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 development

Browse Source
This commit is contained in:
Peter Baylies 2022-09-08 22:54:26 -04:00 committed by GitHub
commit 7f0cc7072b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
8 changed files with 118 additions and 137 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
README.md
View File

@ -1,7 +1,7 @@
<h1 align='center'><b>Stable Diffusion Dream Script</b></h1>
<p align='center'>
<img src="static/logo_temp.png"/>
<img src="static/logo.png"/>
</p>
<p align="center">
@ -22,7 +22,7 @@ text-to-image generator. This fork supports:
generating images in your browser.
3. Support for img2img in which you provide a seed image to guide the
image creation
image creation. (inpainting & masking coming soon)
4. Preliminary inpainting support.
@ -33,9 +33,9 @@ text-to-image generator. This fork supports:
7. Weighted subprompts for prompt tuning.
8. [Image variations](VARIATIONS.md) which allow you to systematically
generate variations of an image you like and combine two or more
images together to combine the best features of both.
7. [Image variations](VARIATIONS.md) which allow you to systematically
generate variations of an image you like and combine two or more
images together to combine the best features of both.
9. Textual inversion for customization of the prompt language and images.
@ -387,9 +387,8 @@ and introducing a new vocabulary to the fixed model.
To train, prepare a folder that contains images sized at 512x512 and execute the following:
WINDOWS: As the default backend is not available on Windows, if you're using that platform, set the environment variable `PL_TORCH_DISTRIBUTED_BACKEND=gloo`
```
(ldm) ~/stable-diffusion$ python3 ./main.py --base ./configs/stable-diffusion/v1-finetune.yaml \
-t \
@ -460,7 +459,7 @@ repository and associated paper for details and limitations.
- WebUI supports GFPGAN/ESRGAN facial reconstruction and upscaling [Kevin Gibbons](https://github.com/bakkot)
- WebUI supports incremental display of in-progress images during generation [Kevin Gibbons](https://github.com/bakkot)
- A new configuration file scheme that allows new models (including upcoming stable-diffusion-v1.5)
to be added without altering the code. ([David Wager](https://github.com/maddavid12))
to be added without altering the code. ([David Wager](https://github.com/maddavid12))
- Can specify --grid on dream.py command line as the default.
- Miscellaneous internal bug and stability fixes.
- Works on M1 Apple hardware.
@ -484,8 +483,8 @@ There are separate installation walkthroughs for [Linux](#linux), [Windows](#win
```
~$ wget https://repo.anaconda.com/archive/Anaconda3-2022.05-Linux-x86_64.sh
~$ chmod +x Anaconda3-2022.05-Linux-x86_64.sh
~$ ./Anaconda3-2022.05-Linux-x86_64.sh
~$ chmod +x Anaconda3-2022.05-Linux-x86_64.sh
~$ ./Anaconda3-2022.05-Linux-x86_64.sh
```
After installing anaconda, you should log out of your system and log back in. If the installation
@ -674,9 +673,9 @@ python scripts\dream.py
```
10. Subsequently, to relaunch the script, first activate the Anaconda
command window (step 3), enter the stable-diffusion directory (step 5,
"cd \path\to\stable-diffusion"), run "conda activate ldm" (step 6b),
and then launch the dream script (step 9).
command window (step 3), enter the stable-diffusion directory (step 5,
"cd \path\to\stable-diffusion"), run "conda activate ldm" (step 6b),
and then launch the dream script (step 9).
**Note:** Tildebyte has written an alternative ["Easy peasy Windows
install"](https://github.com/lstein/stable-diffusion/wiki/Easy-peasy-Windows-install)

181
ldm/dream/server.py
View File

@ -1,11 +1,61 @@
import argparse
import json
import base64
import mimetypes
import os
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from ldm.dream.pngwriter import PngWriter
from ldm.dream.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', seed 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, '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
@ -81,59 +131,15 @@ class DreamServer(BaseHTTPRequestHandler):
content_length = int(self.headers['Content-Length'])
post_data = json.loads(self.rfile.read(content_length))
prompt = post_data['prompt']
initimg = post_data['initimg']
strength = float(post_data['strength'])
iterations = int(post_data['iterations'])
steps = int(post_data['steps'])
width = int(post_data['width'])
height = int(post_data['height'])
fit = 'fit' in post_data
seamless = 'seamless' in post_data
cfgscale = float(post_data['cfgscale'])
sampler_name = post_data['sampler']
variation_amount = float(post_data['variation_amount'])
with_variations = post_data['with_variations']
gfpgan_strength = float(post_data['gfpgan_strength']) if gfpgan_model_exists else 0
upscale_level = post_data['upscale_level']
upscale_strength = post_data['upscale_strength']
upscale = [int(upscale_level),float(upscale_strength)] if upscale_level != '' else None
progress_images = 'progress_images' in post_data
threshold = float(post_data['threshold'])
perlin = float(post_data['perlin'])
seed = None if int(post_data['seed']) == -1 else int(post_data['seed'])
if with_variations != '':
parts = []
broken = False
for part in 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:
vseed = int(seed_and_weight[0])
vweight = float(seed_and_weight[1])
except ValueError:
print(f'could not parse with_variation part "{part}"')
broken = True
break
parts.append([vseed, vweight])
if broken:
raise CanceledException
if len(parts) > 0:
with_variations = parts
else:
with_variations = None
opt = build_opt(post_data, self.model.seed, gfpgan_model_exists)
self.canceled.clear()
print(f">> Request to generate with prompt: {prompt}")
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','')
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
@ -146,9 +152,21 @@ class DreamServer(BaseHTTPRequestHandler):
# entry should not be inserted into the image list.
def image_done(image, seed, upscaled=False):
name = f'{prefix}.{seed}.png'
path = pngwriter.save_image_and_prompt_to_png(image, f'{prompt} -S{seed}', name)
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)
config['seed'] = seed
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:
@ -159,24 +177,24 @@ class DreamServer(BaseHTTPRequestHandler):
) + '\n',"utf-8"))
# control state of the "postprocessing..." message
upscaling_requested = upscale or gfpgan_strength>0
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
images_generated += 1
if upscaling_requested:
action = None
if images_generated >= iterations:
if images_upscaled < iterations:
if images_generated >= opt.iterations:
if images_upscaled < opt.iterations:
action = 'upscaling-started'
else:
action = 'upscaling-done'
if action:
x = images_upscaled+1
x = images_upscaled + 1
self.wfile.write(bytes(json.dumps(
{'event':action,'processed_file_cnt':f'{x}/{iterations}'}
{'event': action, 'processed_file_cnt': f'{x}/{opt.iterations}'}
) + '\n',"utf-8"))
step_writer = PngWriter(os.path.join(self.outdir, "intermediates"))
@ -189,10 +207,10 @@ class DreamServer(BaseHTTPRequestHandler):
# 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 progress_images and step % 5 == 0 and step < steps - 1:
if opt.progress_images and step % 5 == 0 and step < opt.steps - 1:
image = self.model.sample_to_image(sample)
name = f'{prefix}.{seed}.{step_index}.png'
metadata = f'{prompt} -S{seed} [intermediate]'
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(
@ -200,53 +218,20 @@ class DreamServer(BaseHTTPRequestHandler):
) + '\n',"utf-8"))
try:
if initimg is None:
if opt.init_img is None:
# Run txt2img
self.model.prompt2image(prompt,
iterations=iterations,
cfg_scale = cfgscale,
width = width,
height = height,
seed = seed,
steps = steps,
variation_amount = variation_amount,
with_variations = with_variations,
gfpgan_strength = gfpgan_strength,
upscale = upscale,
sampler_name = sampler_name,
seamless = seamless,
step_callback=image_progress,
image_callback=image_done,
threshold=threshold,
perlin=perlin)
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 = initimg.split(",")[1] # Ignore mime type
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(prompt,
init_img = "./img2img-tmp.png",
strength = strength,
iterations = iterations,
cfg_scale = cfgscale,
seed = seed,
steps = steps,
variation_amount = variation_amount,
with_variations = with_variations,
sampler_name = sampler_name,
width = width,
height = height,
fit = fit,
seamless = seamless,
gfpgan_strength=gfpgan_strength,
upscale = upscale,
step_callback=image_progress,
image_callback=image_done,
threshold=threshold,
perlin=perlin)
self.model.prompt2image(**vars(opt1), step_callback=image_progress, image_callback=image_done)
finally:
# Remove the temp file
os.remove("./img2img-tmp.png")

4
ldm/modules/diffusionmodules/util.py
View File

@ -81,7 +81,9 @@ def make_ddim_timesteps(
# assert ddim_timesteps.shape[0] == num_ddim_timesteps
# add one to get the final alpha values right (the ones from first scale to data during sampling)
steps_out = ddim_timesteps + 1
# steps_out = ddim_timesteps + 1
steps_out = ddim_timesteps
if verbose:
print(f'Selected timesteps for ddim sampler: {steps_out}')
return steps_out

2
ldm/simplet2i.py
View File

@ -10,4 +10,4 @@ from ldm.generate import Generate
class T2I(Generate):
def __init__(self,**kwargs):
print(f'>> The ldm.simplet2i module is deprecated. Use ldm.generate instead. It is a drop-in replacement.')
super().__init__(kwargs)
super().__init__(kwargs)

BIN
static/dream_web/favicon.ico Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 1.1 KiB

15
static/dream_web/index.html
View File

@ -2,9 +2,8 @@
<head>
<title>Stable Diffusion Dream Server</title>
<meta charset="utf-8">
<link rel="icon" href="data:,">
<link rel="icon" type="image/x-icon" href="static/dream_web/favicon.ico" />
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<link rel="stylesheet" href="static/dream_web/index.css">
<script src="config.js"></script>
<script src="static/dream_web/index.js"></script>
@ -30,21 +29,21 @@
<input value="1" type="number" id="iterations" name="iterations" size="4">
<label for="steps">Steps:</label>
<input value="50" type="number" id="steps" name="steps">
<label for="cfgscale">Cfg Scale:</label>
<input value="7.5" type="number" id="cfgscale" name="cfgscale" step="any">
<label for="sampler">Sampler:</label>
<select id="sampler" name="sampler" value="k_lms">
<label for="cfg_scale">Cfg Scale:</label>
<input value="7.5" type="number" id="cfg_scale" name="cfg_scale" step="any">
<label for="sampler_name">Sampler:</label>
<select id="sampler_name" name="sampler_name" value="k_lms">
<option value="ddim">DDIM</option>
<option value="plms">PLMS</option>
<option value="k_lms" selected>KLMS</option>
<option value="k_dpm_2">KDPM_2</option>
<option value="k_dpm_2_a">KDPM_2A</option>
<option value="k_euler">KEULER</option>
<option value="k_euler_a">KEULER_A</option>
<option value="k_euler_a">KEULER_A</option>
<option value="k_heun">KHEUN</option>
</select>
<input type="checkbox" name="seamless" id="seamless">
<label for="seamless">Seamless circular tiling</label>
<label for="seamless">Seamless circular tiling</label>
<br>
<label title="Set to multiple of 64" for="width">Width:</label>
<select id="width" name="width" value="512">

28
static/dream_web/index.js
View File

@ -9,7 +9,13 @@ function toBase64(file) {
function appendOutput(src, seed, config) {
let outputNode = document.createElement("figure");
let altText = seed.toString() + " | " + config.prompt;
let variations = config.with_variations;
if (config.variation_amount > 0) {
variations = (variations ? variations + ',' : '') + seed + ':' + config.variation_amount;
}
let baseseed = (config.with_variations || config.variation_amount > 0) ? config.seed : seed;
let altText = baseseed + ' | ' + (variations ? variations + ' | ' : '') + config.prompt;
// img needs width and height for lazy loading to work
const figureContents = `
@ -25,7 +31,7 @@ function appendOutput(src, seed, config) {
`;
outputNode.innerHTML = figureContents;
let figcaption = outputNode.querySelector('figcaption')
let figcaption = outputNode.querySelector('figcaption');
// Reload image config
figcaption.addEventListener('click', () => {
@ -34,21 +40,11 @@ function appendOutput(src, seed, config) {
if (k == 'initimg') { continue; }
form.querySelector(`*[name=${k}]`).value = config[k];
}
if (config.variation_amount > 0 || config.with_variations != '') {
document.querySelector("#seed").value = config.seed;
} else {
document.querySelector("#seed").value = seed;
}
if (config.variation_amount > 0) {
let oldVarAmt = document.querySelector("#variation_amount").value
let oldVariations = document.querySelector("#with_variations").value
let varSep = ''
document.querySelector("#variation_amount").value = 0;
if (document.querySelector("#with_variations").value != '') {
varSep = ","
}
document.querySelector("#with_variations").value = oldVariations + varSep + seed + ':' + config.variation_amount
document.querySelector("#seed").value = baseseed;
document.querySelector("#with_variations").value = variations || '';
if (document.querySelector("#variation_amount").value <= 0) {
document.querySelector("#variation_amount").value = 0.2;
}
saveFields(document.querySelector("#generate-form"));

BIN
static/logo_temp.png
View File

Binary file not shown.
Side by Side

Before

Width:  |  Height:  |  Size: 34 KiB