mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
commit
8233098136
4
.github/CODEOWNERS
vendored
Normal file
4
.github/CODEOWNERS
vendored
Normal file
@ -0,0 +1,4 @@
|
||||
ldm/invoke/pngwriter.py @CapableWeb
|
||||
ldm/invoke/server_legacy.py @CapableWeb
|
||||
scripts/legacy_api.py @CapableWeb
|
||||
tests/legacy_tests.sh @CapableWeb
|
@ -66,3 +66,43 @@ def write_metadata(img_path:str, meta:dict):
|
||||
info = PngImagePlugin.PngInfo()
|
||||
info.add_text('sd-metadata', json.dumps(meta))
|
||||
im.save(img_path,'PNG',pnginfo=info)
|
||||
|
||||
class PromptFormatter:
|
||||
def __init__(self, t2i, opt):
|
||||
self.t2i = t2i
|
||||
self.opt = opt
|
||||
|
||||
# note: the t2i object should provide all these values.
|
||||
# there should be no need to or against opt values
|
||||
def normalize_prompt(self):
|
||||
"""Normalize the prompt and switches"""
|
||||
t2i = self.t2i
|
||||
opt = self.opt
|
||||
|
||||
switches = list()
|
||||
switches.append(f'"{opt.prompt}"')
|
||||
switches.append(f'-s{opt.steps or t2i.steps}')
|
||||
switches.append(f'-W{opt.width or t2i.width}')
|
||||
switches.append(f'-H{opt.height or t2i.height}')
|
||||
switches.append(f'-C{opt.cfg_scale or t2i.cfg_scale}')
|
||||
switches.append(f'-A{opt.sampler_name or t2i.sampler_name}')
|
||||
# to do: put model name into the t2i object
|
||||
# switches.append(f'--model{t2i.model_name}')
|
||||
if opt.seamless or t2i.seamless:
|
||||
switches.append(f'--seamless')
|
||||
if opt.init_img:
|
||||
switches.append(f'-I{opt.init_img}')
|
||||
if opt.fit:
|
||||
switches.append(f'--fit')
|
||||
if opt.strength and opt.init_img is not None:
|
||||
switches.append(f'-f{opt.strength or t2i.strength}')
|
||||
if opt.gfpgan_strength:
|
||||
switches.append(f'-G{opt.gfpgan_strength}')
|
||||
if opt.upscale:
|
||||
switches.append(f'-U {" ".join([str(u) for u in opt.upscale])}')
|
||||
if opt.variation_amount > 0:
|
||||
switches.append(f'-v{opt.variation_amount}')
|
||||
if opt.with_variations:
|
||||
formatted_variations = ','.join(f'{seed}:{weight}' for seed, weight in opt.with_variations)
|
||||
switches.append(f'-V{formatted_variations}')
|
||||
return ' '.join(switches)
|
||||
|
246
ldm/invoke/server_legacy.py
Normal file
246
ldm/invoke/server_legacy.py
Normal file
@ -0,0 +1,246 @@
|
||||
import argparse
|
||||
import json
|
||||
import base64
|
||||
import mimetypes
|
||||
import os
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
from ldm.invoke.pngwriter import PngWriter, PromptFormatter
|
||||
from threading import Event
|
||||
|
||||
def build_opt(post_data, seed, gfpgan_model_exists):
|
||||
opt = argparse.Namespace()
|
||||
setattr(opt, 'prompt', post_data['prompt'])
|
||||
setattr(opt, 'init_img', post_data['initimg'])
|
||||
setattr(opt, 'strength', float(post_data['strength']))
|
||||
setattr(opt, 'iterations', int(post_data['iterations']))
|
||||
setattr(opt, 'steps', int(post_data['steps']))
|
||||
setattr(opt, 'width', int(post_data['width']))
|
||||
setattr(opt, 'height', int(post_data['height']))
|
||||
setattr(opt, 'seamless', 'seamless' in post_data)
|
||||
setattr(opt, 'fit', 'fit' in post_data)
|
||||
setattr(opt, 'mask', 'mask' in post_data)
|
||||
setattr(opt, 'invert_mask', 'invert_mask' in post_data)
|
||||
setattr(opt, 'cfg_scale', float(post_data['cfg_scale']))
|
||||
setattr(opt, 'sampler_name', post_data['sampler_name'])
|
||||
setattr(opt, 'gfpgan_strength', float(post_data['gfpgan_strength']) if gfpgan_model_exists else 0)
|
||||
setattr(opt, 'upscale', [int(post_data['upscale_level']), float(post_data['upscale_strength'])] if post_data['upscale_level'] != '' else None)
|
||||
setattr(opt, 'progress_images', 'progress_images' in post_data)
|
||||
setattr(opt, 'seed', None if int(post_data['seed']) == -1 else int(post_data['seed']))
|
||||
setattr(opt, 'variation_amount', float(post_data['variation_amount']) if int(post_data['seed']) != -1 else 0)
|
||||
setattr(opt, 'with_variations', [])
|
||||
|
||||
broken = False
|
||||
if int(post_data['seed']) != -1 and post_data['with_variations'] != '':
|
||||
for part in post_data['with_variations'].split(','):
|
||||
seed_and_weight = part.split(':')
|
||||
if len(seed_and_weight) != 2:
|
||||
print(f'could not parse with_variation part "{part}"')
|
||||
broken = True
|
||||
break
|
||||
try:
|
||||
seed = int(seed_and_weight[0])
|
||||
weight = float(seed_and_weight[1])
|
||||
except ValueError:
|
||||
print(f'could not parse with_variation part "{part}"')
|
||||
broken = True
|
||||
break
|
||||
opt.with_variations.append([seed, weight])
|
||||
|
||||
if broken:
|
||||
raise CanceledException
|
||||
|
||||
if len(opt.with_variations) == 0:
|
||||
opt.with_variations = None
|
||||
|
||||
return opt
|
||||
|
||||
class CanceledException(Exception):
|
||||
pass
|
||||
|
||||
class DreamServer(BaseHTTPRequestHandler):
|
||||
model = None
|
||||
outdir = None
|
||||
canceled = Event()
|
||||
|
||||
def do_GET(self):
|
||||
if self.path == "/":
|
||||
self.send_response(200)
|
||||
self.send_header("Content-type", "text/html")
|
||||
self.end_headers()
|
||||
with open("./static/dream_web/index.html", "rb") as content:
|
||||
self.wfile.write(content.read())
|
||||
elif self.path == "/config.js":
|
||||
# unfortunately this import can't be at the top level, since that would cause a circular import
|
||||
from ldm.gfpgan.gfpgan_tools import gfpgan_model_exists
|
||||
self.send_response(200)
|
||||
self.send_header("Content-type", "application/javascript")
|
||||
self.end_headers()
|
||||
config = {
|
||||
'gfpgan_model_exists': gfpgan_model_exists
|
||||
}
|
||||
self.wfile.write(bytes("let config = " + json.dumps(config) + ";\n", "utf-8"))
|
||||
elif self.path == "/run_log.json":
|
||||
self.send_response(200)
|
||||
self.send_header("Content-type", "application/json")
|
||||
self.end_headers()
|
||||
output = []
|
||||
|
||||
log_file = os.path.join(self.outdir, "dream_web_log.txt")
|
||||
if os.path.exists(log_file):
|
||||
with open(log_file, "r") as log:
|
||||
for line in log:
|
||||
url, config = line.split(": {", maxsplit=1)
|
||||
config = json.loads("{" + config)
|
||||
config["url"] = url.lstrip(".")
|
||||
if os.path.exists(url):
|
||||
output.append(config)
|
||||
|
||||
self.wfile.write(bytes(json.dumps({"run_log": output}), "utf-8"))
|
||||
elif self.path == "/cancel":
|
||||
self.canceled.set()
|
||||
self.send_response(200)
|
||||
self.send_header("Content-type", "application/json")
|
||||
self.end_headers()
|
||||
self.wfile.write(bytes('{}', 'utf8'))
|
||||
else:
|
||||
path = "." + self.path
|
||||
cwd = os.path.realpath(os.getcwd())
|
||||
is_in_cwd = os.path.commonprefix((os.path.realpath(path), cwd)) == cwd
|
||||
if not (is_in_cwd and os.path.exists(path)):
|
||||
self.send_response(404)
|
||||
return
|
||||
mime_type = mimetypes.guess_type(path)[0]
|
||||
if mime_type is not None:
|
||||
self.send_response(200)
|
||||
self.send_header("Content-type", mime_type)
|
||||
self.end_headers()
|
||||
with open("." + self.path, "rb") as content:
|
||||
self.wfile.write(content.read())
|
||||
else:
|
||||
self.send_response(404)
|
||||
|
||||
def do_POST(self):
|
||||
self.send_response(200)
|
||||
self.send_header("Content-type", "application/json")
|
||||
self.end_headers()
|
||||
|
||||
# unfortunately this import can't be at the top level, since that would cause a circular import
|
||||
# TODO temporarily commented out, import fails for some reason
|
||||
# from ldm.gfpgan.gfpgan_tools import gfpgan_model_exists
|
||||
gfpgan_model_exists = False
|
||||
|
||||
content_length = int(self.headers['Content-Length'])
|
||||
post_data = json.loads(self.rfile.read(content_length))
|
||||
opt = build_opt(post_data, self.model.seed, gfpgan_model_exists)
|
||||
|
||||
self.canceled.clear()
|
||||
print(f">> Request to generate with prompt: {opt.prompt}")
|
||||
# In order to handle upscaled images, the PngWriter needs to maintain state
|
||||
# across images generated by each call to prompt2img(), so we define it in
|
||||
# the outer scope of image_done()
|
||||
config = post_data.copy() # Shallow copy
|
||||
config['initimg'] = config.pop('initimg_name', '')
|
||||
|
||||
images_generated = 0 # helps keep track of when upscaling is started
|
||||
images_upscaled = 0 # helps keep track of when upscaling is completed
|
||||
pngwriter = PngWriter(self.outdir)
|
||||
|
||||
prefix = pngwriter.unique_prefix()
|
||||
# if upscaling is requested, then this will be called twice, once when
|
||||
# the images are first generated, and then again when after upscaling
|
||||
# is complete. The upscaling replaces the original file, so the second
|
||||
# entry should not be inserted into the image list.
|
||||
def image_done(image, seed, upscaled=False, first_seed=-1, use_prefix=None):
|
||||
print(f'First seed: {first_seed}')
|
||||
name = f'{prefix}.{seed}.png'
|
||||
iter_opt = argparse.Namespace(**vars(opt)) # copy
|
||||
if opt.variation_amount > 0:
|
||||
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
|
||||
elif opt.with_variations is None:
|
||||
iter_opt.seed = seed
|
||||
normalized_prompt = PromptFormatter(self.model, iter_opt).normalize_prompt()
|
||||
path = pngwriter.save_image_and_prompt_to_png(image, f'{normalized_prompt} -S{iter_opt.seed}', name)
|
||||
|
||||
if int(config['seed']) == -1:
|
||||
config['seed'] = seed
|
||||
# Append post_data to log, but only once!
|
||||
if not upscaled:
|
||||
with open(os.path.join(self.outdir, "dream_web_log.txt"), "a") as log:
|
||||
log.write(f"{path}: {json.dumps(config)}\n")
|
||||
|
||||
self.wfile.write(bytes(json.dumps(
|
||||
{'event': 'result', 'url': path, 'seed': seed, 'config': config}
|
||||
) + '\n',"utf-8"))
|
||||
|
||||
# control state of the "postprocessing..." message
|
||||
upscaling_requested = opt.upscale or opt.gfpgan_strength > 0
|
||||
nonlocal images_generated # NB: Is this bad python style? It is typical usage in a perl closure.
|
||||
nonlocal images_upscaled # NB: Is this bad python style? It is typical usage in a perl closure.
|
||||
if upscaled:
|
||||
images_upscaled += 1
|
||||
else:
|
||||
images_generated += 1
|
||||
if upscaling_requested:
|
||||
action = None
|
||||
if images_generated >= opt.iterations:
|
||||
if images_upscaled < opt.iterations:
|
||||
action = 'upscaling-started'
|
||||
else:
|
||||
action = 'upscaling-done'
|
||||
if action:
|
||||
x = images_upscaled + 1
|
||||
self.wfile.write(bytes(json.dumps(
|
||||
{'event': action, 'processed_file_cnt': f'{x}/{opt.iterations}'}
|
||||
) + '\n',"utf-8"))
|
||||
|
||||
step_writer = PngWriter(os.path.join(self.outdir, "intermediates"))
|
||||
step_index = 1
|
||||
def image_progress(sample, step):
|
||||
if self.canceled.is_set():
|
||||
self.wfile.write(bytes(json.dumps({'event':'canceled'}) + '\n', 'utf-8'))
|
||||
raise CanceledException
|
||||
path = None
|
||||
# since rendering images is moderately expensive, only render every 5th image
|
||||
# and don't bother with the last one, since it'll render anyway
|
||||
nonlocal step_index
|
||||
if opt.progress_images and step % 5 == 0 and step < opt.steps - 1:
|
||||
image = self.model.sample_to_image(sample)
|
||||
name = f'{prefix}.{opt.seed}.{step_index}.png'
|
||||
metadata = f'{opt.prompt} -S{opt.seed} [intermediate]'
|
||||
path = step_writer.save_image_and_prompt_to_png(image, metadata, name)
|
||||
step_index += 1
|
||||
self.wfile.write(bytes(json.dumps(
|
||||
{'event': 'step', 'step': step + 1, 'url': path}
|
||||
) + '\n',"utf-8"))
|
||||
|
||||
try:
|
||||
if opt.init_img is None:
|
||||
# Run txt2img
|
||||
self.model.prompt2image(**vars(opt), step_callback=image_progress, image_callback=image_done)
|
||||
else:
|
||||
# Decode initimg as base64 to temp file
|
||||
with open("./img2img-tmp.png", "wb") as f:
|
||||
initimg = opt.init_img.split(",")[1] # Ignore mime type
|
||||
f.write(base64.b64decode(initimg))
|
||||
opt1 = argparse.Namespace(**vars(opt))
|
||||
opt1.init_img = "./img2img-tmp.png"
|
||||
|
||||
try:
|
||||
# Run img2img
|
||||
self.model.prompt2image(**vars(opt1), step_callback=image_progress, image_callback=image_done)
|
||||
finally:
|
||||
# Remove the temp file
|
||||
os.remove("./img2img-tmp.png")
|
||||
except CanceledException:
|
||||
print(f"Canceled.")
|
||||
return
|
||||
|
||||
|
||||
class ThreadingDreamServer(ThreadingHTTPServer):
|
||||
def __init__(self, server_address):
|
||||
super(ThreadingDreamServer, self).__init__(server_address, DreamServer)
|
685
scripts/legacy_api.py
Executable file
685
scripts/legacy_api.py
Executable file
@ -0,0 +1,685 @@
|
||||
#!/usr/bin/env python3
|
||||
# Copyright (c) 2022 Lincoln D. Stein (https://github.com/lstein)
|
||||
|
||||
import argparse
|
||||
import shlex
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
import copy
|
||||
import warnings
|
||||
import time
|
||||
import ldm.invoke.readline
|
||||
from ldm.invoke.pngwriter import PngWriter, PromptFormatter
|
||||
from ldm.invoke.server_legacy import DreamServer, ThreadingDreamServer
|
||||
from ldm.invoke.image_util import make_grid
|
||||
from omegaconf import OmegaConf
|
||||
|
||||
# Placeholder to be replaced with proper class that tracks the
|
||||
# outputs and associates with the prompt that generated them.
|
||||
# Just want to get the formatting look right for now.
|
||||
output_cntr = 0
|
||||
|
||||
|
||||
def main():
|
||||
"""Initialize command-line parsers and the diffusion model"""
|
||||
arg_parser = create_argv_parser()
|
||||
opt = arg_parser.parse_args()
|
||||
|
||||
if opt.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.')
|
||||
sys.exit(-1)
|
||||
|
||||
try:
|
||||
models = OmegaConf.load(opt.config)
|
||||
width = models[opt.model].width
|
||||
height = models[opt.model].height
|
||||
config = models[opt.model].config
|
||||
weights = models[opt.model].weights
|
||||
except (FileNotFoundError, IOError, KeyError) as e:
|
||||
print(f'{e}. Aborting.')
|
||||
sys.exit(-1)
|
||||
|
||||
print('* Initializing, be patient...\n')
|
||||
sys.path.append('.')
|
||||
from pytorch_lightning import logging
|
||||
from ldm.generate import Generate
|
||||
|
||||
# these two lines prevent a horrible warning message from appearing
|
||||
# when the frozen CLIP tokenizer is imported
|
||||
import transformers
|
||||
|
||||
transformers.logging.set_verbosity_error()
|
||||
|
||||
# creating a simple text2image object with a handful of
|
||||
# defaults passed on the command line.
|
||||
# additional parameters will be added (or overriden) during
|
||||
# the user input loop
|
||||
t2i = Generate(
|
||||
# width=width,
|
||||
# height=height,
|
||||
sampler_name=opt.sampler_name,
|
||||
weights=weights,
|
||||
full_precision=opt.full_precision,
|
||||
config=config,
|
||||
# grid=opt.grid,
|
||||
# this is solely for recreating the prompt
|
||||
# seamless=opt.seamless,
|
||||
embedding_path=opt.embedding_path,
|
||||
# device_type=opt.device,
|
||||
# ignore_ctrl_c=opt.infile is None,
|
||||
)
|
||||
|
||||
# make sure the output directory exists
|
||||
if not os.path.exists(opt.outdir):
|
||||
os.makedirs(opt.outdir)
|
||||
|
||||
# gets rid of annoying messages about random seed
|
||||
logging.getLogger('pytorch_lightning').setLevel(logging.ERROR)
|
||||
|
||||
# load the infile as a list of lines
|
||||
infile = None
|
||||
if opt.infile:
|
||||
try:
|
||||
if os.path.isfile(opt.infile):
|
||||
infile = open(opt.infile, 'r', encoding='utf-8')
|
||||
elif opt.infile == '-': # stdin
|
||||
infile = sys.stdin
|
||||
else:
|
||||
raise FileNotFoundError(f'{opt.infile} not found.')
|
||||
except (FileNotFoundError, IOError) as e:
|
||||
print(f'{e}. Aborting.')
|
||||
sys.exit(-1)
|
||||
|
||||
if opt.seamless:
|
||||
print(">> changed to seamless tiling mode")
|
||||
|
||||
# preload the model
|
||||
t2i.load_model()
|
||||
|
||||
if not infile:
|
||||
print(
|
||||
"\n* Initialization done! Awaiting your command (-h for help, 'q' to quit)"
|
||||
)
|
||||
|
||||
cmd_parser = create_cmd_parser()
|
||||
if opt.web:
|
||||
dream_server_loop(t2i, opt.host, opt.port, opt.outdir)
|
||||
else:
|
||||
main_loop(t2i, opt.outdir, opt.prompt_as_dir, cmd_parser, infile)
|
||||
|
||||
|
||||
def main_loop(t2i, outdir, prompt_as_dir, parser, infile):
|
||||
"""prompt/read/execute loop"""
|
||||
done = False
|
||||
path_filter = re.compile(r'[<>:"/\\|?*]')
|
||||
last_results = list()
|
||||
|
||||
# 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')
|
||||
else:
|
||||
path_max = 260
|
||||
name_max = 255
|
||||
|
||||
while not done:
|
||||
try:
|
||||
command = get_next_command(infile)
|
||||
except EOFError:
|
||||
done = True
|
||||
continue
|
||||
except KeyboardInterrupt:
|
||||
done = True
|
||||
continue
|
||||
|
||||
# skip empty lines
|
||||
if not command.strip():
|
||||
continue
|
||||
|
||||
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':
|
||||
done = True
|
||||
break
|
||||
|
||||
if elements[0].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]
|
||||
|
||||
try:
|
||||
opt = parser.parse_args(switches)
|
||||
except SystemExit:
|
||||
parser.print_help()
|
||||
continue
|
||||
if len(opt.prompt) == 0:
|
||||
print('Try again with a prompt!')
|
||||
continue
|
||||
# retrieve previous value!
|
||||
if opt.init_img is not None and re.match('^-\\d+$', opt.init_img):
|
||||
try:
|
||||
opt.init_img = last_results[int(opt.init_img)][0]
|
||||
print(f'>> Reusing previous image {opt.init_img}')
|
||||
except IndexError:
|
||||
print(
|
||||
f'>> No previous initial image at position {opt.init_img} found')
|
||||
opt.init_img = None
|
||||
continue
|
||||
|
||||
if opt.seed is not None and opt.seed < 0: # retrieve previous value!
|
||||
try:
|
||||
opt.seed = last_results[opt.seed][1]
|
||||
print(f'>> Reusing previous seed {opt.seed}')
|
||||
except IndexError:
|
||||
print(f'>> No previous seed at position {opt.seed} found')
|
||||
opt.seed = None
|
||||
continue
|
||||
|
||||
do_grid = opt.grid or t2i.grid
|
||||
|
||||
if opt.with_variations is not None:
|
||||
# shotgun parsing, woo
|
||||
parts = []
|
||||
broken = False # python doesn't have labeled loops...
|
||||
for part in opt.with_variations.split(','):
|
||||
seed_and_weight = part.split(':')
|
||||
if len(seed_and_weight) != 2:
|
||||
print(f'could not parse with_variation part "{part}"')
|
||||
broken = True
|
||||
break
|
||||
try:
|
||||
seed = int(seed_and_weight[0])
|
||||
weight = float(seed_and_weight[1])
|
||||
except ValueError:
|
||||
print(f'could not parse with_variation part "{part}"')
|
||||
broken = True
|
||||
break
|
||||
parts.append([seed, weight])
|
||||
if broken:
|
||||
continue
|
||||
if len(parts) > 0:
|
||||
opt.with_variations = parts
|
||||
else:
|
||||
opt.with_variations = None
|
||||
|
||||
if opt.outdir:
|
||||
if not os.path.exists(opt.outdir):
|
||||
os.makedirs(opt.outdir)
|
||||
current_outdir = opt.outdir
|
||||
elif prompt_as_dir:
|
||||
# sanitize the prompt to a valid folder name
|
||||
subdir = path_filter.sub('_', opt.prompt)[:name_max].rstrip(' .')
|
||||
|
||||
# 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)))]
|
||||
current_outdir = os.path.join(outdir, subdir)
|
||||
|
||||
print('Writing files to directory: "' + current_outdir + '"')
|
||||
|
||||
# make sure the output directory exists
|
||||
if not os.path.exists(current_outdir):
|
||||
os.makedirs(current_outdir)
|
||||
else:
|
||||
current_outdir = outdir
|
||||
|
||||
# Here is where the images are actually generated!
|
||||
last_results = []
|
||||
try:
|
||||
file_writer = PngWriter(current_outdir)
|
||||
prefix = file_writer.unique_prefix()
|
||||
results = [] # list of filename, prompt pairs
|
||||
grid_images = dict() # seed -> Image, only used if `do_grid`
|
||||
|
||||
def image_writer(image, seed, upscaled=False):
|
||||
path = None
|
||||
if do_grid:
|
||||
grid_images[seed] = image
|
||||
else:
|
||||
if upscaled and opt.save_original:
|
||||
filename = f'{prefix}.{seed}.postprocessed.png'
|
||||
else:
|
||||
filename = f'{prefix}.{seed}.png'
|
||||
if opt.variation_amount > 0:
|
||||
iter_opt = argparse.Namespace(**vars(opt)) # copy
|
||||
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(
|
||||
t2i, iter_opt).normalize_prompt()
|
||||
metadata_prompt = f'{normalized_prompt} -S{iter_opt.seed}'
|
||||
elif opt.with_variations is not None:
|
||||
normalized_prompt = PromptFormatter(
|
||||
t2i, opt).normalize_prompt()
|
||||
# use the original seed - the per-iteration value is the last variation-seed
|
||||
metadata_prompt = f'{normalized_prompt} -S{opt.seed}'
|
||||
else:
|
||||
normalized_prompt = PromptFormatter(
|
||||
t2i, opt).normalize_prompt()
|
||||
metadata_prompt = f'{normalized_prompt} -S{seed}'
|
||||
path = file_writer.save_image_and_prompt_to_png(
|
||||
image, metadata_prompt, 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])
|
||||
last_results.append([path, seed])
|
||||
|
||||
t2i.prompt2image(image_callback=image_writer, **vars(opt))
|
||||
|
||||
if do_grid and len(grid_images) > 0:
|
||||
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(
|
||||
t2i, opt).normalize_prompt()
|
||||
metadata_prompt = f'{normalized_prompt} -S{first_seed} --grid -n{len(grid_images)} # {grid_seeds}'
|
||||
path = file_writer.save_image_and_prompt_to_png(
|
||||
grid_img, metadata_prompt, filename
|
||||
)
|
||||
results = [[path, metadata_prompt]]
|
||||
|
||||
except AssertionError as e:
|
||||
print(e)
|
||||
continue
|
||||
|
||||
except OSError as e:
|
||||
print(e)
|
||||
continue
|
||||
|
||||
print('Outputs:')
|
||||
log_path = os.path.join(current_outdir, 'dream_log.txt')
|
||||
write_log_message(results, log_path)
|
||||
print()
|
||||
|
||||
print('goodbye!')
|
||||
|
||||
|
||||
def get_next_command(infile=None) -> str: # command string
|
||||
if infile is None:
|
||||
command = input('dream> ')
|
||||
else:
|
||||
command = infile.readline()
|
||||
if not command:
|
||||
raise EOFError
|
||||
else:
|
||||
command = command.strip()
|
||||
print(f'#{command}')
|
||||
return command
|
||||
|
||||
|
||||
def dream_server_loop(t2i, host, port, outdir):
|
||||
print('\n* --web was specified, starting web server...')
|
||||
# Change working directory to the stable-diffusion directory
|
||||
os.chdir(
|
||||
os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))
|
||||
)
|
||||
|
||||
# Start server
|
||||
DreamServer.model = t2i
|
||||
DreamServer.outdir = outdir
|
||||
dream_server = ThreadingDreamServer((host, port))
|
||||
print(">> Started Stable Diffusion dream server!")
|
||||
if host == '0.0.0.0':
|
||||
print(
|
||||
f"Point your browser at http://localhost:{port} or use the host's DNS name or IP address.")
|
||||
else:
|
||||
print(">> Default host address now 127.0.0.1 (localhost). Use --host 0.0.0.0 to bind any address.")
|
||||
print(f">> Point your browser at http://{host}:{port}.")
|
||||
|
||||
try:
|
||||
dream_server.serve_forever()
|
||||
except KeyboardInterrupt:
|
||||
pass
|
||||
|
||||
dream_server.server_close()
|
||||
|
||||
|
||||
def write_log_message(results, log_path):
|
||||
"""logs the name of the output image, prompt, and prompt args to the terminal and log file"""
|
||||
global output_cntr
|
||||
log_lines = [f'{path}: {prompt}\n' for path, prompt in results]
|
||||
for l in log_lines:
|
||||
output_cntr += 1
|
||||
print(f'[{output_cntr}] {l}',end='')
|
||||
|
||||
|
||||
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(
|
||||
'--device',
|
||||
'-d',
|
||||
type=str,
|
||||
default='cuda',
|
||||
help="device to run stable diffusion on. defaults to cuda `torch.cuda.current_device()` if available"
|
||||
)
|
||||
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 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.',
|
||||
)
|
||||
# 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()
|
46
tests/legacy_tests.sh
Executable file
46
tests/legacy_tests.sh
Executable file
@ -0,0 +1,46 @@
|
||||
#! /usr/bin/env bash
|
||||
|
||||
# This file contains bunch of compatibility tests that ensures
|
||||
# that the API interface of `scripts/legacy-api.py` remains stable
|
||||
|
||||
set -e
|
||||
|
||||
OUTDIR=$(mktemp -d)
|
||||
|
||||
echo "Using directory $OUTDIR"
|
||||
|
||||
# Start API
|
||||
python -u scripts/legacy_api.py --web --host=localhost --port=3333 --outdir=$OUTDIR &> $OUTDIR/sd.log &
|
||||
APP_PID=$!
|
||||
|
||||
echo "Wait for server to startup"
|
||||
|
||||
tail -f -n0 $OUTDIR/sd.log | grep -qe "Point your browser at"
|
||||
|
||||
echo "Started, continuing"
|
||||
|
||||
if [ $? == 1 ]; then
|
||||
echo "Search terminated without finding the pattern"
|
||||
fi
|
||||
|
||||
# Generate image
|
||||
RESULT=$(curl -v -X POST -d '{"index":0,"variation_amount":0,"with_variations":"","steps":25,"width":512,"seed":"1337","prompt":"A cat wearing a hat","strength":0.5,"initimg":null,"cfg_scale":2,"iterations":1,"upscale_level":0,"upscale_strength":0,"sampler_name":"k_euler","height":512}' localhost:3333 | grep result)
|
||||
|
||||
# Test 01 - Image contents
|
||||
FILENAME=$(echo $RESULT | jq -r .url)
|
||||
|
||||
ACTUAL_CHECKSUM=$(sha256sum $FILENAME)
|
||||
EXPECTED_CHECKSUM="a77799226a4dfc62a1674498e575c775da042959a4b90b13e26f666c302f079f"
|
||||
|
||||
if [ "$ACTUAL_CHECKSUM" != "$EXPECTED_CHECKSUM" ]; then
|
||||
echo "Expected hash $EXPECTED_CHECKSUM but got hash $ACTUAL_CHECKSUM"
|
||||
kill $APP_PID
|
||||
# rm -r $OUTDIR
|
||||
exit 33
|
||||
fi
|
||||
|
||||
# Assert output
|
||||
|
||||
# Cleanup
|
||||
kill $APP_PID
|
||||
# rm -r $OUTDIR
|
Loading…
x
Reference in New Issue
Block a user