mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
* Feature complete for #266 with exception of several small deviations: 1. initial image and model weight hashes use full sha256 hash rather than first 8 digits 2. Initialization parameters for post-processing steps not provided 3. Uses top-level "images" tags for both a single image and a grid of images. This change was suggested in a comment. * Added scripts/sd_metadata.py to retrieve and print metadata from PNG files * New ldm.dream.args.Args class is a namespace like object which holds all defaults and can be modified during exection to hold current settings. * Modified dream.py and server.py to accommodate Args class.
This commit is contained in:
Lincoln Stein
GitHub
426
scripts/dream.py
Executable file → Normal file
426
scripts/dream.py
Executable file → Normal file
@ -1,8 +1,6 @@
|
||||
#!/usr/bin/env python3
|
||||
# Copyright (c) 2022 Lincoln D. Stein (https://github.com/lstein)
|
||||
|
||||
import argparse
|
||||
import shlex
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
@ -10,7 +8,8 @@ import copy
|
||||
import warnings
|
||||
import time
|
||||
import ldm.dream.readline
|
||||
from ldm.dream.pngwriter import PngWriter, PromptFormatter
|
||||
from ldm.dream.args import Args, format_metadata
|
||||
from ldm.dream.pngwriter import PngWriter
|
||||
from ldm.dream.server import DreamServer, ThreadingDreamServer
|
||||
from ldm.dream.image_util import make_grid
|
||||
from omegaconf import OmegaConf
|
||||
@ -22,14 +21,16 @@ output_cntr = 0
|
||||
|
||||
def main():
|
||||
"""Initialize command-line parsers and the diffusion model"""
|
||||
arg_parser = create_argv_parser()
|
||||
opt = arg_parser.parse_args()
|
||||
opt = Args()
|
||||
args = opt.parse_args()
|
||||
if not args:
|
||||
sys.exit(-1)
|
||||
|
||||
if opt.laion400m:
|
||||
if args.laion400m:
|
||||
print('--laion400m flag has been deprecated. Please use --model laion400m instead.')
|
||||
sys.exit(-1)
|
||||
if opt.weights != 'model':
|
||||
print('--weights argument has been deprecated. Please configure ./configs/models.yaml, and call it using --model instead.')
|
||||
if args.weights:
|
||||
print('--weights argument has been deprecated. Please edit ./configs/models.yaml, and select the weights using --model instead.')
|
||||
sys.exit(-1)
|
||||
|
||||
print('* Initializing, be patient...\n')
|
||||
@ -47,7 +48,7 @@ def main():
|
||||
# the user input loop
|
||||
try:
|
||||
gen = Generate(
|
||||
conf = opt.config,
|
||||
conf = opt.conf,
|
||||
model = opt.model,
|
||||
sampler_name = opt.sampler_name,
|
||||
embedding_path = opt.embedding_path,
|
||||
@ -91,11 +92,10 @@ def main():
|
||||
dream_server_loop(gen, opt.host, opt.port, opt.outdir)
|
||||
sys.exit(0)
|
||||
|
||||
cmd_parser = create_cmd_parser()
|
||||
main_loop(gen, opt.outdir, opt.prompt_as_dir, cmd_parser, infile)
|
||||
main_loop(gen, opt, infile)
|
||||
|
||||
# TODO: main_loop() has gotten busy. Needs to be refactored.
|
||||
def main_loop(gen, outdir, prompt_as_dir, parser, infile):
|
||||
def main_loop(gen, opt, infile):
|
||||
"""prompt/read/execute loop"""
|
||||
done = False
|
||||
path_filter = re.compile(r'[<>:"/\\|?*]')
|
||||
@ -103,8 +103,8 @@ def main_loop(gen, outdir, prompt_as_dir, parser, infile):
|
||||
|
||||
# os.pathconf is not available on Windows
|
||||
if hasattr(os, 'pathconf'):
|
||||
path_max = os.pathconf(outdir, 'PC_PATH_MAX')
|
||||
name_max = os.pathconf(outdir, 'PC_NAME_MAX')
|
||||
path_max = os.pathconf(opt.outdir, 'PC_PATH_MAX')
|
||||
name_max = os.pathconf(opt.outdir, 'PC_NAME_MAX')
|
||||
else:
|
||||
path_max = 260
|
||||
name_max = 255
|
||||
@ -123,41 +123,17 @@ def main_loop(gen, outdir, prompt_as_dir, parser, infile):
|
||||
if command.startswith(('#', '//')):
|
||||
continue
|
||||
|
||||
# before splitting, escape single quotes so as not to mess
|
||||
# up the parser
|
||||
command = command.replace("'", "\\'")
|
||||
|
||||
try:
|
||||
elements = shlex.split(command)
|
||||
except ValueError as e:
|
||||
print(str(e))
|
||||
continue
|
||||
|
||||
if elements[0] == 'q':
|
||||
if command.startswith('q '):
|
||||
done = True
|
||||
break
|
||||
|
||||
if elements[0].startswith(
|
||||
if command.startswith(
|
||||
'!dream'
|
||||
): # in case a stored prompt still contains the !dream command
|
||||
elements.pop(0)
|
||||
|
||||
# rearrange the arguments to mimic how it works in the Dream bot.
|
||||
switches = ['']
|
||||
switches_started = False
|
||||
|
||||
for el in elements:
|
||||
if el[0] == '-' and not switches_started:
|
||||
switches_started = True
|
||||
if switches_started:
|
||||
switches.append(el)
|
||||
else:
|
||||
switches[0] += el
|
||||
switches[0] += ' '
|
||||
switches[0] = switches[0][: len(switches[0]) - 1]
|
||||
command.replace('!dream','',1)
|
||||
|
||||
try:
|
||||
opt = parser.parse_args(switches)
|
||||
parser = opt.parse_cmd(command)
|
||||
except SystemExit:
|
||||
parser.print_help()
|
||||
continue
|
||||
@ -185,6 +161,7 @@ def main_loop(gen, outdir, prompt_as_dir, parser, infile):
|
||||
opt.seed = None
|
||||
continue
|
||||
|
||||
# TODO - move this into a module
|
||||
if opt.with_variations is not None:
|
||||
# shotgun parsing, woo
|
||||
parts = []
|
||||
@ -220,7 +197,7 @@ def main_loop(gen, outdir, prompt_as_dir, parser, infile):
|
||||
|
||||
# truncate path to maximum allowed length
|
||||
# 27 is the length of '######.##########.##.png', plus two separators and a NUL
|
||||
subdir = subdir[:(path_max - 27 - len(os.path.abspath(outdir)))]
|
||||
subdir = subdir[:(path_max - 27 - len(os.path.abspath(opt.outdir)))]
|
||||
current_outdir = os.path.join(outdir, subdir)
|
||||
|
||||
print('Writing files to directory: "' + current_outdir + '"')
|
||||
@ -248,31 +225,36 @@ def main_loop(gen, outdir, prompt_as_dir, parser, infile):
|
||||
filename = f'{prefix}.{seed}.postprocessed.png'
|
||||
else:
|
||||
filename = f'{prefix}.{seed}.png'
|
||||
# the handling of variations is probably broken
|
||||
# Also, given the ability to add stuff to the dream_prompt_str, it isn't
|
||||
# necessary to make a copy of the opt option just to change its attributes
|
||||
if opt.variation_amount > 0:
|
||||
iter_opt = argparse.Namespace(**vars(opt)) # copy
|
||||
iter_opt = copy.copy(opt)
|
||||
this_variation = [[seed, opt.variation_amount]]
|
||||
if opt.with_variations is None:
|
||||
iter_opt.with_variations = this_variation
|
||||
else:
|
||||
iter_opt.with_variations = opt.with_variations + this_variation
|
||||
iter_opt.variation_amount = 0
|
||||
normalized_prompt = PromptFormatter(
|
||||
gen, iter_opt).normalize_prompt()
|
||||
metadata_prompt = f'{normalized_prompt} -S{iter_opt.seed}'
|
||||
formatted_dream_prompt = iter_opt.dream_prompt_str(seed=seed)
|
||||
elif opt.with_variations is not None:
|
||||
normalized_prompt = PromptFormatter(
|
||||
gen, opt).normalize_prompt()
|
||||
# use the original seed - the per-iteration value is the last variation-seed
|
||||
metadata_prompt = f'{normalized_prompt} -S{opt.seed}'
|
||||
formatted_dream_prompt = opt.dream_prompt_str(seed=seed)
|
||||
else:
|
||||
normalized_prompt = PromptFormatter(
|
||||
gen, opt).normalize_prompt()
|
||||
metadata_prompt = f'{normalized_prompt} -S{seed}'
|
||||
formatted_dream_prompt = opt.dream_prompt_str(seed=seed)
|
||||
path = file_writer.save_image_and_prompt_to_png(
|
||||
image, metadata_prompt, filename)
|
||||
image = image,
|
||||
dream_prompt = formatted_dream_prompt,
|
||||
metadata = format_metadata(
|
||||
opt,
|
||||
seeds = [seed],
|
||||
weights = gen.weights,
|
||||
model_hash = gen.model_hash,
|
||||
),
|
||||
name = filename,
|
||||
)
|
||||
if (not upscaled) or opt.save_original:
|
||||
# only append to results if we didn't overwrite an earlier output
|
||||
results.append([path, metadata_prompt])
|
||||
results.append([path, formatted_dream_prompt])
|
||||
last_results.append([path, seed])
|
||||
|
||||
catch_ctrl_c = infile is None # if running interactively, we catch keyboard interrupts
|
||||
@ -286,15 +268,22 @@ def main_loop(gen, outdir, prompt_as_dir, parser, infile):
|
||||
grid_img = make_grid(list(grid_images.values()))
|
||||
grid_seeds = list(grid_images.keys())
|
||||
first_seed = last_results[0][1]
|
||||
filename = f'{prefix}.{first_seed}.png'
|
||||
# TODO better metadata for grid images
|
||||
normalized_prompt = PromptFormatter(
|
||||
gen, opt).normalize_prompt()
|
||||
metadata_prompt = f'{normalized_prompt} -S{first_seed} --grid -n{len(grid_images)} # {grid_seeds}'
|
||||
filename = f'{prefix}.{first_seed}.png'
|
||||
formatted_dream_prompt = opt.dream_prompt_str(seed=first_seed,grid=True,iterations=len(grid_images))
|
||||
formatted_dream_prompt += f' # {grid_seeds}'
|
||||
metadata = format_metadata(
|
||||
opt,
|
||||
seeds = grid_seeds,
|
||||
weights = gen.weights,
|
||||
model_hash = gen.model_hash
|
||||
)
|
||||
path = file_writer.save_image_and_prompt_to_png(
|
||||
grid_img, metadata_prompt, filename
|
||||
image = grid_img,
|
||||
dream_prompt = formatted_dream_prompt,
|
||||
metadata = metadata,
|
||||
name = filename
|
||||
)
|
||||
results = [[path, metadata_prompt]]
|
||||
results = [[path, formatted_dream_prompt]]
|
||||
|
||||
except AssertionError as e:
|
||||
print(e)
|
||||
@ -325,7 +314,6 @@ def get_next_command(infile=None) -> str: # command string
|
||||
print(f'#{command}')
|
||||
return command
|
||||
|
||||
|
||||
def dream_server_loop(gen, host, port, outdir):
|
||||
print('\n* --web was specified, starting web server...')
|
||||
# Change working directory to the stable-diffusion directory
|
||||
@ -365,315 +353,5 @@ def write_log_message(results, log_path):
|
||||
with open(log_path, 'a', encoding='utf-8') as file:
|
||||
file.writelines(log_lines)
|
||||
|
||||
|
||||
SAMPLER_CHOICES = [
|
||||
'ddim',
|
||||
'k_dpm_2_a',
|
||||
'k_dpm_2',
|
||||
'k_euler_a',
|
||||
'k_euler',
|
||||
'k_heun',
|
||||
'k_lms',
|
||||
'plms',
|
||||
]
|
||||
|
||||
|
||||
def create_argv_parser():
|
||||
parser = argparse.ArgumentParser(
|
||||
description="""Generate images using Stable Diffusion.
|
||||
Use --web to launch the web interface.
|
||||
Use --from_file to load prompts from a file path or standard input ("-").
|
||||
Otherwise you will be dropped into an interactive command prompt (type -h for help.)
|
||||
Other command-line arguments are defaults that can usually be overridden
|
||||
prompt the command prompt.
|
||||
"""
|
||||
)
|
||||
parser.add_argument(
|
||||
'--laion400m',
|
||||
'--latent_diffusion',
|
||||
'-l',
|
||||
dest='laion400m',
|
||||
action='store_true',
|
||||
help='Fallback to the latent diffusion (laion400m) weights and config',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--from_file',
|
||||
dest='infile',
|
||||
type=str,
|
||||
help='If specified, load prompts from this file',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-n',
|
||||
'--iterations',
|
||||
type=int,
|
||||
default=1,
|
||||
help='Number of images to generate',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-F',
|
||||
'--full_precision',
|
||||
dest='full_precision',
|
||||
action='store_true',
|
||||
help='Use more memory-intensive full precision math for calculations',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-g',
|
||||
'--grid',
|
||||
action='store_true',
|
||||
help='Generate a grid instead of individual images',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-A',
|
||||
'-m',
|
||||
'--sampler',
|
||||
dest='sampler_name',
|
||||
choices=SAMPLER_CHOICES,
|
||||
metavar='SAMPLER_NAME',
|
||||
default='k_lms',
|
||||
help=f'Set the initial sampler. Default: k_lms. Supported samplers: {", ".join(SAMPLER_CHOICES)}',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--outdir',
|
||||
'-o',
|
||||
type=str,
|
||||
default='outputs/img-samples',
|
||||
help='Directory to save generated images and a log of prompts and seeds. Default: outputs/img-samples',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--seamless',
|
||||
action='store_true',
|
||||
help='Change the model to seamless tiling (circular) mode',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--embedding_path',
|
||||
type=str,
|
||||
help='Path to a pre-trained embedding manager checkpoint - can only be set on command line',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--prompt_as_dir',
|
||||
'-p',
|
||||
action='store_true',
|
||||
help='Place images in subdirectories named after the prompt.',
|
||||
)
|
||||
# GFPGAN related args
|
||||
parser.add_argument(
|
||||
'--gfpgan_bg_upsampler',
|
||||
type=str,
|
||||
default='realesrgan',
|
||||
help='Background upsampler. Default: realesrgan. Options: realesrgan, none.',
|
||||
|
||||
)
|
||||
parser.add_argument(
|
||||
'--gfpgan_bg_tile',
|
||||
type=int,
|
||||
default=400,
|
||||
help='Tile size for background sampler, 0 for no tile during testing. Default: 400.',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--gfpgan_model_path',
|
||||
type=str,
|
||||
default='experiments/pretrained_models/GFPGANv1.3.pth',
|
||||
help='Indicates the path to the GFPGAN model, relative to --gfpgan_dir.',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--gfpgan_dir',
|
||||
type=str,
|
||||
default='./src/gfpgan',
|
||||
help='Indicates the directory containing the GFPGAN code.',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--web',
|
||||
dest='web',
|
||||
action='store_true',
|
||||
help='Start in web server mode.',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--host',
|
||||
type=str,
|
||||
default='127.0.0.1',
|
||||
help='Web server: Host or IP to listen on. Set to 0.0.0.0 to accept traffic from other devices on your network.'
|
||||
)
|
||||
parser.add_argument(
|
||||
'--port',
|
||||
type=int,
|
||||
default='9090',
|
||||
help='Web server: Port to listen on'
|
||||
)
|
||||
parser.add_argument(
|
||||
'--weights',
|
||||
default='model',
|
||||
help='Indicates the Stable Diffusion model to use.',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--model',
|
||||
default='stable-diffusion-1.4',
|
||||
help='Indicates which diffusion model to load. (currently "stable-diffusion-1.4" (default) or "laion400m")',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--config',
|
||||
default='configs/models.yaml',
|
||||
help='Path to configuration file for alternate models.',
|
||||
)
|
||||
return parser
|
||||
|
||||
|
||||
def create_cmd_parser():
|
||||
parser = argparse.ArgumentParser(
|
||||
description='Example: dream> a fantastic alien landscape -W1024 -H960 -s100 -n12'
|
||||
)
|
||||
parser.add_argument('prompt')
|
||||
parser.add_argument('-s', '--steps', type=int, help='Number of steps')
|
||||
parser.add_argument(
|
||||
'-S',
|
||||
'--seed',
|
||||
type=int,
|
||||
help='Image seed; a +ve integer, or use -1 for the previous seed, -2 for the one before that, etc',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-n',
|
||||
'--iterations',
|
||||
type=int,
|
||||
default=1,
|
||||
help='Number of samplings to perform (slower, but will provide seeds for individual images)',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-W', '--width', type=int, help='Image width, multiple of 64'
|
||||
)
|
||||
parser.add_argument(
|
||||
'-H', '--height', type=int, help='Image height, multiple of 64'
|
||||
)
|
||||
parser.add_argument(
|
||||
'-C',
|
||||
'--cfg_scale',
|
||||
default=7.5,
|
||||
type=float,
|
||||
help='Classifier free guidance (CFG) scale - higher numbers cause generator to "try" harder.',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-g', '--grid', action='store_true', help='generate a grid'
|
||||
)
|
||||
parser.add_argument(
|
||||
'--outdir',
|
||||
'-o',
|
||||
type=str,
|
||||
default=None,
|
||||
help='Directory to save generated images and a log of prompts and seeds',
|
||||
)
|
||||
parser.add_argument(
|
||||
'--seamless',
|
||||
action='store_true',
|
||||
help='Change the model to seamless tiling (circular) mode',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-i',
|
||||
'--individual',
|
||||
action='store_true',
|
||||
help='Generate individual files (default)',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-I',
|
||||
'--init_img',
|
||||
type=str,
|
||||
help='Path to input image for img2img mode (supersedes width and height)',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-M',
|
||||
'--init_mask',
|
||||
type=str,
|
||||
help='Path to input mask for inpainting mode (supersedes width and height)',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-T',
|
||||
'-fit',
|
||||
'--fit',
|
||||
action='store_true',
|
||||
help='If specified, will resize the input image to fit within the dimensions of width x height (512x512 default)',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-f',
|
||||
'--strength',
|
||||
default=0.75,
|
||||
type=float,
|
||||
help='Strength for noising/unnoising. 0.0 preserves image exactly, 1.0 replaces it completely',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-G',
|
||||
'--gfpgan_strength',
|
||||
default=0,
|
||||
type=float,
|
||||
help='The strength at which to apply the GFPGAN model to the result, in order to improve faces.',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-U',
|
||||
'--upscale',
|
||||
nargs='+',
|
||||
default=None,
|
||||
type=float,
|
||||
help='Scale factor (2, 4) for upscaling final output followed by upscaling strength (0-1.0). If strength not specified, defaults to 0.75'
|
||||
)
|
||||
parser.add_argument(
|
||||
'-save_orig',
|
||||
'--save_original',
|
||||
action='store_true',
|
||||
help='Save original. Use it when upscaling to save both versions.',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-embiggen',
|
||||
'--embiggen',
|
||||
nargs='+',
|
||||
default=None,
|
||||
type=float,
|
||||
help='Embiggen tiled img2img for higher resolution and detail without extra VRAM usage. Takes scale factor relative to the size of the --init_img (-I), followed by ESRGAN upscaling strength (0-1.0), followed by minimum amount of overlap between tiles as a decimal ratio (0 - 1.0) or number of pixels. ESRGAN strength defaults to 0.75, and overlap defaults to 0.25 . ESRGAN is used to upscale the init prior to cutting it into tiles/pieces to run through img2img and then stitch back togeather.',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-embiggen_tiles',
|
||||
'--embiggen_tiles',
|
||||
nargs='+',
|
||||
default=None,
|
||||
type=int,
|
||||
help='If while doing Embiggen we are altering only parts of the image, takes a list of tiles by number to process and replace onto the image e.g. `1 3 5`, useful for redoing problematic spots from a prior Embiggen run',
|
||||
)
|
||||
# variants is going to be superseded by a generalized "prompt-morph" function
|
||||
# parser.add_argument('-v','--variants',type=int,help="in img2img mode, the first generated image will get passed back to img2img to generate the requested number of variants")
|
||||
parser.add_argument(
|
||||
'-x',
|
||||
'--skip_normalize',
|
||||
action='store_true',
|
||||
help='Skip subprompt weight normalization',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-A',
|
||||
'-m',
|
||||
'--sampler',
|
||||
dest='sampler_name',
|
||||
default=None,
|
||||
type=str,
|
||||
choices=SAMPLER_CHOICES,
|
||||
metavar='SAMPLER_NAME',
|
||||
help=f'Switch to a different sampler. Supported samplers: {", ".join(SAMPLER_CHOICES)}',
|
||||
)
|
||||
parser.add_argument(
|
||||
'-t',
|
||||
'--log_tokenization',
|
||||
action='store_true',
|
||||
help='shows how the prompt is split into tokens'
|
||||
)
|
||||
parser.add_argument(
|
||||
'-v',
|
||||
'--variation_amount',
|
||||
default=0.0,
|
||||
type=float,
|
||||
help='If > 0, generates variations on the initial seed instead of random seeds per iteration. Must be between 0 and 1. Higher values will be more different.'
|
||||
)
|
||||
parser.add_argument(
|
||||
'-V',
|
||||
'--with_variations',
|
||||
default=None,
|
||||
type=str,
|
||||
help='list of variations to apply, in the format `seed:weight,seed:weight,...'
|
||||
)
|
||||
return parser
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
|
||||
22
scripts/sd-metadata.py
Normal file
22
scripts/sd-metadata.py
Normal file
@ -0,0 +1,22 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
import sys
|
||||
import json
|
||||
from ldm.dream.pngwriter import retrieve_metadata
|
||||
|
||||
if len(sys.argv) < 2:
|
||||
print("Usage: file2prompt.py <file1.png> <file2.png> <file3.png>...")
|
||||
print("This script opens up the indicated dream.py-generated PNG file(s) and prints out their metadata.")
|
||||
exit(-1)
|
||||
|
||||
filenames = sys.argv[1:]
|
||||
for f in filenames:
|
||||
try:
|
||||
metadata = retrieve_metadata(f)
|
||||
print(f'{f}:\n',json.dumps(metadata, indent=4))
|
||||
except FileNotFoundError:
|
||||
sys.stderr.write(f'{f} not found\n')
|
||||
continue
|
||||
except PermissionError:
|
||||
sys.stderr.write(f'{f} could not be opened due to inadequate permissions\n')
|
||||
continue
|
||||
Reference in New Issue
Block a user