Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'development' into patch-1

Browse Source
This commit is contained in:
Lincoln Stein 2022-09-26 03:29:33 -04:00 committed by GitHub
commit b512d198f0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 155 additions and 125 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
docs/help/TROUBLESHOOT.md
View File

@ -27,10 +27,25 @@ rm ${PIP_LOG}
**SOLUTION**
Enter the stable-diffusion directory and completely remove the `src` directory and all its contents.
The safest way to do this is to enter the stable-diffusion directory and give the command
`git clean -f`. If this still doesn't fix the problem, try "conda clean -all" and then restart at
the `conda env create` step.
Conda sometimes gets stuck at the last PIP step, in which several git repositories are
cloned and built.
Enter the stable-diffusion directory and completely remove the `src`
directory and all its contents. The safest way to do this is to enter
the stable-diffusion directory and give the command `git clean -f`. If
this still doesn't fix the problem, try "conda clean -all" and then
restart at the `conda env create` step.
To further understand the problem to checking the install lot using this method:
```bash
export PIP_LOG="/tmp/pip_log.txt"
touch ${PIP_LOG}
tail -f ${PIP_LOG} &
conda env create -f environment-mac.yaml --debug --verbose
killall tail
rm ${PIP_LOG}
```
---

2
docs/installation/INSTALL_MAC.md
View File

@ -125,7 +125,7 @@ ln -s "$PATH_TO_CKPT/sd-v1-4.ckpt" \
=== "Intel x86_64"
```bash
PIP_EXISTS_ACTION=w CONDA_SUBDIR=osx-x86_64 \
PIP_EXISTS_ACTION=w CONDA_SUBDIR=osx-64 \
conda env create \
-f environment-mac.yaml \
&& conda activate ldm

2
ldm/dream/args.py
View File

@ -594,7 +594,7 @@ class Args(object):
'--upscale',
nargs='+',
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',
help='Scale factor (1, 2, 3, 4, etc..) for upscaling final output followed by upscaling strength (0-1.0). If strength not specified, defaults to 0.75',
default=None,
)
postprocessing_group.add_argument(

110
ldm/dream/generator/embiggen.py
View File

@ -5,17 +5,41 @@ and generates with ldm.dream.generator.img2img
import torch
import numpy as np
from tqdm import trange
from PIL import Image
from ldm.dream.generator.base import Generator
from ldm.models.diffusion.ddim import DDIMSampler
from ldm.dream.generator.img2img import Img2Img
from ldm.dream.devices import choose_autocast
class Embiggen(Generator):
def __init__(self, model, precision):
super().__init__(model, precision)
self.init_latent = None
# Replace generate because Embiggen doesn't need/use most of what it does normallly
def generate(self,prompt,iterations=1,seed=None,
image_callback=None, step_callback=None,
**kwargs):
scope = choose_autocast(self.precision)
make_image = self.get_make_image(
prompt,
step_callback = step_callback,
**kwargs
)
results = []
seed = seed if seed else self.new_seed()
# Noise will be generated by the Img2Img generator when called
with scope(self.model.device.type), self.model.ema_scope():
for n in trange(iterations, desc='Generating'):
# make_image will call Img2Img which will do the equivalent of get_noise itself
image = make_image()
results.append([image, seed])
if image_callback is not None:
image_callback(image, seed)
seed = self.new_seed()
return results
@torch.no_grad()
def get_make_image(
self,
@ -151,8 +175,19 @@ class Embiggen(Generator):
# Clamp values to max 255
if distanceToLR > 255:
distanceToLR = 255
# Place the pixel as invert of distance
agradientC.putpixel((x, y), int(255 - distanceToLR))
#Place the pixel as invert of distance
agradientC.putpixel((x, y), round(255 - distanceToLR))
# Create alternative asymmetric diagonal corner to use on "tailing" intersections to prevent hard edges
# Fits for a left-fading gradient on the bottom side and full opacity on the right side.
agradientAsymC = Image.new('L', (256, 256))
for y in range(256):
for x in range(256):
value = round(max(0, x-(255-y)) * (255 / max(1,y)))
#Clamp values
value = max(0, value)
value = min(255, value)
agradientAsymC.putpixel((x, y), value)
# Create alpha layers default fully white
alphaLayerL = Image.new("L", (width, height), 255)
@ -163,8 +198,13 @@ class Embiggen(Generator):
alphaLayerT.paste(agradientT, (0, 0))
alphaLayerLTC.paste(agradientL, (0, 0))
alphaLayerLTC.paste(agradientT, (0, 0))
alphaLayerLTC.paste(agradientC.resize(
(overlap_size_x, overlap_size_y)), (0, 0))
alphaLayerLTC.paste(agradientC.resize((overlap_size_x, overlap_size_y)), (0, 0))
# make masks with an asymmetric upper-right corner so when the curved transparent corner of the next tile
# to its right is placed it doesn't reveal a hard trailing semi-transparent edge in the overlapping space
alphaLayerTaC = alphaLayerT.copy()
alphaLayerTaC.paste(agradientAsymC.rotate(270).resize((overlap_size_x, overlap_size_y)), (width - overlap_size_x, 0))
alphaLayerLTaC = alphaLayerLTC.copy()
alphaLayerLTaC.paste(agradientAsymC.rotate(270).resize((overlap_size_x, overlap_size_y)), (width - overlap_size_x, 0))
if embiggen_tiles:
# Individual unconnected sides
@ -242,7 +282,7 @@ class Embiggen(Generator):
del agradientT
del agradientC
def make_image(x_T):
def make_image():
# Make main tiles -------------------------------------------------
if embiggen_tiles:
print(f'>> Making {len(embiggen_tiles)} Embiggen tiles...')
@ -251,7 +291,20 @@ class Embiggen(Generator):
f'>> Making {(emb_tiles_x * emb_tiles_y)} Embiggen tiles ({emb_tiles_x}x{emb_tiles_y})...')
emb_tile_store = []
# Although we could use the same seed for every tile for determinism, at higher strengths this may
# produce duplicated structures for each tile and make the tiling effect more obvious
# instead track and iterate a local seed we pass to Img2Img
seed = self.seed
seedintlimit = np.iinfo(np.uint32).max - 1 # only retreive this one from numpy
for tile in range(emb_tiles_x * emb_tiles_y):
# Don't iterate on first tile
if tile != 0:
if seed < seedintlimit:
seed += 1
else:
seed = 0
# Determine if this is a re-run and replace
if embiggen_tiles and not tile in embiggen_tiles:
continue
@ -294,21 +347,20 @@ class Embiggen(Generator):
tile_results = gen_img2img.generate(
prompt,
iterations=1,
seed=self.seed,
sampler=sampler,
steps=steps,
cfg_scale=cfg_scale,
conditioning=conditioning,
ddim_eta=ddim_eta,
image_callback=None, # called only after the final image is generated
step_callback=step_callback, # called after each intermediate image is generated
width=width,
height=height,
init_img=init_img, # img2img doesn't need this, but it might in the future
init_image=newinitimage, # notice that init_image is different from init_img
mask_image=None,
strength=strength,
iterations = 1,
seed = seed,
sampler = sampler,
steps = steps,
cfg_scale = cfg_scale,
conditioning = conditioning,
ddim_eta = ddim_eta,
image_callback = None, # called only after the final image is generated
step_callback = step_callback, # called after each intermediate image is generated
width = width,
height = height,
init_image = newinitimage, # notice that init_image is different from init_img
mask_image = None,
strength = strength,
)
emb_tile_store.append(tile_results[0][0])
@ -382,7 +434,7 @@ class Embiggen(Generator):
elif emb_row_i == emb_tiles_y - 1:
if emb_column_i == 0:
if (tile+1) in embiggen_tiles: # Look-ahead right
intileimage.putalpha(alphaLayerT)
intileimage.putalpha(alphaLayerTaC)
else:
intileimage.putalpha(alphaLayerRTC)
elif emb_column_i == emb_tiles_x - 1:
@ -390,7 +442,7 @@ class Embiggen(Generator):
intileimage.putalpha(alphaLayerLTC)
else:
if (tile+1) in embiggen_tiles: # Look-ahead right
intileimage.putalpha(alphaLayerLTC)
intileimage.putalpha(alphaLayerLTaC)
else:
intileimage.putalpha(alphaLayerABB)
# vertical middle of image
@ -398,7 +450,7 @@ class Embiggen(Generator):
if emb_column_i == 0:
if (tile+1) in embiggen_tiles: # Look-ahead right
if (tile+emb_tiles_x) in embiggen_tiles: # Look-ahead down
intileimage.putalpha(alphaLayerT)
intileimage.putalpha(alphaLayerTaC)
else:
intileimage.putalpha(alphaLayerTB)
elif (tile+emb_tiles_x) in embiggen_tiles: # Look-ahead down only
@ -413,7 +465,7 @@ class Embiggen(Generator):
else:
if (tile+1) in embiggen_tiles: # Look-ahead right
if (tile+emb_tiles_x) in embiggen_tiles: # Look-ahead down
intileimage.putalpha(alphaLayerLTC)
intileimage.putalpha(alphaLayerLTaC)
else:
intileimage.putalpha(alphaLayerABR)
elif (tile+emb_tiles_x) in embiggen_tiles: # Look-ahead down only
@ -425,9 +477,15 @@ class Embiggen(Generator):
if emb_row_i == 0 and emb_column_i >= 1:
intileimage.putalpha(alphaLayerL)
elif emb_row_i >= 1 and emb_column_i == 0:
if emb_column_i + 1 == emb_tiles_x: # If we don't have anything that can be placed to the right
intileimage.putalpha(alphaLayerT)
else:
intileimage.putalpha(alphaLayerTaC)
else:
if emb_column_i + 1 == emb_tiles_x: # If we don't have anything that can be placed to the right
intileimage.putalpha(alphaLayerLTC)
else:
intileimage.putalpha(alphaLayerLTaC)
# Layer tile onto final image
outputsuperimage.alpha_composite(intileimage, (left, top))
else:

54
ldm/dream/restoration/realesrgan.py
View File

@ -14,45 +14,22 @@ class ESRGAN():
else:
use_half_precision = True
def load_esrgan_bg_upsampler(self, upsampler_scale):
def load_esrgan_bg_upsampler(self):
if not torch.cuda.is_available(): # CPU or MPS on M1
use_half_precision = False
else:
use_half_precision = True
model_path = {
2: 'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth',
4: 'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth',
}
if upsampler_scale not in model_path:
return None
else:
from basicsr.archs.rrdbnet_arch import RRDBNet
from realesrgan.archs.srvgg_arch import SRVGGNetCompact
from realesrgan import RealESRGANer
if upsampler_scale == 4:
model = RRDBNet(
num_in_ch=3,
num_out_ch=3,
num_feat=64,
num_block=23,
num_grow_ch=32,
scale=4,
)
if upsampler_scale == 2:
model = RRDBNet(
num_in_ch=3,
num_out_ch=3,
num_feat=64,
num_block=23,
num_grow_ch=32,
scale=2,
)
model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
model_path = 'https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth'
scale = 4
bg_upsampler = RealESRGANer(
scale=upsampler_scale,
model_path=model_path[upsampler_scale],
scale=scale,
model_path=model_path,
model=model,
tile=self.bg_tile_size,
tile_pad=10,
@ -63,24 +40,27 @@ class ESRGAN():
return bg_upsampler
def process(self, image, strength: float, seed: str = None, upsampler_scale: int = 2):
if seed is not None:
print(
f'>> Real-ESRGAN Upscaling seed:{seed} : scale:{upsampler_scale}x'
)
with warnings.catch_warnings():
warnings.filterwarnings('ignore', category=DeprecationWarning)
warnings.filterwarnings('ignore', category=UserWarning)
try:
upsampler = self.load_esrgan_bg_upsampler(upsampler_scale)
upsampler = self.load_esrgan_bg_upsampler()
except Exception:
import traceback
import sys
print('>> Error loading Real-ESRGAN:', file=sys.stderr)
print(traceback.format_exc(), file=sys.stderr)
if upsampler_scale == 0:
print('>> Real-ESRGAN: Invalid scaling option. Image not upscaled.')
return image
if seed is not None:
print(
f'>> Real-ESRGAN Upscaling seed:{seed} : scale:{upsampler_scale}x'
)
output, _ = upsampler.enhance(
np.array(image, dtype=np.uint8),
outscale=upsampler_scale,

23
ldm/generate.py
View File

@ -497,11 +497,8 @@ class Generate:
prompt = None
try:
args = metadata_from_png(image_path)
if len(args) > 1:
print("* Can't postprocess a grid")
return
seed = args[0].seed
prompt = args[0].prompt
seed = args.seed
prompt = args.prompt
print(f'>> retrieved seed {seed} and prompt "{prompt}" from {image_path}')
except:
m = re.search('(\d+)\.png$',image_path)
@ -724,14 +721,6 @@ class Generate:
for r in image_list:
image, seed = r
try:
if upscale is not None:
if self.esrgan is not None:
if len(upscale) < 2:
upscale.append(0.75)
image = self.esrgan.process(
image, upscale[1], seed, int(upscale[0]))
else:
print(">> ESRGAN is disabled. Image not upscaled.")
if strength > 0:
if self.gfpgan is not None or self.codeformer is not None:
if facetool == 'gfpgan':
@ -747,6 +736,14 @@ class Generate:
image = self.codeformer.process(image=image, strength=strength, device=cf_device, seed=seed, fidelity=codeformer_fidelity)
else:
print(">> Face Restoration is disabled.")
if upscale is not None:
if self.esrgan is not None:
if len(upscale) < 2:
upscale.append(0.75)
image = self.esrgan.process(
image, upscale[1], seed, int(upscale[0]))
else:
print(">> ESRGAN is disabled. Image not upscaled.")
except Exception as e:
print(
f'>> Error running RealESRGAN or GFPGAN. Your image was not upscaled.\n{e}'

26
scripts/preload_models.py
View File

@ -49,33 +49,13 @@ except ModuleNotFoundError:
if gfpgan:
print('Loading models from RealESRGAN and facexlib')
try:
from basicsr.archs.rrdbnet_arch import RRDBNet
from realesrgan.archs.srvgg_arch import SRVGGNetCompact
from facexlib.utils.face_restoration_helper import FaceRestoreHelper
RealESRGANer(
scale=2,
model_path='https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth',
model=RRDBNet(
num_in_ch=3,
num_out_ch=3,
num_feat=64,
num_block=23,
num_grow_ch=32,
scale=2,
),
)
RealESRGANer(
scale=4,
model_path='https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth',
model=RRDBNet(
num_in_ch=3,
num_out_ch=3,
num_feat=64,
num_block=23,
num_grow_ch=32,
scale=4,
),
model_path='https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth',
model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
)
FaceRestoreHelper(1, det_model='retinaface_resnet50')