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 model-switching

Browse Source
This commit is contained in:
Lincoln Stein 2022-10-14 13:18:59 -04:00 committed by GitHub
commit fe2a2cfc8b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
32 changed files with 727 additions and 575 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
backend/invoke_ai_web_server.py
View File

@ -319,7 +319,7 @@ class InvokeAIWebServer:
elif postprocessing_parameters['type'] == 'gfpgan':
image = self.gfpgan.process(
image=image,
strength=postprocessing_parameters['gfpgan_strength'],
strength=postprocessing_parameters['facetool_strength'],
seed=seed,
)
else:
@ -625,7 +625,7 @@ class InvokeAIWebServer:
seed=seed,
)
postprocessing = True
all_parameters['gfpgan_strength'] = gfpgan_parameters[
all_parameters['facetool_strength'] = gfpgan_parameters[
'strength'
]
@ -723,6 +723,7 @@ class InvokeAIWebServer:
'height',
'extra',
'seamless',
'hires_fix',
]
rfc_dict = {}
@ -735,12 +736,12 @@ class InvokeAIWebServer:
postprocessing = []
# 'postprocessing' is either null or an
if 'gfpgan_strength' in parameters:
if 'facetool_strength' in parameters:
postprocessing.append(
{
'type': 'gfpgan',
'strength': float(parameters['gfpgan_strength']),
'strength': float(parameters['facetool_strength']),
}
)
@ -837,7 +838,7 @@ class InvokeAIWebServer:
elif parameters['type'] == 'gfpgan':
postprocessing_metadata['type'] = 'gfpgan'
postprocessing_metadata['strength'] = parameters[
'gfpgan_strength'
'facetool_strength'
]
else:
raise TypeError(f"Invalid type: {parameters['type']}")

10
backend/modules/parameters.py
View File

@ -36,6 +36,8 @@ def parameters_to_command(params):
switches.append(f'-A {params["sampler_name"]}')
if "seamless" in params and params["seamless"] == True:
switches.append(f"--seamless")
if "hires_fix" in params and params["hires_fix"] == True:
switches.append(f"--hires")
if "init_img" in params and len(params["init_img"]) > 0:
switches.append(f'-I {params["init_img"]}')
if "init_mask" in params and len(params["init_mask"]) > 0:
@ -46,8 +48,14 @@ def parameters_to_command(params):
switches.append(f'-f {params["strength"]}')
if "fit" in params and params["fit"] == True:
switches.append(f"--fit")
if "gfpgan_strength" in params and params["gfpgan_strength"]:
if "facetool" in params:
switches.append(f'-ft {params["facetool"]}')
if "facetool_strength" in params and params["facetool_strength"]:
switches.append(f'-G {params["facetool_strength"]}')
elif "gfpgan_strength" in params and params["gfpgan_strength"]:
switches.append(f'-G {params["gfpgan_strength"]}')
if "codeformer_fidelity" in params:
switches.append(f'-cf {params["codeformer_fidelity"]}')
if "upscale" in params and params["upscale"]:
switches.append(f'-U {params["upscale"][0]} {params["upscale"][1]}')
if "variation_amount" in params and params["variation_amount"] > 0:

11
backend/server.py
View File

@ -349,7 +349,7 @@ def handle_run_gfpgan_event(original_image, gfpgan_parameters):
eventlet.sleep(0)
image = gfpgan.process(
image=image, strength=gfpgan_parameters["gfpgan_strength"], seed=seed
image=image, strength=gfpgan_parameters["facetool_strength"], seed=seed
)
progress["currentStatus"] = "Saving image"
@ -464,7 +464,7 @@ def parameters_to_post_processed_image_metadata(parameters, original_image_path,
image["strength"] = parameters["upscale"][1]
elif type == "gfpgan":
image["type"] = "gfpgan"
image["strength"] = parameters["gfpgan_strength"]
image["strength"] = parameters["facetool_strength"]
else:
raise TypeError(f"Invalid type: {type}")
@ -493,6 +493,7 @@ def parameters_to_generated_image_metadata(parameters):
"height",
"extra",
"seamless",
"hires_fix",
]
rfc_dict = {}
@ -505,10 +506,10 @@ def parameters_to_generated_image_metadata(parameters):
postprocessing = []
# 'postprocessing' is either null or an
if "gfpgan_strength" in parameters:
if "facetool_strength" in parameters:
postprocessing.append(
{"type": "gfpgan", "strength": float(parameters["gfpgan_strength"])}
{"type": "gfpgan", "strength": float(parameters["facetool_strength"])}
)
if "upscale" in parameters:
@ -751,7 +752,7 @@ def generate_images(generation_parameters, esrgan_parameters, gfpgan_parameters)
image=image, strength=gfpgan_parameters["strength"], seed=seed
)
postprocessing = True
all_parameters["gfpgan_strength"] = gfpgan_parameters["strength"]
all_parameters["facetool_strength"] = gfpgan_parameters["strength"]
progress["currentStatus"] = "Saving image"
socketio.emit("progressUpdate", progress)

4
docs/features/CLI.md
View File

@ -154,7 +154,9 @@ Here are the invoke> command that apply to txt2img:
| --log_tokenization | -t | False | Display a color-coded list of the parsed tokens derived from the prompt |
| --skip_normalization| -x | False | Weighted subprompts will not be normalized. See [Weighted Prompts](./OTHER.md#weighted-prompts) |
| --upscale <int> <float> | -U <int> <float> | -U 1 0.75| Upscale image by magnification factor (2, 4), and set strength of upscaling (0.0-1.0). If strength not set, will default to 0.75. |
| --gfpgan_strength <float> | -G <float> | -G0 | Fix faces using the GFPGAN algorithm; argument indicates how hard the algorithm should try (0.0-1.0) |
| --facetool_strength <float> | -G <float> | -G0 | Fix faces (defaults to using the GFPGAN algorithm); argument indicates how hard the algorithm should try (0.0-1.0) |
| --facetool <name> | -ft <name> | -ft gfpgan | Select face restoration algorithm to use: gfpgan, codeformer |
| --codeformer_fidelity | -cf <float> | 0.75 | Used along with CodeFormer. Takes values between 0 and 1. 0 produces high quality but low accuracy. 1 produces high accuracy but low quality |
| --save_original | -save_orig| False | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced. |
| --variation <float> |-v<float>| 0.0 | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with -S<seed> and -n<int> to generate a series a riffs on a starting image. See [Variations](./VARIATIONS.md). |
| --with_variations <pattern> | | None | Combine two or more variations. See [Variations](./VARIATIONS.md) for now to use this. |

2
docs/features/POSTPROCESS.md
View File

@ -69,7 +69,7 @@ If you do not explicitly specify an upscaling_strength, it will default to 0.75.
### Face Restoration
`-G : <gfpgan_strength>`
`-G : <facetool_strength>`
This prompt argument controls the strength of the face restoration that is being
applied. Similar to upscaling, values between `0.5 to 0.8` are recommended.

483
frontend/dist/assets/index.989a0ca2.js vendored
View File

File diff suppressed because one or more lines are too long

483
frontend/dist/assets/index.ea68b5f5.js vendored Normal file
View File

File diff suppressed because one or more lines are too long

2
frontend/dist/index.html vendored
View File

@ -6,7 +6,7 @@
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>InvokeAI - A Stable Diffusion Toolkit</title>
<link rel="shortcut icon" type="icon" href="/assets/favicon.0d253ced.ico" />
<script type="module" crossorigin src="/assets/index.989a0ca2.js"></script>
<script type="module" crossorigin src="/assets/index.ea68b5f5.js"></script>
<link rel="stylesheet" href="/assets/index.58175ea1.css">
</head>

1
frontend/src/app/constants.ts
View File

@ -50,6 +50,7 @@ export const PARAMETERS: { [key: string]: string } = {
maskPath: 'Initial Image Mask',
shouldFitToWidthHeight: 'Fit Initial Image',
seamless: 'Seamless Tiling',
hiresFix: 'High Resolution Optimizations',
};
export const NUMPY_RAND_MIN = 0;

18
frontend/src/app/features.ts
View File

@ -14,10 +14,13 @@ export enum Feature {
FACE_CORRECTION,
IMAGE_TO_IMAGE,
}
/** For each tooltip in the UI, the below feature definitions & props will pull relevant information into the tooltip.
*
* To-do: href & GuideImages are placeholders, and are not currently utilized, but will be updated (along with the tooltip UI) as feature and UI development and we get a better idea on where things "forever homes" will be .
*/
export const FEATURES: Record<Feature, FeatureHelpInfo> = {
[Feature.PROMPT]: {
text: 'This field will take all prompt text, including both content and stylistic terms. CLI Commands will not work in the prompt.',
text: 'This field will take all prompt text, including both content and stylistic terms. While weights can be included in the prompt, standard CLI Commands/parameters will not work.',
href: 'link/to/docs/feature3.html',
guideImage: 'asset/path.gif',
},
@ -27,17 +30,16 @@ export const FEATURES: Record<Feature, FeatureHelpInfo> = {
guideImage: 'asset/path.gif',
},
[Feature.OTHER]: {
text: 'Additional Options',
href: 'link/to/docs/feature3.html',
text: 'These options will enable alternative processing modes for Invoke. Seamless tiling will work to generate repeating patterns in the output. High Resolution Optimization performs a two-step generation cycle, and should be used at higher resolutions when you desire a more coherent image/composition. ', href: 'link/to/docs/feature3.html',
guideImage: 'asset/path.gif',
},
[Feature.SEED]: {
text: 'Seed values provide an initial set of noise which guide the denoising process.',
text: 'Seed values provide an initial set of noise which guide the denoising process, and can be randomized or populated with a seed from a previous invocation. The Threshold feature can be used to mitigate undesirable outcomes at higher CFG values (try between 0-10), and Perlin can be used to add Perlin noise into the denoising process - Both serve to add variation to your outputs. ',
href: 'link/to/docs/feature3.html',
guideImage: 'asset/path.gif',
},
[Feature.VARIATIONS]: {
text: 'Try a variation with an amount of between 0 and 1 to change the output image for the set seed.',
text: 'Try a variation with an amount of between 0 and 1 to change the output image for the set seed - Interesting variations on the seed are found between 0.1 and 0.3.',
href: 'link/to/docs/feature3.html',
guideImage: 'asset/path.gif',
},
@ -47,8 +49,8 @@ export const FEATURES: Record<Feature, FeatureHelpInfo> = {
guideImage: 'asset/path.gif',
},
[Feature.FACE_CORRECTION]: {
text: 'Using GFPGAN or CodeFormer, Face Correction will attempt to identify faces in outputs, and correct any defects/abnormalities. Higher values will apply a stronger corrective pressure on outputs.',
href: 'link/to/docs/feature2.html',
text: 'Using GFPGAN, Face Correction will attempt to identify faces in outputs, and correct any defects/abnormalities. Higher values will apply a stronger corrective pressure on outputs, resulting in more appealing faces (with less respect for accuracy of the original subject).',
href: 'link/to/docs/feature3.html',
guideImage: 'asset/path.gif',
},
[Feature.IMAGE_TO_IMAGE]: {

1
frontend/src/app/invokeai.d.ts vendored
View File

@ -55,6 +55,7 @@ export declare type CommonGeneratedImageMetadata = {
width: number;
height: number;
seamless: boolean;
hires_fix: boolean;
extra: null | Record<string, never>; // Pending development of RFC #266
};

2
frontend/src/app/socketio/emitters.ts
View File

@ -76,7 +76,7 @@ const makeSocketIOEmitters = (
const { gfpganStrength } = getState().options;
const gfpganParameters = {
gfpgan_strength: gfpganStrength,
facetool_strength: gfpganStrength,
};
socketio.emit('runPostprocessing', imageToProcess, {
type: 'gfpgan',

10
frontend/src/common/util/parameterTranslation.ts
View File

@ -29,6 +29,7 @@ export const frontendToBackendParameters = (
sampler,
seed,
seamless,
hiresFix,
shouldUseInitImage,
img2imgStrength,
initialImagePath,
@ -59,6 +60,7 @@ export const frontendToBackendParameters = (
sampler_name: sampler,
seed,
seamless,
hires_fix: hiresFix,
progress_images: shouldDisplayInProgress,
};
@ -123,10 +125,11 @@ export const backendToFrontendParameters = (parameters: {
sampler_name,
seed,
seamless,
hires_fix,
progress_images,
variation_amount,
with_variations,
gfpgan_strength,
facetool_strength,
upscale,
init_img,
init_mask,
@ -151,9 +154,9 @@ export const backendToFrontendParameters = (parameters: {
}
}
if (gfpgan_strength > 0) {
if (facetool_strength > 0) {
options.shouldRunGFPGAN = true;
options.gfpganStrength = gfpgan_strength;
options.gfpganStrength = facetool_strength;
}
if (upscale) {
@ -185,6 +188,7 @@ export const backendToFrontendParameters = (parameters: {
options.sampler = sampler_name;
options.seed = seed;
options.seamless = seamless;
options.hiresFix = hires_fix;
}
return options;

12
frontend/src/features/gallery/ImageMetaDataViewer/ImageMetadataViewer.tsx
View File

@ -16,11 +16,13 @@ import {
setCfgScale,
setGfpganStrength,
setHeight,
setHiresFix,
setImg2imgStrength,
setInitialImagePath,
setMaskPath,
setPrompt,
setSampler,
setSeamless,
setSeed,
setSeedWeights,
setShouldFitToWidthHeight,
@ -116,6 +118,7 @@ const ImageMetadataViewer = memo(
steps,
cfg_scale,
seamless,
hires_fix,
width,
height,
strength,
@ -214,7 +217,14 @@ const ImageMetadataViewer = memo(
<MetadataItem
label="Seamless"
value={seamless}
onClick={() => dispatch(setWidth(seamless))}
onClick={() => dispatch(setSeamless(seamless))}
/>
)}
{hires_fix && (
<MetadataItem
label="High Resolution Optimization"
value={hires_fix}
onClick={() => dispatch(setHiresFix(hires_fix))}
/>
)}
{width && (

32
frontend/src/features/options/HiresOptions.tsx Normal file
View File

@ -0,0 +1,32 @@
import { Flex } from '@chakra-ui/react';
import { RootState } from '../../app/store';
import { useAppDispatch, useAppSelector } from '../../app/store';
import { setHiresFix } from './optionsSlice';
import { ChangeEvent } from 'react';
import IAISwitch from '../../common/components/IAISwitch';
/**
* Image output options. Includes width, height, seamless tiling.
*/
const HiresOptions = () => {
const dispatch = useAppDispatch();
const hiresFix = useAppSelector((state: RootState) => state.options.hiresFix);
const handleChangeHiresFix = (e: ChangeEvent<HTMLInputElement>) =>
dispatch(setHiresFix(e.target.checked));
return (
<Flex gap={2} direction={'column'}>
<IAISwitch
label="High Res Optimization"
fontSize={'md'}
isChecked={hiresFix}
onChange={handleChangeHiresFix}
/>
</Flex>
);
};
export default HiresOptions;

25
frontend/src/features/options/OutputOptions.tsx
View File

@ -1,29 +1,14 @@
import { Flex } from '@chakra-ui/react';
import { RootState } from '../../app/store';
import { useAppDispatch, useAppSelector } from '../../app/store';
import { setSeamless } from './optionsSlice';
import { ChangeEvent } from 'react';
import IAISwitch from '../../common/components/IAISwitch';
/**
* Image output options. Includes width, height, seamless tiling.
*/
import HiresOptions from './HiresOptions';
import SeamlessOptions from './SeamlessOptions';
const OutputOptions = () => {
const dispatch = useAppDispatch();
const seamless = useAppSelector((state: RootState) => state.options.seamless);
const handleChangeSeamless = (e: ChangeEvent<HTMLInputElement>) =>
dispatch(setSeamless(e.target.checked));
return (
<Flex gap={2} direction={'column'}>
<IAISwitch
label="Seamless tiling"
fontSize={'md'}
isChecked={seamless}
onChange={handleChangeSeamless}
/>
<SeamlessOptions />
<HiresOptions />
</Flex>
);
};

28
frontend/src/features/options/SeamlessOptions.tsx Normal file
View File

@ -0,0 +1,28 @@
import { Flex } from '@chakra-ui/react';
import { RootState } from '../../app/store';
import { useAppDispatch, useAppSelector } from '../../app/store';
import { setSeamless } from './optionsSlice';
import { ChangeEvent } from 'react';
import IAISwitch from '../../common/components/IAISwitch';
const SeamlessOptions = () => {
const dispatch = useAppDispatch();
const seamless = useAppSelector((state: RootState) => state.options.seamless);
const handleChangeSeamless = (e: ChangeEvent<HTMLInputElement>) =>
dispatch(setSeamless(e.target.checked));
return (
<Flex gap={2} direction={'column'}>
<IAISwitch
label="Seamless tiling"
fontSize={'md'}
isChecked={seamless}
onChange={handleChangeSeamless}
/>
</Flex>
);
};
export default SeamlessOptions;

8
frontend/src/features/options/optionsSlice.ts
View File

@ -25,6 +25,7 @@ export interface OptionsState {
initialImagePath: string | null;
maskPath: string;
seamless: boolean;
hiresFix: boolean;
shouldFitToWidthHeight: boolean;
shouldGenerateVariations: boolean;
variationAmount: number;
@ -50,6 +51,7 @@ const initialOptionsState: OptionsState = {
perlin: 0,
seed: 0,
seamless: false,
hiresFix: false,
shouldUseInitImage: false,
img2imgStrength: 0.75,
initialImagePath: null,
@ -138,6 +140,9 @@ export const optionsSlice = createSlice({
setSeamless: (state, action: PayloadAction<boolean>) => {
state.seamless = action.payload;
},
setHiresFix: (state, action: PayloadAction<boolean>) => {
state.hiresFix = action.payload;
},
setShouldFitToWidthHeight: (state, action: PayloadAction<boolean>) => {
state.shouldFitToWidthHeight = action.payload;
},
@ -180,6 +185,7 @@ export const optionsSlice = createSlice({
threshold,
perlin,
seamless,
hires_fix,
width,
height,
strength,
@ -256,6 +262,7 @@ export const optionsSlice = createSlice({
if (perlin) state.perlin = perlin;
if (typeof perlin === 'undefined') state.perlin = 0;
if (typeof seamless === 'boolean') state.seamless = seamless;
if (typeof hires_fix === 'boolean') state.hiresFix = hires_fix;
if (width) state.width = width;
if (height) state.height = height;
},
@ -301,6 +308,7 @@ export const {
setSampler,
setSeed,
setSeamless,
setHiresFix,
setImg2imgStrength,
setGfpganStrength,
setUpscalingLevel,

36
ldm/generate.py
View File

@ -35,6 +35,24 @@ from ldm.invoke.devices import choose_torch_device, choose_precision
from ldm.invoke.conditioning import get_uc_and_c
from ldm.invoke.model_cache import ModelCache
def fix_func(orig):
if hasattr(torch.backends, 'mps') and torch.backends.mps.is_available():
def new_func(*args, **kw):
device = kw.get("device", "mps")
kw["device"]="cpu"
return orig(*args, **kw).to(device)
return new_func
return orig
torch.rand = fix_func(torch.rand)
torch.rand_like = fix_func(torch.rand_like)
torch.randn = fix_func(torch.randn)
torch.randn_like = fix_func(torch.randn_like)
torch.randint = fix_func(torch.randint)
torch.randint_like = fix_func(torch.randint_like)
torch.bernoulli = fix_func(torch.bernoulli)
torch.multinomial = fix_func(torch.multinomial)
"""Simplified text to image API for stable diffusion/latent diffusion
Example Usage:
@ -137,6 +155,7 @@ class Generate:
self.precision = precision
self.strength = 0.75
self.seamless = False
self.hires_fix = False
self.embedding_path = embedding_path
self.model = None # empty for now
self.model_hash = None
@ -156,6 +175,7 @@ class Generate:
# device to Generate(). However the device was then ignored, so
# it wasn't actually doing anything. This logic could be reinstated.
device_type = choose_torch_device()
print(f'>> Using device_type {device_type}')
self.device = torch.device(device_type)
if full_precision:
if self.precision != 'auto':
@ -236,7 +256,7 @@ class Generate:
embiggen_tiles = None,
# these are specific to GFPGAN/ESRGAN
facetool = None,
gfpgan_strength = 0,
facetool_strength = 0,
codeformer_fidelity = None,
save_original = False,
upscale = None,
@ -256,9 +276,10 @@ class Generate:
height // height of image, in multiples of 64 (512)
cfg_scale // how strongly the prompt influences the image (7.5) (must be >1)
seamless // whether the generated image should tile
hires_fix // whether the Hires Fix should be applied during generation
init_img // path to an initial image
strength // strength for noising/unnoising init_img. 0.0 preserves image exactly, 1.0 replaces it completely
gfpgan_strength // strength for GFPGAN. 0.0 preserves image exactly, 1.0 replaces it completely
facetool_strength // strength for GFPGAN/CodeFormer. 0.0 preserves image exactly, 1.0 replaces it completely
ddim_eta // image randomness (eta=0.0 means the same seed always produces the same image)
step_callback // a function or method that will be called each step
image_callback // a function or method that will be called each time an image is generated
@ -289,6 +310,7 @@ class Generate:
width = width or self.width
height = height or self.height
seamless = seamless or self.seamless
hires_fix = hires_fix or self.hires_fix
cfg_scale = cfg_scale or self.cfg_scale
ddim_eta = ddim_eta or self.ddim_eta
iterations = iterations or self.iterations
@ -405,11 +427,11 @@ class Generate:
reference_image_path = init_color,
image_callback = image_callback)
if upscale is not None or gfpgan_strength > 0:
if upscale is not None or facetool_strength > 0:
self.upscale_and_reconstruct(results,
upscale = upscale,
facetool = facetool,
strength = gfpgan_strength,
strength = facetool_strength,
codeformer_fidelity = codeformer_fidelity,
save_original = save_original,
image_callback = image_callback)
@ -452,7 +474,7 @@ class Generate:
self,
image_path,
tool = 'gfpgan', # one of 'upscale', 'gfpgan', 'codeformer', 'outpaint', or 'embiggen'
gfpgan_strength = 0.0,
facetool_strength = 0.0,
codeformer_fidelity = 0.75,
upscale = None,
out_direction = None,
@ -499,11 +521,11 @@ class Generate:
facetool = 'codeformer'
elif tool == 'upscale':
facetool = 'gfpgan' # but won't be run
gfpgan_strength = 0
facetool_strength = 0
return self.upscale_and_reconstruct(
[[image,seed]],
facetool = facetool,
strength = gfpgan_strength,
strength = facetool_strength,
codeformer_fidelity = codeformer_fidelity,
save_original = save_original,
upscale = upscale,

18
ldm/invoke/args.py
View File

@ -242,9 +242,13 @@ class Args(object):
else:
switches.append(f'-A {a["sampler_name"]}')
# gfpgan-specific parameters
if a['gfpgan_strength']:
switches.append(f'-G {a["gfpgan_strength"]}')
# facetool-specific parameters
if a['facetool']:
switches.append(f'-ft {a["facetool"]}')
if a['facetool_strength']:
switches.append(f'-G {a["facetool_strength"]}')
if a['codeformer_fidelity']:
switches.append(f'-cf {a["codeformer_fidelity"]}')
if a['outcrop']:
switches.append(f'-c {" ".join([str(u) for u in a["outcrop"]])}')
@ -636,6 +640,13 @@ class Args(object):
dest='hires_fix',
help='Create hires image using img2img to prevent duplicated objects'
)
render_group.add_argument(
'--save_intermediates',
type=int,
default=0,
dest='save_intermediates',
help='Save every nth intermediate image into an "intermediates" directory within the output directory'
)
img2img_group.add_argument(
'-I',
'--init_img',
@ -692,6 +703,7 @@ class Args(object):
)
postprocessing_group.add_argument(
'-G',
'--facetool_strength',
'--gfpgan_strength',
type=float,
help='The strength at which to apply the face restoration to the result.',

5
ldm/invoke/readline.py
View File

@ -33,6 +33,7 @@ COMMANDS = (
'--perlin',
'--grid','-g',
'--individual','-i',
'--save_intermediates',
'--init_img','-I',
'--init_mask','-M',
'--init_color',
@ -43,7 +44,9 @@ COMMANDS = (
'--embedding_path',
'--device',
'--grid','-g',
'--gfpgan_strength','-G',
'--facetool','-ft',
'--facetool_strength','-G',
'--codeformer_fidelity','-cf',
'--upscale','-U',
'-save_orig','--save_original',
'--skip_normalize','-x',

5
ldm/invoke/server.py
View File

@ -31,12 +31,13 @@ def build_opt(post_data, seed, gfpgan_model_exists):
setattr(opt, 'embiggen', None)
setattr(opt, 'embiggen_tiles', None)
setattr(opt, 'gfpgan_strength', float(post_data['gfpgan_strength']) if gfpgan_model_exists else 0)
setattr(opt, 'facetool_strength', float(post_data['facetool_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, 'threshold', float(post_data['threshold']))
setattr(opt, 'perlin', float(post_data['perlin']))
setattr(opt, 'hires_fix', 'hires_fix' in post_data)
setattr(opt, 'variation_amount', float(post_data['variation_amount']) if int(post_data['seed']) != -1 else 0)
setattr(opt, 'with_variations', [])
setattr(opt, 'embiggen', None)
@ -196,7 +197,7 @@ class DreamServer(BaseHTTPRequestHandler):
) + '\n',"utf-8"))
# control state of the "postprocessing..." message
upscaling_requested = opt.upscale or opt.gfpgan_strength > 0
upscaling_requested = opt.upscale or opt.facetool_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:

3
ldm/models/diffusion/ksampler.py
View File

@ -98,7 +98,8 @@ class KSampler(Sampler):
rho=7.,
device=self.device,
)
self.sigmas = self.karras_sigmas
self.sigmas = self.model_sigmas
#self.sigmas = self.karras_sigmas
# ALERT: We are completely overriding the sample() method in the base class, which
# means that inpainting will not work. To get this to work we need to be able to

2
ldm/models/diffusion/sampler.py
View File

@ -140,7 +140,7 @@ class Sampler(object):
conditioning=None,
callback=None,
normals_sequence=None,
img_callback=None,
img_callback=None, # TODO: this is very confusing because it is called "step_callback" elsewhere. Change.
quantize_x0=False,
eta=0.0,
mask=None,

14
ldm/modules/diffusionmodules/model.py
View File

@ -49,9 +49,15 @@ class Upsample(nn.Module):
padding=1)
def forward(self, x):
cpu_m1_cond = True if hasattr(torch.backends, 'mps') and torch.backends.mps.is_available() and \
x.size()[0] * x.size()[1] * x.size()[2] * x.size()[3] % 2**27 == 0 else False
if cpu_m1_cond:
x = x.to('cpu') # send to cpu
x = torch.nn.functional.interpolate(x, scale_factor=2.0, mode="nearest")
if self.with_conv:
x = self.conv(x)
if cpu_m1_cond:
x = x.to('mps') # return to mps
return x
@ -117,6 +123,14 @@ class ResnetBlock(nn.Module):
padding=0)
def forward(self, x, temb):
if hasattr(torch.backends, 'mps') and torch.backends.mps.is_available():
x_size = x.size()
if (x_size[0] * x_size[1] * x_size[2] * x_size[3]) % 2**29 == 0:
self.to('cpu')
x = x.to('cpu')
else:
self.to('mps')
x = x.to('mps')
h = self.norm1(x)
h = silu(h)
h = self.conv1(h)

21
notebooks/Stable_Diffusion_AI_Notebook.ipynb
View File

@ -6,7 +6,7 @@
"id": "ycYWcsEKc6w7"
},
"source": [
"# Stable Diffusion AI Notebook (Release 1.14)\n",
"# Stable Diffusion AI Notebook (Release 2.0.0)\n",
"\n",
"<img src=\"https://user-images.githubusercontent.com/60411196/186547976-d9de378a-9de8-4201-9c25-c057a9c59bad.jpeg\" alt=\"stable-diffusion-ai\" width=\"170px\"/> <br>\n",
"#### Instructions:\n",
@ -58,8 +58,8 @@
"from os.path import exists\n",
"\n",
"!git clone --quiet https://github.com/invoke-ai/InvokeAI.git # Original repo\n",
"%cd /content/stable-diffusion/\n",
"!git checkout --quiet tags/release-1.14.1"
"%cd /content/InvokeAI/\n",
"!git checkout --quiet tags/v2.0.0"
]
},
{
@ -79,6 +79,7 @@
"!pip install colab-xterm\n",
"!pip install -r requirements-lin-win-colab-CUDA.txt\n",
"!pip install clean-fid torchtext\n",
"!pip install transformers\n",
"gc.collect()"
]
},
@ -106,7 +107,7 @@
"source": [
"#@title 5. Load small ML models required\n",
"import gc\n",
"%cd /content/stable-diffusion/\n",
"%cd /content/InvokeAI/\n",
"!python scripts/preload_models.py\n",
"gc.collect()"
]
@ -171,18 +172,18 @@
"import os \n",
"\n",
"# Folder creation if it doesn't exist\n",
"if exists(\"/content/stable-diffusion/models/ldm/stable-diffusion-v1\"):\n",
"if exists(\"/content/InvokeAI/models/ldm/stable-diffusion-v1\"):\n",
" print(\"❗ Dir stable-diffusion-v1 already exists\")\n",
"else:\n",
" %mkdir /content/stable-diffusion/models/ldm/stable-diffusion-v1\n",
" %mkdir /content/InvokeAI/models/ldm/stable-diffusion-v1\n",
" print(\"✅ Dir stable-diffusion-v1 created\")\n",
"\n",
"# Symbolic link if it doesn't exist\n",
"if exists(\"/content/stable-diffusion/models/ldm/stable-diffusion-v1/model.ckpt\"):\n",
"if exists(\"/content/InvokeAI/models/ldm/stable-diffusion-v1/model.ckpt\"):\n",
" print(\"❗ Symlink already created\")\n",
"else: \n",
" src = model_path\n",
" dst = '/content/stable-diffusion/models/ldm/stable-diffusion-v1/model.ckpt'\n",
" dst = '/content/InvokeAI/models/ldm/stable-diffusion-v1/model.ckpt'\n",
" os.symlink(src, dst) \n",
" print(\"✅ Symbolic link created successfully\")"
]
@ -207,7 +208,7 @@
"source": [
"#@title 9. Run Terminal and Execute Dream bot\n",
"#@markdown <font color=\"blue\">Steps:</font> <br>\n",
"#@markdown 1. Execute command `python scripts/dream.py` to run dream bot.<br>\n",
"#@markdown 1. Execute command `python scripts/invoke.py` to run InvokeAI.<br>\n",
"#@markdown 2. After initialized you'll see `Dream>` line.<br>\n",
"#@markdown 3. Example text: `Astronaut floating in a distant galaxy` <br>\n",
"#@markdown 4. To quit Dream bot use: `q` command.<br>\n",
@ -233,7 +234,7 @@
"%matplotlib inline\n",
"\n",
"images = []\n",
"for img_path in sorted(glob.glob('/content/stable-diffusion/outputs/img-samples/*.png'), reverse=True):\n",
"for img_path in sorted(glob.glob('/content/InvokeAI/outputs/img-samples/*.png'), reverse=True):\n",
" images.append(mpimg.imread(img_path))\n",
"\n",
"images = images[:15] \n",

15
scripts/dream.py
View File

@ -1,12 +1,11 @@
#!/usr/bin/env python3
# Copyright (c) 2022 Lincoln D. Stein (https://github.com/lstein)
import sys
import os.path
script_path = sys.argv[0]
script_args = sys.argv[1:]
script_dir,script_name = os.path.split(script_path)
script_dest = os.path.join(script_dir,'invoke.py')
os.execlp('python3','python3',script_dest,*script_args)
import warnings
import invoke
if __name__ == '__main__':
warnings.warn("dream.py is being deprecated, please run invoke.py for the "
"new UI/API or legacy_api.py for the old API",
DeprecationWarning)
invoke.main()

17
scripts/invoke.py
View File

@ -236,6 +236,7 @@ def main_loop(gen, opt, infile):
grid_images = dict() # seed -> Image, only used if `opt.grid`
prior_variations = opt.with_variations or []
prefix = file_writer.unique_prefix()
step_callback = make_step_callback(gen, opt, prefix) if opt.save_intermediates > 0 else None
def image_writer(image, seed, upscaled=False, first_seed=None, use_prefix=None):
# note the seed is the seed of the current image
@ -297,6 +298,7 @@ def main_loop(gen, opt, infile):
opt.last_operation='generate'
gen.prompt2image(
image_callback=image_writer,
step_callback=step_callback,
catch_interrupts=catch_ctrl_c,
**vars(opt)
)
@ -494,7 +496,7 @@ def do_postprocess (gen, opt, callback):
file_path = os.path.join(opt.outdir,file_path)
tool=None
if opt.gfpgan_strength > 0:
if opt.facetool_strength > 0:
tool = opt.facetool
elif opt.embiggen:
tool = 'embiggen'
@ -510,7 +512,7 @@ def do_postprocess (gen, opt, callback):
gen.apply_postprocessor(
image_path = file_path,
tool = tool,
gfpgan_strength = opt.gfpgan_strength,
facetool_strength = opt.facetool_strength,
codeformer_fidelity = opt.codeformer_fidelity,
save_original = opt.save_original,
upscale = opt.upscale,
@ -666,6 +668,17 @@ def load_face_restoration(opt):
return gfpgan,codeformer,esrgan
def make_step_callback(gen, opt, prefix):
destination = os.path.join(opt.outdir,'intermediates',prefix)
os.makedirs(destination,exist_ok=True)
print(f'>> Intermediate images will be written into {destination}')
def callback(img, step):
if step % opt.save_intermediates == 0 or step == opt.steps-1:
filename = os.path.join(destination,f'{step:04}.png')
image = gen.sample_to_image(img)
image.save(filename,'PNG')
return callback
def retrieve_dream_command(opt,file_path,completer):
'''
Given a full or partial path to a previously-generated image file,

6
server/models.py
View File

@ -35,13 +35,14 @@ class DreamBase():
perlin: float = 0.0
sampler_name: string = 'klms'
seamless: bool = False
hires_fix: bool = False
model: str = None # The model to use (currently unused)
embeddings = None # The embeddings to use (currently unused)
progress_images: bool = False
# GFPGAN
enable_gfpgan: bool
gfpgan_strength: float = 0
facetool_strength: float = 0
# Upscale
enable_upscale: bool
@ -91,12 +92,13 @@ class DreamBase():
# model: str = None # The model to use (currently unused)
# embeddings = None # The embeddings to use (currently unused)
self.seamless = 'seamless' in j
self.hires_fix = 'hires_fix' in j
self.progress_images = 'progress_images' in j
# GFPGAN
self.enable_gfpgan = 'enable_gfpgan' in j and bool(j.get('enable_gfpgan'))
if self.enable_gfpgan:
self.gfpgan_strength = float(j.get('gfpgan_strength'))
self.facetool_strength = float(j.get('facetool_strength'))
# Upscale
self.enable_upscale = 'enable_upscale' in j and bool(j.get('enable_upscale'))

9
server/services.py
View File

@ -334,11 +334,11 @@ class GeneratorService:
# TODO: Support no generation (just upscaling/gfpgan)
upscale = None if not jobRequest.enable_upscale else jobRequest.upscale
gfpgan_strength = 0 if not jobRequest.enable_gfpgan else jobRequest.gfpgan_strength
facetool_strength = 0 if not jobRequest.enable_gfpgan else jobRequest.facetool_strength
if not jobRequest.enable_generate:
# If not generating, check if we're upscaling or running gfpgan
if not upscale and not gfpgan_strength:
if not upscale and not facetool_strength:
# Invalid settings (TODO: Add message to help user)
raise CanceledException()
@ -347,7 +347,7 @@ class GeneratorService:
self.__model.upscale_and_reconstruct(
image_list = [[image,0]],
upscale = upscale,
strength = gfpgan_strength,
strength = facetool_strength,
save_original = False,
image_callback = lambda image, seed, upscaled=False: self.__on_image_result(jobRequest, image, seed, upscaled))
@ -371,10 +371,11 @@ class GeneratorService:
steps = jobRequest.steps,
variation_amount = jobRequest.variation_amount,
with_variations = jobRequest.with_variations,
gfpgan_strength = gfpgan_strength,
facetool_strength = facetool_strength,
upscale = upscale,
sampler_name = jobRequest.sampler_name,
seamless = jobRequest.seamless,
hires_fix = jobRequest.hires_fix,
embiggen = jobRequest.embiggen,
embiggen_tiles = jobRequest.embiggen_tiles,
step_callback = lambda sample, step: self.__on_progress(jobRequest, sample, step),

4
static/dream_web/index.html
View File

@ -144,8 +144,8 @@
<input type="checkbox" name="enable_gfpgan" id="enable_gfpgan">
<label for="enable_gfpgan">Enable gfpgan</label>
</legend>
<label title="Strength of the gfpgan (face fixing) algorithm." for="gfpgan_strength">GPFGAN Strength:</label>
<input value="0.8" min="0" max="1" type="number" id="gfpgan_strength" name="gfpgan_strength" step="0.05">
<label title="Strength of the gfpgan (face fixing) algorithm." for="facetool_strength">GPFGAN Strength:</label>
<input value="0.8" min="0" max="1" type="number" id="facetool_strength" name="facetool_strength" step="0.05">
</fieldset>
<fieldset id="upscale">
<legend>

4
static/legacy_web/index.html
View File

@ -100,8 +100,8 @@
</fieldset>
<fieldset id="gfpgan">
<div class="section-header">Post-processing options</div>
<label title="Strength of the gfpgan (face fixing) algorithm." for="gfpgan_strength">GPFGAN Strength (0 to disable):</label>
<input value="0.0" min="0" max="1" type="number" id="gfpgan_strength" name="gfpgan_strength" step="0.1">
<label title="Strength of the gfpgan (face fixing) algorithm." for="facetool_strength">GPFGAN Strength (0 to disable):</label>
<input value="0.0" min="0" max="1" type="number" id="facetool_strength" name="facetool_strength" step="0.1">
<label title="Upscaling to perform using ESRGAN." for="upscale_level">Upscaling Level</label>
<select id="upscale_level" name="upscale_level" value="">
<option value="" selected>None</option>