if self.latent_sampling_method == "random":
entry.latent_sample = shared.sd_model.get_first_stage_encoding(entry.latent_dist).to(devices.cpu)
return entry
class PersonalizedDataLoader(DataLoader):
def __init__(self, dataset, latent_sampling_method="once", batch_size=1, pin_memory=False):
super(PersonalizedDataLoader, self).__init__(dataset, shuffle=True, drop_last=True, batch_size=batch_size, pin_memory=pin_memory)
if latent_sampling_method == "random":
self.collate_fn = collate_wrapper_random
else:
self.collate_fn = collate_wrapper
class BatchLoader:
def __init__(self, data):
self.cond_text = [entry.cond_text for entry in data]
self.cond = [entry.cond for entry in data]
self.latent_sample = torch.stack([entry.latent_sample for entry in data]).squeeze(1)
#self.emb_index = [entry.emb_index for entry in data]
#print(self.latent_sample.device)
def pin_memory(self):
self.latent_sample = self.latent_sample.pin_memory()
return self
def collate_wrapper(batch):
return BatchLoader(batch)
class BatchLoaderRandom(BatchLoader):
def __init__(self, data):
super().__init__(data)
def pin_memory(self):
return self
def collate_wrapper_random(batch):
return BatchLoaderRandom(batch)
\ No newline at end of file
This diff is collapsed.
import os
import tempfile
from collections import namedtuple
import gradio as gr
from PIL import PngImagePlugin
from modules import shared
Savedfile = namedtuple("Savedfile", ["name"])
def save_pil_to_file(pil_image, dir=None):
already_saved_as = getattr(pil_image, 'already_saved_as', None)
if already_saved_as and os.path.isfile(already_saved_as):
shared.demo.temp_dirs = shared.demo.temp_dirs | {os.path.abspath(os.path.dirname(already_saved_as))}
file_obj = Savedfile(already_saved_as)
return file_obj
if shared.opts.temp_dir != "":
dir = shared.opts.temp_dir
use_metadata = False
metadata = PngImagePlugin.PngInfo()
for key, value in pil_image.info.items():
if isinstance(key, str) and isinstance(value, str):
metadata.add_text(key, value)
use_metadata = True
file_obj = tempfile.NamedTemporaryFile(delete=False, suffix=".png", dir=dir)
pil_image.save(file_obj, pnginfo=(metadata if use_metadata else None))
return file_obj
# override save to file function so that it also writes PNG info
gr.processing_utils.save_pil_to_file = save_pil_to_file
def on_tmpdir_changed():
if shared.opts.temp_dir == "" or shared.demo is None:
return
os.makedirs(shared.opts.temp_dir, exist_ok=True)
shared.demo.temp_dirs = shared.demo.temp_dirs | {os.path.abspath(shared.opts.temp_dir)}
def cleanup_tmpdr():
temp_dir = shared.opts.temp_dir
if temp_dir == "" or not os.path.isdir(temp_dir):
return
for root, dirs, files in os.walk(temp_dir, topdown=False):
for name in files:
_, extension = os.path.splitext(name)
if extension != ".png":
continue
filename = os.path.join(root, name)
os.remove(filename)
......@@ -25,3 +25,5 @@ kornia==0.6.7
lark==1.1.2
inflection==0.5.1
GitPython==3.1.27
torchsde==0.2.5
safetensors==0.2.5
......@@ -58,29 +58,19 @@ def apply_order(p, x, xs):
prompt_tmp += part
prompt_tmp += x[idx]
p.prompt = prompt_tmp + p.prompt
def build_samplers_dict():
samplers_dict = {}
for i, sampler in enumerate(sd_samplers.all_samplers):
samplers_dict[sampler.name.lower()] = i
for alias in sampler.aliases:
samplers_dict[alias.lower()] = i
return samplers_dict
def apply_sampler(p, x, xs):
sampler_index = build_samplers_dict().get(x.lower(), None)
if sampler_index is None:
sampler_name = sd_samplers.samplers_map.get(x.lower(), None)
if sampler_name is None:
raise RuntimeError(f"Unknown sampler: {x}")
p.sampler_index = sampler_index
p.sampler_name = sampler_name
def confirm_samplers(p, xs):
samplers_dict = build_samplers_dict()
for x in xs:
if x.lower() not in samplers_dict.keys():
if x.lower() not in sd_samplers.samplers_map:
raise RuntimeError(f"Unknown sampler: {x}")
......
......@@ -11,8 +11,8 @@ class TestExtrasWorking(unittest.TestCase):
"codeformer_visibility": 0,
"codeformer_weight": 0,
"upscaling_resize": 2,
"upscaling_resize_w": 512,
"upscaling_resize_h": 512,
"upscaling_resize_w": 128,
"upscaling_resize_h": 128,
"upscaling_crop": True,
"upscaler_1": "None",
"upscaler_2": "None",
......
import unittest
import requests
class TestTxt2ImgWorking(unittest.TestCase):
def setUp(self):
self.url_txt2img = "http://localhost:7860/sdapi/v1/txt2img"
self.simple_txt2img = {
"enable_hr": False,
"denoising_strength": 0,
"firstphase_width": 0,
"firstphase_height": 0,
"prompt": "example prompt",
"styles": [],
"seed": -1,
"subseed": -1,
"subseed_strength": 0,
"seed_resize_from_h": -1,
"seed_resize_from_w": -1,
"batch_size": 1,
"n_iter": 1,
"steps": 3,
"cfg_scale": 7,
"width": 64,
"height": 64,
"restore_faces": False,
"tiling": False,
"negative_prompt": "",
"eta": 0,
"s_churn": 0,
"s_tmax": 0,
"s_tmin": 0,
"s_noise": 1,
"sampler_index": "Euler a"
}
def test_txt2img_with_restore_faces_performed(self):
self.simple_txt2img["restore_faces"] = True
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
class TestTxt2ImgCorrectness(unittest.TestCase):
pass
if __name__ == "__main__":
unittest.main()
......@@ -51,9 +51,5 @@ class TestImg2ImgWorking(unittest.TestCase):
self.assertEqual(requests.post(self.url_img2img, json=self.simple_img2img).status_code, 200)
class TestImg2ImgCorrectness(unittest.TestCase):
pass
if __name__ == "__main__":
unittest.main()
......@@ -49,26 +49,20 @@ class TestTxt2ImgWorking(unittest.TestCase):
self.simple_txt2img["enable_hr"] = True
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
def test_txt2img_with_restore_faces_performed(self):
self.simple_txt2img["restore_faces"] = True
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
def test_txt2img_with_tiling_faces_performed(self):
def test_txt2img_with_tiling_performed(self):
self.simple_txt2img["tiling"] = True
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
def test_txt2img_with_vanilla_sampler_performed(self):
self.simple_txt2img["sampler_index"] = "PLMS"
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
self.simple_txt2img["sampler_index"] = "DDIM"
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
def test_txt2img_multiple_batches_performed(self):
self.simple_txt2img["n_iter"] = 2
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
class TestTxt2ImgCorrectness(unittest.TestCase):
pass
if __name__ == "__main__":
unittest.main()
......@@ -18,20 +18,6 @@ class UtilsTests(unittest.TestCase):
def test_options_get(self):
self.assertEqual(requests.get(self.url_options).status_code, 200)
def test_options_write(self):
response = requests.get(self.url_options)
self.assertEqual(response.status_code, 200)
pre_value = response.json()["send_seed"]
self.assertEqual(requests.post(self.url_options, json={"send_seed":not pre_value}).status_code, 200)
response = requests.get(self.url_options)
self.assertEqual(response.status_code, 200)
self.assertEqual(response.json()["send_seed"], not pre_value)
requests.post(self.url_options, json={"send_seed": pre_value})
def test_cmd_flags(self):
self.assertEqual(requests.get(self.url_cmd_flags).status_code, 200)
......@@ -60,4 +46,8 @@ class UtilsTests(unittest.TestCase):
self.assertEqual(requests.get(self.url_artist_categories).status_code, 200)
def test_artists(self):
self.assertEqual(requests.get(self.url_artists).status_code, 200)
\ No newline at end of file
self.assertEqual(requests.get(self.url_artists).status_code, 200)
if __name__ == "__main__":
unittest.main()
......@@ -3,7 +3,7 @@ import requests
import time
def run_tests():
def run_tests(proc, test_dir):
timeout_threshold = 240
start_time = time.time()
while time.time()-start_time < timeout_threshold:
......@@ -11,9 +11,14 @@ def run_tests():
requests.head("http://localhost:7860/")
break
except requests.exceptions.ConnectionError:
pass
if time.time()-start_time < timeout_threshold:
suite = unittest.TestLoader().discover('', pattern='*_test.py')
if proc.poll() is not None:
break
if proc.poll() is None:
if test_dir is None:
test_dir = ""
suite = unittest.TestLoader().discover(test_dir, pattern="*_test.py", top_level_dir="test")
result = unittest.TextTestRunner(verbosity=2).run(suite)
return len(result.failures) + len(result.errors)
else:
print("Launch unsuccessful")
return 1
model:
base_learning_rate: 1.0e-04
target: ldm.models.diffusion.ddpm.LatentDiffusion
params:
linear_start: 0.00085
linear_end: 0.0120
num_timesteps_cond: 1
log_every_t: 200
timesteps: 1000
first_stage_key: "jpg"
cond_stage_key: "txt"
image_size: 64
channels: 4
cond_stage_trainable: false # Note: different from the one we trained before
conditioning_key: crossattn
monitor: val/loss_simple_ema
scale_factor: 0.18215
use_ema: False
scheduler_config: # 10000 warmup steps
target: ldm.lr_scheduler.LambdaLinearScheduler
params:
warm_up_steps: [ 10000 ]
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
f_start: [ 1.e-6 ]
f_max: [ 1. ]
f_min: [ 1. ]
unet_config:
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
params:
image_size: 32 # unused
in_channels: 4
out_channels: 4
model_channels: 320
attention_resolutions: [ 4, 2, 1 ]
num_res_blocks: 2
channel_mult: [ 1, 2, 4, 4 ]
num_heads: 8
use_spatial_transformer: True
transformer_depth: 1
context_dim: 768
use_checkpoint: True
legacy: False
first_stage_config:
target: ldm.models.autoencoder.AutoencoderKL
params:
embed_dim: 4
monitor: val/rec_loss
ddconfig:
double_z: true
z_channels: 4
resolution: 256
in_channels: 3
out_ch: 3
ch: 128
ch_mult:
- 1
- 2
- 4
- 4
num_res_blocks: 2
attn_resolutions: []
dropout: 0.0
lossconfig:
target: torch.nn.Identity
cond_stage_config:
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
......@@ -8,9 +8,10 @@ from fastapi import FastAPI
from fastapi.middleware.cors import CORSMiddleware
from fastapi.middleware.gzip import GZipMiddleware
from modules.call_queue import wrap_queued_call, queue_lock, wrap_gradio_gpu_call
from modules.paths import script_path
from modules import devices, sd_samplers, upscaler, extensions, localization
from modules import shared, devices, sd_samplers, upscaler, extensions, localization, ui_tempdir
import modules.codeformer_model as codeformer
import modules.extras
import modules.face_restoration
......@@ -23,7 +24,6 @@ import modules.scripts
import modules.sd_hijack
import modules.sd_models
import modules.sd_vae
import modules.shared as shared
import modules.txt2img
import modules.script_callbacks
......@@ -32,36 +32,12 @@ from modules import modelloader
from modules.shared import cmd_opts
import modules.hypernetworks.hypernetwork
queue_lock = threading.Lock()
if cmd_opts.server_name:
server_name = cmd_opts.server_name
else:
server_name = "0.0.0.0" if cmd_opts.listen else None
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 modules.ui.wrap_gradio_call(f, extra_outputs=extra_outputs, add_stats=True)
def initialize():
extensions.list_extensions()
......@@ -86,8 +62,9 @@ def initialize():
shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: modules.sd_models.reload_model_weights()))
shared.opts.onchange("sd_vae", wrap_queued_call(lambda: modules.sd_vae.reload_vae_weights()), call=False)
shared.opts.onchange("sd_vae_as_default", wrap_queued_call(lambda: modules.sd_vae.reload_vae_weights()), call=False)
shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: modules.hypernetworks.hypernetwork.load_hypernetwork(shared.opts.sd_hypernetwork)))
shared.opts.onchange("sd_hypernetwork", wrap_queued_call(lambda: shared.reload_hypernetworks()))
shared.opts.onchange("sd_hypernetwork_strength", modules.hypernetworks.hypernetwork.apply_strength)
shared.opts.onchange("temp_dir", ui_tempdir.on_tmpdir_changed)
if cmd_opts.tls_keyfile is not None and cmd_opts.tls_keyfile is not None:
......@@ -111,8 +88,12 @@ def initialize():
def setup_cors(app):
if cmd_opts.cors_allow_origins:
if cmd_opts.cors_allow_origins and cmd_opts.cors_allow_origins_regex:
app.add_middleware(CORSMiddleware, allow_origins=cmd_opts.cors_allow_origins.split(','), allow_origin_regex=cmd_opts.cors_allow_origins_regex, allow_methods=['*'])
elif cmd_opts.cors_allow_origins:
app.add_middleware(CORSMiddleware, allow_origins=cmd_opts.cors_allow_origins.split(','), allow_methods=['*'])
elif cmd_opts.cors_allow_origins_regex:
app.add_middleware(CORSMiddleware, allow_origin_regex=cmd_opts.cors_allow_origins_regex, allow_methods=['*'])
def create_api(app):
......@@ -150,9 +131,12 @@ def webui():
initialize()
while 1:
demo = modules.ui.create_ui(wrap_gradio_gpu_call=wrap_gradio_gpu_call)
if shared.opts.clean_temp_dir_at_start:
ui_tempdir.cleanup_tmpdr()
shared.demo = modules.ui.create_ui()
app, local_url, share_url = demo.launch(
app, local_url, share_url = shared.demo.launch(
share=cmd_opts.share,
server_name=server_name,
server_port=cmd_opts.port,
......@@ -179,9 +163,10 @@ def webui():
if launch_api:
create_api(app)
modules.script_callbacks.app_started_callback(demo, app)
modules.script_callbacks.app_started_callback(shared.demo, app)
modules.script_callbacks.app_started_callback(shared.demo, app)
wait_on_server(demo)
wait_on_server(shared.demo)
sd_samplers.set_samplers()
......
......@@ -3,6 +3,7 @@
# Please do not make any changes to this file, #
# change the variables in webui-user.sh instead #
#################################################
# Read variables from webui-user.sh
# shellcheck source=/dev/null
if [[ -f webui-user.sh ]]
......@@ -46,6 +47,17 @@ then
LAUNCH_SCRIPT="launch.py"
fi
# this script cannot be run as root by default
can_run_as_root=0
# read any command line flags to the webui.sh script
while getopts "f" flag
do
case ${flag} in
f) can_run_as_root=1;;
esac
done
# Disable sentry logging
export ERROR_REPORTING=FALSE
......@@ -61,7 +73,7 @@ printf "\e[1m\e[34mTested on Debian 11 (Bullseye)\e[0m"
printf "\n%s\n" "${delimiter}"
# Do not run as root
if [[ $(id -u) -eq 0 ]]
if [[ $(id -u) -eq 0 && can_run_as_root -eq 0 ]]
then
printf "\n%s\n" "${delimiter}"
printf "\e[1m\e[31mERROR: This script must not be launched as root, aborting...\e[0m"
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment