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 'main' into development

Browse Source 
- this syncs documentation and code
This commit is contained in:
Lincoln Stein 2022-10-09 14:47:27 -04:00
commit 8faa06fb15
100 changed files with 1976 additions and 1107 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
.github/workflows/test-dream-conda.yml → .github/workflows/test-invoke-conda.yml vendored
View File

@ -1,4 +1,4 @@
name: Test Dream with Conda
name: Test Invoke with Conda
on:
push:
branches:
@ -9,7 +9,7 @@ jobs:
strategy:
matrix:
os: [ ubuntu-latest, macos-12 ]
name: Test dream.py on ${{ matrix.os }} with conda
name: Test invoke.py on ${{ matrix.os }} with conda
runs-on: ${{ matrix.os }}
steps:
- run: |
@ -85,9 +85,9 @@ jobs:
fi
# Utterly hacky, but I don't know how else to do this
if [[ ${{ github.ref }} == 'refs/heads/master' ]]; then
time ${{ steps.vars.outputs.PYTHON_BIN }} scripts/dream.py --from_file tests/preflight_prompts.txt
time ${{ steps.vars.outputs.PYTHON_BIN }} scripts/invoke.py --from_file tests/preflight_prompts.txt
elif [[ ${{ github.ref }} == 'refs/heads/development' ]]; then
time ${{ steps.vars.outputs.PYTHON_BIN }} scripts/dream.py --from_file tests/dev_prompts.txt
time ${{ steps.vars.outputs.PYTHON_BIN }} scripts/invoke.py --from_file tests/dev_prompts.txt
fi
mkdir -p outputs/img-samples
- name: Archive results

3
.gitignore vendored
View File

@ -196,3 +196,6 @@ checkpoints
.vscode/
gfpgan/
models/ldm/stable-diffusion-v1/model.sha256
# GFPGAN model files
gfpgan/

32
README.md
View File

@ -24,7 +24,7 @@ _This repository was formally known as lstein/stable-diffusion_
[CI checks on dev badge]: https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/development?label=CI%20status%20on%20dev&cache=900&icon=github
[CI checks on dev link]: https://github.com/invoke-ai/InvokeAI/actions?query=branch%3Adevelopment
[CI checks on main badge]: https://flat.badgen.net/github/checks/invoke-ai/InvokeAI/main?label=CI%20status%20on%20main&cache=900&icon=github
[CI checks on main link]: https://github.com/invoke-ai/InvokeAI/actions/workflows/test-dream-conda.yml
[CI checks on main link]: https://github.com/invoke-ai/InvokeAI/actions/workflows/test-invoke-conda.yml
[discord badge]: https://flat.badgen.net/discord/members/ZmtBAhwWhy?icon=discord
[discord link]: https://discord.gg/ZmtBAhwWhy
[github forks badge]: https://flat.badgen.net/github/forks/invoke-ai/InvokeAI?icon=github
@ -41,10 +41,13 @@ _This repository was formally known as lstein/stable-diffusion_
[latest release link]: https://github.com/invoke-ai/InvokeAI/releases
</div>
This is a fork of [CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion), the open
source text-to-image generator. It provides a streamlined process with various new features and
options to aid the image generation process. It runs on Windows, Mac and Linux machines, and runs on
GPU cards with as little as 4 GB or RAM.
This is a fork of
[CompVis/stable-diffusion](https://github.com/CompVis/stable-diffusion),
the open source text-to-image generator. It provides a streamlined
process with various new features and options to aid the image
generation process. It runs on Windows, Mac and Linux machines, with
GPU cards with as little as 4 GB or RAM. It provides both a polished
Web interface, and an easy-to-use command-line interface.
_Note: This fork is rapidly evolving. Please use the
[Issues](https://github.com/invoke-ai/InvokeAI/issues) tab to report bugs and make feature
@ -90,20 +93,26 @@ You wil need one of the following:
- At least 6 GB of free disk space for the machine learning model, Python, and all its dependencies.
#### Note
**Note**
If you have a Nvidia 10xx series card (e.g. the 1080ti), please
run the dream script in full-precision mode as shown below.
Similarly, specify full-precision mode on Apple M1 hardware.
Precision is auto configured based on the device. If however you encounter
errors like 'expected type Float but found Half' or 'not implemented for Half'
you can try starting `dream.py` with the `--precision=float32` flag:
you can try starting `invoke.py` with the `--precision=float32` flag:
```bash
(ldm) ~/stable-diffusion$ python scripts/dream.py --precision=float32
(ldm) ~/stable-diffusion$ python scripts/invoke.py --precision=float32
```
### Features
#### Major Features
- [Web Server](docs/features/WEB.md)
- [Interactive Command Line Interface](docs/features/CLI.md)
- [Image To Image](docs/features/IMG2IMG.md)
- [Inpainting Support](docs/features/INPAINTING.md)
@ -111,10 +120,9 @@ you can try starting `dream.py` with the `--precision=float32` flag:
- [Upscaling, face-restoration and outpainting](docs/features/POSTPROCESS.md)
- [Seamless Tiling](docs/features/OTHER.md#seamless-tiling)
- [Google Colab](docs/features/OTHER.md#google-colab)
- [Web Server](docs/features/WEB.md)
- [Reading Prompts From File](docs/features/PROMPTS.md#reading-prompts-from-a-file)
- [Shortcut: Reusing Seeds](docs/features/OTHER.md#shortcuts-reusing-seeds)
- [Weighted Prompts](docs/features/PROMPTS.md#weighted-prompts)
- [Prompt Blending](docs/features/PROMPTS.md#prompt-blending)
- [Thresholding and Perlin Noise Initialization Options](/docs/features/OTHER.md#thresholding-and-perlin-noise-initialization-options)
- [Negative/Unconditioned Prompts](docs/features/PROMPTS.md#negative-and-unconditioned-prompts)
- [Variations](docs/features/VARIATIONS.md)
@ -130,7 +138,7 @@ you can try starting `dream.py` with the `--precision=float32` flag:
- vNEXT (TODO 2022)
- Deprecated `--full_precision` / `-F`. Simply omit it and `dream.py` will auto
- Deprecated `--full_precision` / `-F`. Simply omit it and `invoke.py` will auto
configure. To switch away from auto use the new flag like `--precision=float32`.
- v1.14 (11 September 2022)
@ -156,7 +164,7 @@ you can try starting `dream.py` with the `--precision=float32` flag:
- 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))
- Can specify --grid on dream.py command line as the default.
- Can specify --grid on invoke.py command line as the default.
- Miscellaneous internal bug and stability fixes.
- Works on M1 Apple hardware.
- Multiple bug fixes.

8
backend/invoke_ai_web_server.py
View File

@ -12,9 +12,9 @@ from PIL import Image
from uuid import uuid4
from threading import Event
from ldm.dream.args import Args, APP_ID, APP_VERSION, calculate_init_img_hash
from ldm.dream.pngwriter import PngWriter, retrieve_metadata
from ldm.dream.conditioning import split_weighted_subprompts
from ldm.invoke.args import Args, APP_ID, APP_VERSION, calculate_init_img_hash
from ldm.invoke.pngwriter import PngWriter, retrieve_metadata
from ldm.invoke.conditioning import split_weighted_subprompts
from backend.modules.parameters import parameters_to_command
@ -147,7 +147,7 @@ class InvokeAIWebServer:
self.init_image_path = os.path.join(self.result_path, 'init-images/')
self.mask_image_path = os.path.join(self.result_path, 'mask-images/')
# txt log
self.log_path = os.path.join(self.result_path, 'dream_log.txt')
self.log_path = os.path.join(self.result_path, 'invoke_log.txt')
# make all output paths
[
os.makedirs(path, exist_ok=True)

2
backend/modules/create_cmd_parser.py
View File

@ -1,6 +1,6 @@
import argparse
import os
from ldm.dream.args import PRECISION_CHOICES
from ldm.invoke.args import PRECISION_CHOICES
def create_cmd_parser():

2
backend/modules/parameters.py
View File

@ -15,7 +15,7 @@ SAMPLER_CHOICES = [
def parameters_to_command(params):
"""
Converts dict of parameters into a `dream.py` REPL command.
Converts dict of parameters into a `invoke.py` REPL command.
"""
switches = list()

12
backend/server.py
View File

@ -30,10 +30,10 @@ from send2trash import send2trash
from ldm.generate import Generate
from ldm.dream.restoration import Restoration
from ldm.dream.pngwriter import PngWriter, retrieve_metadata
from ldm.dream.args import APP_ID, APP_VERSION, calculate_init_img_hash
from ldm.dream.conditioning import split_weighted_subprompts
from ldm.invoke.restoration import Restoration
from ldm.invoke.pngwriter import PngWriter, retrieve_metadata
from ldm.invoke.args import APP_ID, APP_VERSION, calculate_init_img_hash
from ldm.invoke.conditioning import split_weighted_subprompts
from modules.parameters import parameters_to_command
@ -125,7 +125,7 @@ class CanceledException(Exception):
try:
gfpgan, codeformer, esrgan = None, None, None
from ldm.dream.restoration.base import Restoration
from ldm.invoke.restoration.base import Restoration
restoration = Restoration()
gfpgan, codeformer = restoration.load_face_restore_models()
@ -164,7 +164,7 @@ init_image_path = os.path.join(result_path, "init-images/")
mask_image_path = os.path.join(result_path, "mask-images/")
# txt log
log_path = os.path.join(result_path, "dream_log.txt")
log_path = os.path.join(result_path, "invoke_log.txt")
# make all output paths
[

18
docs/CHANGELOG.md
View File

@ -5,9 +5,9 @@
- Supports a Google Colab notebook for a standalone server running on Google hardware [Arturo Mendivil](https://github.com/artmen1516)
- 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)
- Output directory can be specified on the dream> command line.
- Output directory can be specified on the invoke> command line.
- The grid was displaying duplicated images when not enough images to fill the final row [Muhammad Usama](https://github.com/SMUsamaShah)
- Can specify --grid on dream.py command line as the default.
- Can specify --grid on invoke.py command line as the default.
- Miscellaneous internal bug and stability fixes.
---
@ -16,13 +16,13 @@
- Improved file handling, including ability to read prompts from standard input.
(kudos to [Yunsaki](https://github.com/yunsaki)
- The web server is now integrated with the dream.py script. Invoke by adding --web to
the dream.py command arguments.
- The web server is now integrated with the invoke.py script. Invoke by adding --web to
the invoke.py command arguments.
- Face restoration and upscaling via GFPGAN and Real-ESGAN are now automatically
enabled if the GFPGAN directory is located as a sibling to Stable Diffusion.
VRAM requirements are modestly reduced. Thanks to both [Blessedcoolant](https://github.com/blessedcoolant) and
[Oceanswave](https://github.com/oceanswave) for their work on this.
- You can now swap samplers on the dream> command line. [Blessedcoolant](https://github.com/blessedcoolant)
- You can now swap samplers on the invoke> command line. [Blessedcoolant](https://github.com/blessedcoolant)
---
@ -32,7 +32,7 @@
- You now can specify a seed of -1 to use the previous image's seed, -2 to use the seed for the image generated before that, etc.
Seed memory only extends back to the previous command, but will work on all images generated with the -n# switch.
- Variant generation support temporarily disabled pending more general solution.
- Created a feature branch named **yunsaki-morphing-dream** which adds experimental support for
- Created a feature branch named **yunsaki-morphing-invoke** which adds experimental support for
iteratively modifying the prompt and its parameters. Please see[ Pull Request #86](https://github.com/lstein/stable-diffusion/pull/86)
for a synopsis of how this works. Note that when this feature is eventually added to the main branch, it will may be modified
significantly.
@ -57,7 +57,7 @@
## v1.08 (24 August 2022)
- Escape single quotes on the dream> command before trying to parse. This avoids
- Escape single quotes on the invoke> command before trying to parse. This avoids
parse errors.
- Removed instruction to get Python3.8 as first step in Windows install.
Anaconda3 does it for you.
@ -94,7 +94,7 @@
be regenerated with the indicated key
- It should no longer be possible for one image to overwrite another
- You can use the "cd" and "pwd" commands at the dream> prompt to set and retrieve
- You can use the "cd" and "pwd" commands at the invoke> prompt to set and retrieve
the path of the output directory.
---
@ -128,7 +128,7 @@
- added k_lms sampling.
**Please run "conda env update" to load the k_lms dependencies!!**
- use half precision arithmetic by default, resulting in faster execution and lower memory requirements
Pass argument --full_precision to dream.py to get slower but more accurate image generation
Pass argument --full_precision to invoke.py to get slower but more accurate image generation
---

BIN
docs/assets/Lincoln-and-Parrot-512-transparent.png Executable file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 284 KiB

BIN
docs/assets/Lincoln-and-Parrot-512.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 252 KiB

BIN
docs/assets/invoke-web-server-1.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 983 KiB

BIN
docs/assets/invoke-web-server-2.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 101 KiB

BIN
docs/assets/invoke-web-server-3.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 546 KiB

BIN
docs/assets/invoke-web-server-4.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 336 KiB

BIN
docs/assets/invoke-web-server-5.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 29 KiB

BIN
docs/assets/invoke-web-server-6.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 148 KiB

BIN
docs/assets/invoke-web-server-7.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 637 KiB

BIN
docs/assets/invoke-web-server-8.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 529 KiB

BIN
docs/assets/invoke_web_server.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 989 KiB

BIN
docs/assets/prompt-blending/blue-sphere-0.25-red-cube-0.75-hybrid.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 501 KiB

BIN
docs/assets/prompt-blending/blue-sphere-0.5-red-cube-0.5-hybrid.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 473 KiB

BIN
docs/assets/prompt-blending/blue-sphere-0.5-red-cube-0.5.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 618 KiB

BIN
docs/assets/prompt-blending/blue-sphere-0.75-red-cube-0.25-hybrid.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 557 KiB

BIN
docs/assets/prompt-blending/blue-sphere-red-cube-hybrid.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 340 KiB

20
docs/features/CHANGELOG.md
View File

@ -4,7 +4,7 @@ title: Changelog
# :octicons-log-16: Changelog
## v1.13 <small>(in process)</small>
## v1.13
- Supports a Google Colab notebook for a standalone server running on Google
hardware [Arturo Mendivil](https://github.com/artmen1516)
@ -12,10 +12,10 @@ title: Changelog
[Kevin Gibbons](https://github.com/bakkot)
- WebUI supports incremental display of in-progress images during generation
[Kevin Gibbons](https://github.com/bakkot)
- Output directory can be specified on the dream> command line.
- Output directory can be specified on the invoke> command line.
- The grid was displaying duplicated images when not enough images to fill the
final row [Muhammad Usama](https://github.com/SMUsamaShah)
- Can specify --grid on dream.py command line as the default.
- Can specify --grid on invoke.py command line as the default.
- Miscellaneous internal bug and stability fixes.
---
@ -24,14 +24,14 @@ title: Changelog
- Improved file handling, including ability to read prompts from standard input.
(kudos to [Yunsaki](https://github.com/yunsaki)
- The web server is now integrated with the dream.py script. Invoke by adding
--web to the dream.py command arguments.
- The web server is now integrated with the invoke.py script. Invoke by adding
--web to the invoke.py command arguments.
- Face restoration and upscaling via GFPGAN and Real-ESGAN are now automatically
enabled if the GFPGAN directory is located as a sibling to Stable Diffusion.
VRAM requirements are modestly reduced. Thanks to both
[Blessedcoolant](https://github.com/blessedcoolant) and
[Oceanswave](https://github.com/oceanswave) for their work on this.
- You can now swap samplers on the dream> command line.
- You can now swap samplers on the invoke> command line.
[Blessedcoolant](https://github.com/blessedcoolant)
---
@ -45,7 +45,7 @@ title: Changelog
back to the previous command, but will work on all images generated with the
-n# switch.
- Variant generation support temporarily disabled pending more general solution.
- Created a feature branch named **yunsaki-morphing-dream** which adds
- Created a feature branch named **yunsaki-morphing-invoke** which adds
experimental support for iteratively modifying the prompt and its parameters.
Please
see[ Pull Request #86](https://github.com/lstein/stable-diffusion/pull/86) for
@ -75,7 +75,7 @@ title: Changelog
## v1.08 <small>(24 August 2022)</small>
- Escape single quotes on the dream> command before trying to parse. This avoids
- Escape single quotes on the invoke> command before trying to parse. This avoids
parse errors.
- Removed instruction to get Python3.8 as first step in Windows install.
Anaconda3 does it for you.
@ -112,7 +112,7 @@ title: Changelog
can be regenerated with the indicated key
- It should no longer be possible for one image to overwrite another
- You can use the "cd" and "pwd" commands at the dream> prompt to set and
- You can use the "cd" and "pwd" commands at the invoke> prompt to set and
retrieve the path of the output directory.
## v1.04 <small>(22 August 2022 - after the drop)</small>
@ -139,5 +139,5 @@ title: Changelog
- added k_lms sampling. **Please run "conda env update -f environment.yaml" to
load the k_lms dependencies!!**
- use half precision arithmetic by default, resulting in faster execution and
lower memory requirements Pass argument --full_precision to dream.py to get
lower memory requirements Pass argument --full_precision to invoke.py to get
slower but more accurate image generation

64
docs/features/CLI.md
View File

@ -8,8 +8,8 @@ hide:
## **Interactive Command Line Interface**
The `dream.py` script, located in `scripts/dream.py`, provides an interactive
interface to image generation similar to the "dream mothership" bot that Stable
The `invoke.py` script, located in `scripts/dream.py`, provides an interactive
interface to image generation similar to the "invoke mothership" bot that Stable
AI provided on its Discord server.
Unlike the `txt2img.py` and `img2img.py` scripts provided in the original
@ -34,21 +34,21 @@ The script is confirmed to work on Linux, Windows and Mac systems.
currently rudimentary, but a much better replacement is on its way.
```bash
(ldm) ~/stable-diffusion$ python3 ./scripts/dream.py
(ldm) ~/stable-diffusion$ python3 ./scripts/invoke.py
* Initializing, be patient...
Loading model from models/ldm/text2img-large/model.ckpt
(...more initialization messages...)
* Initialization done! Awaiting your command...
dream> ashley judd riding a camel -n2 -s150
invoke> ashley judd riding a camel -n2 -s150
Outputs:
outputs/img-samples/00009.png: "ashley judd riding a camel" -n2 -s150 -S 416354203
outputs/img-samples/00010.png: "ashley judd riding a camel" -n2 -s150 -S 1362479620
dream> "there's a fly in my soup" -n6 -g
invoke> "there's a fly in my soup" -n6 -g
outputs/img-samples/00011.png: "there's a fly in my soup" -n6 -g -S 2685670268
seeds for individual rows: [2685670268, 1216708065, 2335773498, 822223658, 714542046, 3395302430]
dream> q
invoke> q
# this shows how to retrieve the prompt stored in the saved image's metadata
(ldm) ~/stable-diffusion$ python ./scripts/images2prompt.py outputs/img_samples/*.png
@ -57,10 +57,10 @@ dream> q
00011.png: "there's a fly in my soup" -n6 -g -S 2685670268
```
![dream-py-demo](../assets/dream-py-demo.png)
![invoke-py-demo](../assets/dream-py-demo.png)
The `dream>` prompt's arguments are pretty much identical to those used in the
Discord bot, except you don't need to type "!dream" (it doesn't hurt if you do).
The `invoke>` prompt's arguments are pretty much identical to those used in the
Discord bot, except you don't need to type "!invoke" (it doesn't hurt if you do).
A significant change is that creation of individual images is now the default
unless `--grid` (`-g`) is given. A full list is given in
[List of prompt arguments](#list-of-prompt-arguments).
@ -73,7 +73,7 @@ the location of the model weight files.
### List of arguments recognized at the command line
These command-line arguments can be passed to `dream.py` when you first run it
These command-line arguments can be passed to `invoke.py` when you first run it
from the Windows, Mac or Linux command line. Some set defaults that can be
overridden on a per-prompt basis (see [List of prompt arguments]
(#list-of-prompt-arguments). Others
@ -112,15 +112,15 @@ These arguments are deprecated but still work:
| --laion400m | -l | False | Use older LAION400m weights; use `--model=laion400m` instead |
**A note on path names:** On Windows systems, you may run into
problems when passing the dream script standard backslashed path
problems when passing the invoke script standard backslashed path
names because the Python interpreter treats "\" as an escape.
You can either double your slashes (ick): C:\\\\path\\\\to\\\\my\\\\file, or
use Linux/Mac style forward slashes (better): C:/path/to/my/file.
## List of prompt arguments
After the dream.py script initializes, it will present you with a
**dream>** prompt. Here you can enter information to generate images
After the invoke.py script initializes, it will present you with a
**invoke>** prompt. Here you can enter information to generate images
from text (txt2img), to embellish an existing image or sketch
(img2img), or to selectively alter chosen regions of the image
(inpainting).
@ -128,13 +128,13 @@ from text (txt2img), to embellish an existing image or sketch
### This is an example of txt2img:
~~~~
dream> waterfall and rainbow -W640 -H480
invoke> waterfall and rainbow -W640 -H480
~~~~
This will create the requested image with the dimensions 640 (width)
and 480 (height).
Here are the dream> command that apply to txt2img:
Here are the invoke> command that apply to txt2img:
| Argument | Shortcut | Default | Description |
|--------------------|------------|---------------------|--------------|
@ -167,7 +167,7 @@ the nearest multiple of 64.
### This is an example of img2img:
~~~~
dream> waterfall and rainbow -I./vacation-photo.png -W640 -H480 --fit
invoke> waterfall and rainbow -I./vacation-photo.png -W640 -H480 --fit
~~~~
This will modify the indicated vacation photograph by making it more
@ -188,7 +188,7 @@ accepts additional options:
### This is an example of inpainting:
~~~~
dream> waterfall and rainbow -I./vacation-photo.png -M./vacation-mask.png -W640 -H480 --fit
invoke> waterfall and rainbow -I./vacation-photo.png -M./vacation-mask.png -W640 -H480 --fit
~~~~
This will do the same thing as img2img, but image alterations will
@ -224,20 +224,20 @@ Some examples:
Upscale to 4X its original size and fix faces using codeformer:
~~~
dream> !fix 0000045.4829112.png -G1 -U4 -ft codeformer
invoke> !fix 0000045.4829112.png -G1 -U4 -ft codeformer
~~~
Use the GFPGAN algorithm to fix faces, then upscale to 3X using --embiggen:
~~~
dream> !fix 0000045.4829112.png -G0.8 -ft gfpgan
invoke> !fix 0000045.4829112.png -G0.8 -ft gfpgan
>> fixing outputs/img-samples/0000045.4829112.png
>> retrieved seed 4829112 and prompt "boy enjoying a banana split"
>> GFPGAN - Restoring Faces for image seed:4829112
Outputs:
[1] outputs/img-samples/000017.4829112.gfpgan-00.png: !fix "outputs/img-samples/0000045.4829112.png" -s 50 -S -W 512 -H 512 -C 7.5 -A k_lms -G 0.8
dream> !fix 000017.4829112.gfpgan-00.png --embiggen 3
invoke> !fix 000017.4829112.gfpgan-00.png --embiggen 3
...lots of text...
Outputs:
[2] outputs/img-samples/000018.2273800735.embiggen-00.png: !fix "outputs/img-samples/000017.243781548.gfpgan-00.png" -s 50 -S 2273800735 -W 512 -H 512 -C 7.5 -A k_lms --embiggen 3.0 0.75 0.25
@ -251,9 +251,9 @@ provide either the name of a file in the current output directory, or
a full file path.
~~~
dream> !fetch 0000015.8929913.png
invoke> !fetch 0000015.8929913.png
# the script returns the next line, ready for editing and running:
dream> a fantastic alien landscape -W 576 -H 512 -s 60 -A plms -C 7.5
invoke> a fantastic alien landscape -W 576 -H 512 -s 60 -A plms -C 7.5
~~~
Note that this command may behave unexpectedly if given a PNG file that
@ -261,7 +261,7 @@ was not generated by InvokeAI.
## !history
The dream script keeps track of all the commands you issue during a
The invoke script keeps track of all the commands you issue during a
session, allowing you to re-run them. On Mac and Linux systems, it
also writes the command-line history out to disk, giving you access to
the most recent 1000 commands issued.
@ -272,7 +272,7 @@ issued during the session (Windows), or the most recent 1000 commands
where "NNN" is the history line number. For example:
~~~
dream> !history
invoke> !history
...
[14] happy woman sitting under tree wearing broad hat and flowing garment
[15] beautiful woman sitting under tree wearing broad hat and flowing garment
@ -280,8 +280,8 @@ dream> !history
[20] watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
[21] surrealist painting of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
...
dream> !20
dream> watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
invoke> !20
invoke> watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
~~~
## !search <search string>
@ -290,7 +290,7 @@ This is similar to !history but it only returns lines that contain
`search string`. For example:
~~~
dream> !search surreal
invoke> !search surreal
[21] surrealist painting of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
~~~
@ -312,16 +312,16 @@ command completion.
- To paste a cut section back in, position the cursor where you want to paste, and type CTRL-Y
Windows users can get similar, but more limited, functionality if they
launch dream.py with the "winpty" program and have the `pyreadline3`
launch invoke.py with the "winpty" program and have the `pyreadline3`
library installed:
~~~
> winpty python scripts\dream.py
> winpty python scripts\invoke.py
~~~
On the Mac and Linux platforms, when you exit dream.py, the last 1000
On the Mac and Linux platforms, when you exit invoke.py, the last 1000
lines of your command-line history will be saved. When you restart
dream.py, you can access the saved history using the up-arrow key.
invoke.py, you can access the saved history using the up-arrow key.
In addition, limited command-line completion is installed. In various
contexts, you can start typing your command and press tab. A list of
@ -334,7 +334,7 @@ will attempt to complete pathnames for you. This is most handy for the
the path with a slash ("/") or "./". For example:
~~~
dream> zebra with a mustache -I./test-pictures<TAB>
invoke> zebra with a mustache -I./test-pictures<TAB>
-I./test-pictures/Lincoln-and-Parrot.png -I./test-pictures/zebra.jpg -I./test-pictures/madonna.png
-I./test-pictures/bad-sketch.png -I./test-pictures/man_with_eagle/
```

8
docs/features/EMBIGGEN.md
View File

@ -106,8 +106,8 @@ Running Embiggen with 512x512 tiles on an existing image, scaling up by a factor
and doing the same again (default ESRGAN strength is 0.75, default overlap between tiles is 0.25):
```bash
dream > a photo of a forest at sunset -s 100 -W 512 -H 512 -I outputs/forest.png -f 0.4 -embiggen 2.5
dream > a photo of a forest at sunset -s 100 -W 512 -H 512 -I outputs/forest.png -f 0.4 -embiggen 2.5 0.75 0.25
invoke > a photo of a forest at sunset -s 100 -W 512 -H 512 -I outputs/forest.png -f 0.4 -embiggen 2.5
invoke > a photo of a forest at sunset -s 100 -W 512 -H 512 -I outputs/forest.png -f 0.4 -embiggen 2.5 0.75 0.25
```
If your starting image was also 512x512 this should have taken 9 tiles.
@ -118,7 +118,7 @@ If there weren't enough clouds in the sky of that forest you just made
tiles:
```bash
dream> a photo of puffy clouds over a forest at sunset -s 100 -W 512 -H 512 -I outputs/000002.seed.png -f 0.5 -embiggen_tiles 1 2 3
invoke> a photo of puffy clouds over a forest at sunset -s 100 -W 512 -H 512 -I outputs/000002.seed.png -f 0.5 -embiggen_tiles 1 2 3
```
## Fixing Previously-Generated Images
@ -129,7 +129,7 @@ syntax `!fix path/to/file.png <embiggen>`. For example, you can rewrite the
previous command to look like this:
~~~~
dream> !fix ./outputs/000002.seed.png -embiggen_tiles 1 2 3
invoke> !fix ./outputs/000002.seed.png -embiggen_tiles 1 2 3
~~~~
A new file named `000002.seed.fixed.png` will be created in the output directory. Note that

59
docs/features/IMG2IMG.md
View File

@ -10,18 +10,39 @@ top of the image you provide, preserving the original's basic shape and layout.
the `--init_img` option as shown here:
```commandline
dream> "waterfall and rainbow" --init_img=./init-images/crude_drawing.png --strength=0.5 -s100 -n4
tree on a hill with a river, nature photograph, national geographic -I./test-pictures/tree-and-river-sketch.png -f 0.85
```
This will take the original image shown here:
<img src="https://user-images.githubusercontent.com/50542132/193946000-c42a96d8-5a74-4f8a-b4c3-5213e6cadcce.png" width=350>
and generate a new image based on it as shown here:
<img src="https://user-images.githubusercontent.com/111189/194135515-53d4c060-e994-4016-8121-7c685e281ac9.png" width=350>
The `--init_img (-I)` option gives the path to the seed picture. `--strength (-f)` controls how much
the original will be modified, ranging from `0.0` (keep the original intact), to `1.0` (ignore the
original completely). The default is `0.75`, and ranges from `0.25-0.75` give interesting results.
original completely). The default is `0.75`, and ranges from `0.25-0.90` give interesting results.
Other relevant options include `-C` (classification free guidance scale), and `-s` (steps). Unlike `txt2img`,
adding steps will continuously change the resulting image and it will not converge.
You may also pass a `-v<variation_amount>` option to generate `-n<iterations>` count variants on
the original image. This is done by passing the first generated image
back into img2img the requested number of times. It generates
interesting variants.
Note that the prompt makes a big difference. For example, this slight variation on the prompt produces
a very different image:
`photograph of a tree on a hill with a river`
<img src="https://user-images.githubusercontent.com/111189/194135220-16b62181-b60c-4248-8989-4834a8fd7fbd.png" width=350>
(When designing prompts, think about how the images scraped from the internet were captioned. Very few photographs will
be labeled "photograph" or "photorealistic." They will, however, be captioned with the publication, photographer, camera
model, or film settings.)
If the initial image contains transparent regions, then Stable Diffusion will only draw within the
transparent regions, a process called "inpainting". However, for this to work correctly, the color
information underneath the transparent needs to be preserved, not erased.
@ -29,6 +50,17 @@ information underneath the transparent needs to be preserved, not erased.
More details can be found here:
[Creating Transparent Images For Inpainting](./INPAINTING.md#creating-transparent-regions-for-inpainting)
<<<<<<< HEAD
=======
**IMPORTANT ISSUE** `img2img` does not work properly on initial images smaller than 512x512. Please scale your
image to at least 512x512 before using it. Larger images are not a problem, but may run out of VRAM on your
GPU card. To fix this, use the --fit option, which downscales the initial image to fit within the box specified
by width x height:
~~~
tree on a hill with a river, national geographic -I./test-pictures/big-sketch.png -H512 -W512 --fit
~~~
>>>>>>> main
## How does it actually work, though?
The main difference between `img2img` and `prompt2img` is the starting point. While `prompt2img` always starts with pure
@ -38,7 +70,11 @@ gaussian noise and progressively refines it over the requested number of steps,
**Let's start** by thinking about vanilla `prompt2img`, just generating an image from a prompt. If the step count is 10, then the "latent space" (Stable Diffusion's internal representation of the image) for the prompt "fire" with seed `1592514025` develops something like this:
```commandline
<<<<<<< HEAD
dream> "fire" -s10 -W384 -H384 -S1592514025
=======
invoke> "fire" -s10 -W384 -H384 -S1592514025
>>>>>>> main
```
![latent steps](../assets/img2img/000019.steps.png)
@ -66,7 +102,11 @@ Notice how much more fuzzy the starting image is for strength `0.7` compared to
| | strength = 0.7 | strength = 0.4 |
| -- | -- | -- |
| initial image that SD sees | ![](../assets/img2img/000032.step-0.png) | ![](../assets/img2img/000030.step-0.png) |
<<<<<<< HEAD
| steps argument to `dream>` | `-S10` | `-S10` |
=======
| steps argument to `invoke>` | `-S10` | `-S10` |
>>>>>>> main
| steps actually taken | 7 | 4 |
| latent space at each step | ![](../assets/img2img/000032.steps.gravity.png) | ![](../assets/img2img/000030.steps.gravity.png) |
| output | ![](../assets/img2img/000032.1592514025.png) | ![](../assets/img2img/000030.1592514025.png) |
@ -77,10 +117,17 @@ Both of the outputs look kind of like what I was thinking of. With the strength
If you want to try this out yourself, all of these are using a seed of `1592514025` with a width/height of `384`, step count `10`, the default sampler (`k_lms`), and the single-word prompt `fire`:
```commandline
<<<<<<< HEAD
dream> "fire" -s10 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png --strength 0.7
```
The code for rendering intermediates is on my (damian0815's) branch [document-img2img](https://github.com/damian0815/InvokeAI/tree/document-img2img) - run `dream.py` and check your `outputs/img-samples/intermediates` folder while generating an image.
=======
invoke> "fire" -s10 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png --strength 0.7
```
The code for rendering intermediates is on my (damian0815's) branch [document-img2img](https://github.com/damian0815/InvokeAI/tree/document-img2img) - run `invoke.py` and check your `outputs/img-samples/intermediates` folder while generating an image.
>>>>>>> main
### Compensating for the reduced step count
@ -89,7 +136,11 @@ After putting this guide together I was curious to see how the difference would
Here's strength `0.4` (note step count `50`, which is `20 ÷ 0.4` to make sure SD does `20` steps from my image):
```commandline
<<<<<<< HEAD
dream> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
=======
invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
>>>>>>> main
```
![](../assets/img2img/000035.1592514025.png)
@ -97,7 +148,11 @@ dream> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
and strength `0.7` (note step count `30`, which is roughly `20 ÷ 0.7` to make sure SD does `20` steps from my image):
```commandline
<<<<<<< HEAD
dream> "fire" -s30 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.7
=======
invoke> "fire" -s30 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.7
>>>>>>> main
```
![](../assets/img2img/000046.1592514025.png)

12
docs/features/INPAINTING.md
View File

@ -8,7 +8,7 @@ title: Inpainting
Inpainting is really cool. To do it, you start with an initial image and use a photoeditor to make
one or more regions transparent (i.e. they have a "hole" in them). You then provide the path to this
image at the dream> command line using the `-I` switch. Stable Diffusion will only paint within the
image at the invoke> command line using the `-I` switch. Stable Diffusion will only paint within the
transparent region.
There's a catch. In the current implementation, you have to prepare the initial image correctly so
@ -17,13 +17,13 @@ applications will by default erase the color information under the transparent p
them with white or black, which will lead to suboptimal inpainting. You also must take care to
export the PNG file in such a way that the color information is preserved.
If your photoeditor is erasing the underlying color information, `dream.py` will give you a big fat
If your photoeditor is erasing the underlying color information, `invoke.py` will give you a big fat
warning. If you can't find a way to coax your photoeditor to retain color values under transparent
areas, then you can combine the `-I` and `-M` switches to provide both the original unedited image
and the masked (partially transparent) image:
```bash
dream> "man with cat on shoulder" -I./images/man.png -M./images/man-transparent.png
invoke> "man with cat on shoulder" -I./images/man.png -M./images/man-transparent.png
```
We are hoping to get rid of the need for this workaround in an upcoming release.
@ -38,8 +38,8 @@ We are hoping to get rid of the need for this workaround in an upcoming release.
2. Layer->Transparency->Add Alpha Channel
3. Use lasoo tool to select region to mask
4. Choose Select -> Float to create a floating selection
5. Open the Layers toolbar (++ctrl+l++) and select "Floating Selection"
6. Set opacity to 0%
5. Open the Layers toolbar (^L) and select "Floating Selection"
6. Set opacity to a value between 0% and 99%
7. Export as PNG
8. In the export dialogue, Make sure the "Save colour values from
transparent pixels" checkbox is selected.
@ -69,7 +69,7 @@ We are hoping to get rid of the need for this workaround in an upcoming release.
![step6](../assets/step6.png)
7. After following the inpainting instructions above (either through the CLI or the Web UI), marvel at your newfound ability to selectively dream. Lookin' good!
7. After following the inpainting instructions above (either through the CLI or the Web UI), marvel at your newfound ability to selectively invoke. Lookin' good!
![step7](../assets/step7.png)

8
docs/features/OTHER.md
View File

@ -22,10 +22,10 @@ Output Example: ![Colab Notebook](../assets/colab_notebook.png)
The seamless tiling mode causes generated images to seamlessly tile with itself. To use it, add the
`--seamless` option when starting the script which will result in all generated images to tile, or
for each `dream>` prompt as shown here:
for each `invoke>` prompt as shown here:
```python
dream> "pond garden with lotus by claude monet" --seamless -s100 -n4
invoke> "pond garden with lotus by claude monet" --seamless -s100 -n4
```
---
@ -42,12 +42,12 @@ Here's an example of using this to do a quick refinement. It also illustrates us
switch to turn on upscaling and face enhancement (see previous section):
```bash
dream> a cute child playing hopscotch -G0.5
invoke> a cute child playing hopscotch -G0.5
[...]
outputs/img-samples/000039.3498014304.png: "a cute child playing hopscotch" -s50 -W512 -H512 -C7.5 -mk_lms -S3498014304
# I wonder what it will look like if I bump up the steps and set facial enhancement to full strength?
dream> a cute child playing hopscotch -G1.0 -s100 -S -1
invoke> a cute child playing hopscotch -G1.0 -s100 -S -1
reusing previous seed 3498014304
[...]
outputs/img-samples/000040.3498014304.png: "a cute child playing hopscotch" -G1.0 -s100 -W512 -H512 -C7.5 -mk_lms -S3498014304

4
docs/features/OUTPAINTING.md
View File

@ -31,7 +31,7 @@ Pretty nice, but it's annoying that the top of her head is cut
off. She's also a bit off center. Let's fix that!
~~~~
dream> !fix images/curly.png --outcrop top 64 right 64
invoke> !fix images/curly.png --outcrop top 64 right 64
~~~~
This is saying to apply the `outcrop` extension by extending the top
@ -67,7 +67,7 @@ differences. Starting with the same image, here is how we would add an
additional 64 pixels to the top of the image:
~~~
dream> !fix images/curly.png --out_direction top 64
invoke> !fix images/curly.png --out_direction top 64
~~~
(you can abbreviate ``--out_direction` as `-D`.

74
docs/features/POSTPROCESS.md
View File

@ -20,39 +20,33 @@ The default face restoration module is GFPGAN. The default upscale is
Real-ESRGAN. For an alternative face restoration module, see [CodeFormer
Support] below.
As of version 1.14, environment.yaml will install the Real-ESRGAN package into
the standard install location for python packages, and will put GFPGAN into a
subdirectory of "src" in the InvokeAI directory. (The reason for this is
that the standard GFPGAN distribution has a minor bug that adversely affects
image color.) Upscaling with Real-ESRGAN should "just work" without further
intervention. Simply pass the --upscale (-U) option on the dream> command line,
or indicate the desired scale on the popup in the Web GUI.
As of version 1.14, environment.yaml will install the Real-ESRGAN
package into the standard install location for python packages, and
will put GFPGAN into a subdirectory of "src" in the InvokeAI
directory. Upscaling with Real-ESRGAN should "just work" without
further intervention. Simply pass the --upscale (-U) option on the
invoke> command line, or indicate the desired scale on the popup in
the Web GUI.
For **GFPGAN** to work, there is one additional step needed. You will need to
download and copy the GFPGAN
[models file](https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth)
into **src/gfpgan/experiments/pretrained_models**. On Mac and Linux systems,
here's how you'd do it using **wget**:
**GFPGAN** requires a series of downloadable model files to
work. These are loaded when you run `scripts/preload_models.py`. If
GFPAN is failing with an error, please run the following from the
InvokeAI directory:
```bash
wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth -P src/gfpgan/experiments/pretrained_models/
```
~~~~
python scripts/preload_models.py
~~~~
Make sure that you're in the InvokeAI directory when you do this.
If you do not run this script in advance, the GFPGAN module will attempt
to download the models files the first time you try to perform facial
reconstruction.
Alternatively, if you have GFPGAN installed elsewhere, or if you are using an
earlier version of this package which asked you to install GFPGAN in a sibling
directory, you may use the `--gfpgan_dir` argument with `dream.py` to set a
custom path to your GFPGAN directory. _There are other GFPGAN related boot
arguments if you wish to customize further._
!!! warning "Internet connection needed"
Users whose GPU machines are isolated from the Internet (e.g.
on a University cluster) should be aware that the first time you run dream.py with GFPGAN and
Real-ESRGAN turned on, it will try to download model files from the Internet. To rectify this, you
may run `python3 scripts/preload_models.py` after you have installed GFPGAN and all its
dependencies.
Alternatively, if you have GFPGAN installed elsewhere, or if you are
using an earlier version of this package which asked you to install
GFPGAN in a sibling directory, you may use the `--gfpgan_dir` argument
with `invoke.py` to set a custom path to your GFPGAN directory. _There
are other GFPGAN related boot arguments if you wish to customize
further._
## Usage
@ -94,13 +88,13 @@ too.
### Example Usage
```bash
dream> superman dancing with a panda bear -U 2 0.6 -G 0.4
invoke> superman dancing with a panda bear -U 2 0.6 -G 0.4
```
This also works with img2img:
```bash
dream> a man wearing a pineapple hat -I path/to/your/file.png -U 2 0.5 -G 0.6
invoke> a man wearing a pineapple hat -I path/to/your/file.png -U 2 0.5 -G 0.6
```
!!! note
@ -124,15 +118,15 @@ actions.
This repo also allows you to perform face restoration using
[CodeFormer](https://github.com/sczhou/CodeFormer).
In order to setup CodeFormer to work, you need to download the models like with
GFPGAN. You can do this either by running `preload_models.py` or by manually
downloading the
[model file](https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth)
In order to setup CodeFormer to work, you need to download the models
like with GFPGAN. You can do this either by running
`preload_models.py` or by manually downloading the [model
file](https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth)
and saving it to `ldm/restoration/codeformer/weights` folder.
You can use `-ft` prompt argument to swap between CodeFormer and the default
GFPGAN. The above mentioned `-G` prompt argument will allow you to control the
strength of the restoration effect.
You can use `-ft` prompt argument to swap between CodeFormer and the
default GFPGAN. The above mentioned `-G` prompt argument will allow
you to control the strength of the restoration effect.
### Usage:
@ -168,7 +162,7 @@ previously-generated file. Just use the syntax `!fix path/to/file.png
just run:
```
dream> !fix ./outputs/img-samples/000044.2945021133.png -G 0.8 -U 2
invoke> !fix ./outputs/img-samples/000044.2945021133.png -G 0.8 -U 2
```
A new file named `000044.2945021133.fixed.png` will be created in the output
@ -178,5 +172,5 @@ unlike the behavior at generate time.
### Disabling:
If, for some reason, you do not wish to load the GFPGAN and/or ESRGAN libraries,
you can disable them on the dream.py command line with the `--no_restore` and
you can disable them on the invoke.py command line with the `--no_restore` and
`--no_upscale` options, respectively.

105
docs/features/PROMPTS.md
View File

@ -6,9 +6,9 @@ title: Prompting Features
## **Reading Prompts from a File**
You can automate `dream.py` by providing a text file with the prompts you want to run, one line per
You can automate `invoke.py` by providing a text file with the prompts you want to run, one line per
prompt. The text file must be composed with a text editor (e.g. Notepad) and not a word processor.
Each line should look like what you would type at the dream> prompt:
Each line should look like what you would type at the invoke> prompt:
```bash
a beautiful sunny day in the park, children playing -n4 -C10
@ -16,39 +16,23 @@ stormy weather on a mountain top, goats grazing -s100
innovative packaging for a squid's dinner -S137038382
```
Then pass this file's name to `dream.py` when you invoke it:
Then pass this file's name to `invoke.py` when you invoke it:
```bash
(ldm) ~/stable-diffusion$ python3 scripts/dream.py --from_file "path/to/prompts.txt"
(ldm) ~/stable-diffusion$ python3 scripts/invoke.py --from_file "path/to/prompts.txt"
```
You may read a series of prompts from standard input by providing a filename of `-`:
```bash
(ldm) ~/stable-diffusion$ echo "a beautiful day" | python3 scripts/dream.py --from_file -
(ldm) ~/stable-diffusion$ echo "a beautiful day" | python3 scripts/invoke.py --from_file -
```
---
## **Weighted Prompts**
You may weight different sections of the prompt to tell the sampler to attach different levels of
priority to them, by adding `:(number)` to the end of the section you wish to up- or downweight. For
example consider this prompt:
```bash
tabby cat:0.25 white duck:0.75 hybrid
```
This will tell the sampler to invest 25% of its effort on the tabby cat aspect of the image and 75%
on the white duck aspect (surprisingly, this example actually works). The prompt weights can use any
combination of integers and floating point numbers, and they do not need to add up to 1.
---
## **Negative and Unconditioned Prompts**
Any words between a pair of square brackets will try and be ignored by Stable Diffusion's model during generation of images.
Any words between a pair of square brackets will instruct Stable
Diffusion to attempt to ban the concept from the generated image.
```bash
this is a test prompt [not really] to make you understand [cool] how this works.
@ -88,3 +72,78 @@ Getting close - but there's no sense in having a saddle when our horse doesn't h
* You can provide multiple words within the same bracket.
* You can provide multiple brackets with multiple words in different places of your prompt. That works just fine.
* To improve typical anatomy problems, you can add negative prompts like `[bad anatomy, extra legs, extra arms, extra fingers, poorly drawn hands, poorly drawn feet, disfigured, out of frame, tiling, bad art, deformed, mutated]`.
---
## **Prompt Blending**
You may blend together different sections of the prompt to explore the
AI's latent semantic space and generate interesting (and often
surprising!) variations. The syntax is:
```bash
blue sphere:0.25 red cube:0.75 hybrid
```
This will tell the sampler to blend 25% of the concept of a blue
sphere with 75% of the concept of a red cube. The blend weights can
use any combination of integers and floating point numbers, and they
do not need to add up to 1. Everything to the left of the `:XX` up to
the previous `:XX` is used for merging, so the overall effect is:
```bash
0.25 * "blue sphere" + 0.75 * "white duck" + hybrid
```
Because you are exploring the "mind" of the AI, the AI's way of mixing
two concepts may not match yours, leading to surprising effects. To
illustrate, here are three images generated using various combinations
of blend weights. As usual, unless you fix the seed, the prompts will give you
different results each time you run them.
### "blue sphere, red cube, hybrid"
This example doesn't use melding at all and represents the default way
of mixing concepts.
<img src="../assets/prompt-blending/blue-sphere-red-cube-hybrid.png" width=256>
It's interesting to see how the AI expressed the concept of "cube" as
the four quadrants of the enclosing frame. If you look closely, there
is depth there, so the enclosing frame is actually a cube.
### "blue sphere:0.25 red cube:0.75 hybrid"
<img src="../assets/prompt-blending/blue-sphere-0.25-red-cube-0.75-hybrid.png" width=256>
Now that's interesting. We get neither a blue sphere nor a red cube,
but a red sphere embedded in a brick wall, which represents a melding
of concepts within the AI's "latent space" of semantic
representations. Where is Ludwig Wittgenstein when you need him?
### "blue sphere:0.75 red cube:0.25 hybrid"
<img src="../assets/prompt-blending/blue-sphere-0.75-red-cube-0.25-hybrid.png" width=256>
Definitely more blue-spherey. The cube is gone entirely, but it's
really cool abstract art.
### "blue sphere:0.5 red cube:0.5 hybrid"
<img src="../assets/prompt-blending/blue-sphere-0.5-red-cube-0.5-hybrid.png" width=256>
Whoa...! I see blue and red, but no spheres or cubes. Is the word
"hybrid" summoning up the concept of some sort of scifi creature?
Let's find out.
### "blue sphere:0.5 red cube:0.5"
<img src="../assets/prompt-blending/blue-sphere-0.5-red-cube-0.5.png" width=256>
Indeed, removing the word "hybrid" produces an image that is more like
what we'd expect.
In conclusion, prompt blending is great for exploring creative space,
but can be difficult to direct. A forthcoming release of InvokeAI will
feature more deterministic prompt weighting.

10
docs/features/TEXTUAL_INVERSION.md
View File

@ -56,22 +56,22 @@ configs/stable_diffusion/v1-finetune.yaml (currently set to 4000000)
## **Run the Model**
Once the model is trained, specify the trained .pt or .bin file when starting
dream using
invoke using
```bash
python3 ./scripts/dream.py --embedding_path /path/to/embedding.pt
python3 ./scripts/invoke.py --embedding_path /path/to/embedding.pt
```
Then, to utilize your subject at the dream prompt
Then, to utilize your subject at the invoke prompt
```bash
dream> "a photo of *"
invoke> "a photo of *"
```
This also works with image2image
```bash
dream> "waterfall and rainbow in the style of *" --init_img=./init-images/crude_drawing.png --strength=0.5 -s100 -n4
invoke> "waterfall and rainbow in the style of *" --init_img=./init-images/crude_drawing.png --strength=0.5 -s100 -n4
```
For .pt files it's also possible to train multiple tokens (modify the

8
docs/features/VARIATIONS.md
View File

@ -34,7 +34,7 @@ First we let SD create a series of images in the usual way, in this case
requesting six iterations:
```bash
dream> lucy lawless as xena, warrior princess, character portrait, high resolution -n6
invoke> lucy lawless as xena, warrior princess, character portrait, high resolution -n6
...
Outputs:
./outputs/Xena/000001.1579445059.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S1579445059
@ -57,7 +57,7 @@ differing by a variation amount of 0.2. This number ranges from `0` to `1.0`,
with higher numbers being larger amounts of variation.
```bash
dream> "prompt" -n6 -S3357757885 -v0.2
invoke> "prompt" -n6 -S3357757885 -v0.2
...
Outputs:
./outputs/Xena/000002.784039624.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 784039624:0.2 -S3357757885
@ -89,7 +89,7 @@ We combine the two variations using `-V` (`--with_variations`). Again, we must
provide the seed for the originally-chosen image in order for this to work.
```bash
dream> "prompt" -S3357757885 -V3647897225,0.1,1614299449,0.1
invoke> "prompt" -S3357757885 -V3647897225,0.1,1614299449,0.1
Outputs:
./outputs/Xena/000003.1614299449.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1 -S3357757885
```
@ -105,7 +105,7 @@ latter, using both the `-V` (combining) and `-v` (variation strength) options.
Note that we use `-n6` to generate 6 variations:
```bash
dream> "prompt" -S3357757885 -V3647897225,0.1,1614299449,0.1 -v0.05 -n6
invoke> "prompt" -S3357757885 -V3647897225,0.1,1614299449,0.1 -v0.05 -n6
Outputs:
./outputs/Xena/000004.3279757577.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,3279757577:0.05 -S3357757885
./outputs/Xena/000004.2853129515.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -V 3647897225:0.1,1614299449:0.1,2853129515:0.05 -S3357757885

291
docs/features/WEB.md
View File

@ -1,24 +1,290 @@
---
title: InvokeAI Web UI & Server
title: InvokeAI Web Server
---
# :material-web: InvokeAI Web Server
As of version 2.0, this distribution's web server has been updated to include
an all-new UI, with optimizations to improve common workflows for image generation.
## Getting Started & Initialization Commands
To start the web server, run the `dream.py` script by adding the `--web` parameter.
As of version 2.0.0, this distribution comes with a full-featured web
server (see screenshot). To use it, run the `invoke.py` script by
adding the `--web` option:
```bash
(ldm) ~/stable-diffusion$ python3 scripts/dream.py --web
(ldm) ~/InvokeAI$ python3 scripts/invoke.py --web
```
You can then connect to the server by pointing your web browser at
http://localhost:9090, or to the network name or IP address of the server.
http://localhost:9090. To reach the server from a different machine on
your LAN, you may launch the web server with the `--host` argument and
either the IP address of the host you are running it on, or the
wildcard `0.0.0.0`. For example:
### Additional Options
```bash
(ldm) ~/InvokeAI$ python3 scripts/invoke.py --web --host 0.0.0.0
```
# Quick guided walkthrough of the WebGUI's features
While most of the WebGUI's features are intuitive, here is a guided
walkthrough through its various components.
<img src="../assets/invoke-web-server-1.png" width=640>
The screenshot above shows the Text to Image tab of the WebGUI. There
are three main sections:
1. A **control panel** on the left, which contains various settings
for text to image generation. The most important part is the text
field (currently showing `strawberry sushi`) for entering the text
prompt, and the camera icon directly underneath that will render the
image. We'll call this the *Invoke* button from now on.
2. The **current image** section in the middle, which shows a large
format version of the image you are currently working on. A series of
buttons at the top ("image to image", "Use All", "Use Seed", etc) lets
you modify the image in various ways.
3. A **gallery* section on the left that contains a history of the
images you have generated. These images are read and written to the
directory specified at launch time in `--outdir`.
In addition to these three elements, there are a series of icons for
changing global settings, reporting bugs, and changing the theme on
the upper right.
There are also a series of icons to the left of the control panel (see
highlighted area in the screenshot below) which select among a series
of tabs for performing different types of operations.
<img src="../assets/invoke-web-server-2.png" width=512>
From top to bottom, these are:
1. Text to Image - generate images from text
2. Image to Image - from an uploaded starting image (drawing or photograph) generate a new one, modified by the text prompt
3. Inpainting (pending) - Interactively erase portions of a starting image and have the AI fill in the erased region from a text prompt.
4. Outpainting (pending) - Interactively add blank space to the borders of a starting image and fill in the background from a text prompt.
5. Postprocessing (pending) - Interactively postprocess generated images using a variety of filters.
The inpainting, outpainting and postprocessing tabs are currently in
development. However, limited versions of their features can already
be accessed through the Text to Image and Image to Image tabs.
## Walkthrough
The following walkthrough will exercise most (but not all) of the
WebGUI's feature set.
### Text to Image
1. Launch the WebGUI using `python scripts/invoke.py --web` and
connect to it with your browser by accessing
`http://localhost:9090`. If the browser and server are running on
different machines on your LAN, add the option `--host 0.0.0.0` to the
launch command line and connect to the machine hosting the web server
using its IP address or domain name.
2. If all goes well, the WebGUI should come up and you'll see a green
`connected` message on the upper right.
#### Basics
3. Generate an image by typing *strawberry sushi* into the large
prompt field on the upper left and then clicking on the Invoke button
(the one with the Camera icon). After a short wait, you'll see a large
image of sushi in the image panel, and a new thumbnail in the gallery
on the right.
If you need more room on the screen, you can turn the gallery off
by clicking on the **x** to the right of "Your Invocations". You can
turn it back on later by clicking the image icon that appears in the
gallery's place.
The images are written into the directory indicated by the `--outdir`
option provided at script launch time. By default, this is
`outputs/img-samples` under the InvokeAI directory.
4. Generate a bunch of strawberry sushi images by increasing the
number of requested images by adjusting the Images counter just below
the Camera button. As each is generated, it will be added to the
gallery. You can switch the active image by clicking on the gallery
thumbnails.
5. Try playing with different settings, including image width and
height, the Sampler, the Steps and the CFG scale.
Image *Width* and *Height* do what you'd expect. However, be aware that
larger images consume more VRAM memory and take longer to generate.
The *Sampler* controls how the AI selects the image to display. Some
samplers are more "creative" than others and will produce a wider
range of variations (see next section). Some samplers run faster than
others.
*Steps* controls how many noising/denoising/sampling steps the AI will
take. The higher this value, the more refined the image will be, but
the longer the image will take to generate. A typical strategy is to
generate images with a low number of steps in order to select one to
work on further, and then regenerate it using a higher number of
steps.
The *CFG Scale* controls how hard the AI tries to match the generated
image to the input prompt. You can go as high or low as you like, but
generally values greater than 20 won't improve things much, and values
lower than 5 will produce unexpected images. There are complex
interactions between *Steps*, *CFG Scale* and the *Sampler*, so
experiment to find out what works for you.
6. To regenerate a previously-generated image, select the image you
want and click *Use All*. This loads the text prompt and other
original settings into the control panel. If you then press *Invoke*
it will regenerate the image exactly. You can also selectively modify
the prompt or other settings to tweak the image.
Alternatively, you may click on *Use Seed* to load just the image's
seed, and leave other settings unchanged.
7. To regenerate a Stable Diffusion image that was generated by
another SD package, you need to know its text prompt and its
*Seed*. Copy-paste the prompt into the prompt box, unset the
*Randomize Seed* control in the control panel, and copy-paste the
desired *Seed* into its text field. When you Invoke, you will get
something similar to the original image. It will not be exact unless
you also set the correct values for the original sampler, CFG,
steps and dimensions, but it will (usually) be close.
#### Variations on a theme
5. Let's try generating some variations. Select your favorite sushi
image from the gallery to load it. Then select "Use All" from the list
of buttons above. This will load up all the settings used to generate
this image, including its unique seed.
Go down to the Variations section of the Control Panel and set the
button to On. Set Variation Amount to 0.2 to generate a modest
number of variations on the image, and also set the Image counter to
4. Press the `invoke` button. This will generate a series of related
images. To obtain smaller variations, just lower the Variation
Amount. You may also experiment with changing the Sampler. Some
samplers generate more variability than others. *k_euler_a* is
particularly creative, while *ddim* is pretty conservative.
6. For even more variations, experiment with increasing the setting
for *Perlin*. This adds a bit of noise to the image generation
process. Note that values of Perlin noise greater than 0.15 produce
poor images for several of the samplers.
#### Facial reconstruction and upscaling
Stable Diffusion frequently produces mangled faces, particularly when
there are multiple figures in the same scene. Stable Diffusion has
particular issues with generating reallistic eyes. InvokeAI provides
the ability to reconstruct faces using either the GFPGAN or CodeFormer
libraries. For more information see [POSTPROCESS](POSTPROCESS.md).
7. Invoke a prompt that generates a mangled face. A prompt that often
gives this is "portrait of a lawyer, 3/4 shot" (this is not intended
as a slur against lawyers!) Once you have an image that needs some
touching up, load it into the Image panel, and press the button with
the face icon (highlighted in the first screenshot below). A dialog
box will appear. Leave *Strength* at 0.8 and press *Restore Faces". If
all goes well, the eyes and other aspects of the face will be improved
(see the second screenshot)
<img src="../assets/invoke-web-server-3.png">
<img src="../assets/invoke-web-server-4.png">
The facial reconstruction *Strength* field adjusts how aggressively
the face library will try to alter the face. It can be as high as 1.0,
but be aware that this often softens the face airbrush style, losing
some details. The default 0.8 is usually sufficient.
8. "Upscaling" is the process of increasing the size of an image while
retaining the sharpness. InvokeAI uses an external library called
"ESRGAN" to do this. To invoke upscaling, simply select an image and
press the *HD* button above it. You can select between 2X and 4X
upscaling, and adjust the upscaling strength, which has much the same
meaning as in facial reconstruction. Try running this on one of your
previously-generated images.
9. Finally, you can run facial reconstruction and/or upscaling
automatically after each Invocation. Go to the Advanced Options
section of the Control Panel and turn on *Restore Face* and/or
*Upscale*.
### Image to Image
InvokeAI lets you take an existing image and use it as the basis for a
new creation. You can use any sort of image, including a photograph, a
scanned sketch, or a digital drawing, as long as it is in PNG or JPEG
format.
For this tutorial, we'll use files named
[Lincoln-and-Parrot-512.png](../assets/Lincoln-and-Parrot-512.png),
and
[Lincoln-and-Parrot-512-transparent.png](../assets/Lincoln-and-Parrot-512-transparent.png).
Download these images to your local machine now to continue with the walkthrough.
10. Click on the *Image to Image* tab icon, which is the second icon
from the top on the left-hand side of the screen:
<img src="../assets/invoke-web-server-5.png">
This will bring you to a screen similar to the one shown here:
<img src="../assets/invoke-web-server-6.png" width=640>
Drag-and-drop the Lincoln-and-Parrot image into the Image panel, or
click the blank area to get an upload dialog. The image will load into
an area marked *Initial Image*. (The WebGUI will also load the most
recently-generated image from the gallery into a section on the left,
but this image will be replaced in the next step.)
11. Go to the prompt box and type *old sea captain with raven on
shoulder* and press Invoke. A derived image will appear to the right
of the original one:
<img src="../assets/invoke-web-server-7.png" width=640>
12. Experiment with the different settings. The most influential one
in Image to Image is *Image to Image Strength* located about midway
down the control panel. By default it is set to 0.75, but can range
from 0.0 to 0.99. The higher the value, the more of the original image
the AI will replace. A value of 0 will leave the initial image
completely unchanged, while 0.99 will replace it completely. However,
the Sampler and CFG Scale also influence the final result. You can
also generate variations in the same way as described in Text to
Image.
13. What if we only want to change certain part(s) of the image and
leave the rest intact? This is called Inpainting, and a future version
of the InvokeAI web server will provide an interactive painting canvas
on which you can directly draw the areas you wish to Inpaint into. For
now, you can achieve this effect by using an external photoeditor tool
to make one or more regions of the image transparent as described in
[INPAINTING.md] and uploading that.
The file
[Lincoln-and-Parrot-512-transparent.png](../assets/Lincoln-and-Parrot-512-transparent.png)
is a version of the earlier image in which the area around the parrot
has been replaced with transparency. Click on the "x" in the upper
right of the Initial Image and upload the transparent version. Using
the same prompt "old sea captain with raven on shoulder" try Invoking
an image. This time, only the parrot will be replaced, leaving the
rest of the original image intact:
<img src="../assets/invoke-web-server-8.png" width=640>
## Parting remarks
This concludes the walkthrough, but there are several more features that you
can explore. Please check out the [Command Line Interface](CLI.md)
documentation for further explanation of the advanced features that
were not covered here.
The WebGUI is only rapid development. Check back regularly for
updates!
# Reference
## Additional Options
`--web_develop` - Starts the web server in development mode.
`--web_verbose` - Enables verbose logging
@ -72,4 +338,3 @@ When an image from the Invocation Gallery is selected, or is generated, the imag
## Acknowledgements
A huge shout-out to the core team working to make this vision a reality, including [psychedelicious](https://github.com/psychedelicious), [Kyle0654](https://github.com/Kyle0654) and [blessedcoolant](https://github.com/blessedcoolant). [hipsterusername](https://github.com/hipsterusername) was the team's unofficial cheerleader and added tooltips/docs.

4
docs/help/TROUBLESHOOT.md
View File

@ -51,7 +51,7 @@ rm ${PIP_LOG}
### **QUESTION**
`dream.py` crashes with the complaint that it can't find `ldm.simplet2i.py`. Or it complains that
`invoke.py` crashes with the complaint that it can't find `ldm.simplet2i.py`. Or it complains that
function is being passed incorrect parameters.
### **SOLUTION**
@ -63,7 +63,7 @@ Reinstall the stable diffusion modules. Enter the `stable-diffusion` directory a
### **QUESTION**
`dream.py` dies, complaining of various missing modules, none of which starts with `ldm``.
`invoke.py` dies, complaining of various missing modules, none of which starts with `ldm``.
### **SOLUTION**

12
docs/index.md
View File

@ -28,7 +28,7 @@ template: main.html
[CI checks on dev badge]: https://flat.badgen.net/github/checks/lstein/stable-diffusion/development?label=CI%20status%20on%20dev&cache=900&icon=github
[CI checks on dev link]: https://github.com/lstein/stable-diffusion/actions?query=branch%3Adevelopment
[CI checks on main badge]: https://flat.badgen.net/github/checks/lstein/stable-diffusion/main?label=CI%20status%20on%20main&cache=900&icon=github
[CI checks on main link]: https://github.com/lstein/stable-diffusion/actions/workflows/test-dream-conda.yml
[CI checks on main link]: https://github.com/lstein/stable-diffusion/actions/workflows/test-invoke-conda.yml
[discord badge]: https://flat.badgen.net/discord/members/htRgbc7e?icon=discord
[discord link]: https://discord.com/invite/htRgbc7e
[github forks badge]: https://flat.badgen.net/github/forks/lstein/stable-diffusion?icon=github
@ -85,21 +85,21 @@ You wil need one of the following:
!!! note
If you are have a Nvidia 10xx series card (e.g. the 1080ti), please run the dream script in
If you are have a Nvidia 10xx series card (e.g. the 1080ti), please run the invoke script in
full-precision mode as shown below.
Similarly, specify full-precision mode on Apple M1 hardware.
To run in full-precision mode, start `dream.py` with the `--full_precision` flag:
To run in full-precision mode, start `invoke.py` with the `--full_precision` flag:
```bash
(ldm) ~/stable-diffusion$ python scripts/dream.py --full_precision
(ldm) ~/stable-diffusion$ python scripts/invoke.py --full_precision
```
## :octicons-log-16: Latest Changes
### vNEXT <small>(TODO 2022)</small>
- Deprecated `--full_precision` / `-F`. Simply omit it and `dream.py` will auto
- Deprecated `--full_precision` / `-F`. Simply omit it and `invoke.py` will auto
configure. To switch away from auto use the new flag like `--precision=float32`.
### v1.14 <small>(11 September 2022)</small>
@ -124,7 +124,7 @@ You wil need one of the following:
[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))
- Can specify --grid on dream.py command line as the default.
- Can specify --grid on invoke.py command line as the default.
- Miscellaneous internal bug and stability fixes.
- Works on M1 Apple hardware.
- Multiple bug fixes.

24
docs/installation/INSTALL_DOCKER.md
View File

@ -136,7 +136,7 @@ $TAG_STABLE_DIFFUSION
## Startup
If you're on a **Linux container** the `dream` script is **automatically
If you're on a **Linux container** the `invoke` script is **automatically
started** and the output dir set to the Docker volume you created earlier.
If you're **directly on macOS follow these startup instructions**.
@ -148,14 +148,14 @@ half-precision requires autocast and won't work.
By default the images are saved in `outputs/img-samples/`.
```Shell
python3 scripts/dream.py --full_precision
python3 scripts/invoke.py --full_precision
```
You'll get the script's prompt. You can see available options or quit.
```Shell
dream> -h
dream> q
invoke> -h
invoke> q
```
## Text to Image
@ -166,10 +166,10 @@ Then increase steps to 100 or more for good (but slower) results.
The prompt can be in quotes or not.
```Shell
dream> The hulk fighting with sheldon cooper -s5 -n1
dream> "woman closeup highly detailed" -s 150
invoke> The hulk fighting with sheldon cooper -s5 -n1
invoke> "woman closeup highly detailed" -s 150
# Reuse previous seed and apply face restoration
dream> "woman closeup highly detailed" --steps 150 --seed -1 -G 0.75
invoke> "woman closeup highly detailed" --steps 150 --seed -1 -G 0.75
```
You'll need to experiment to see if face restoration is making it better or
@ -210,28 +210,28 @@ If you're on a Docker container, copy your input image into the Docker volume
docker cp /Users/<your-user>/Pictures/sketch-mountains-input.jpg dummy:/data/
```
Try it out generating an image (or more). The `dream` script needs absolute
Try it out generating an image (or more). The `invoke` script needs absolute
paths to find the image so don't use `~`.
If you're on your Mac
```Shell
dream> "A fantasy landscape, trending on artstation" -I /Users/<your-user>/Pictures/sketch-mountains-input.jpg --strength 0.75 --steps 100 -n4
invoke> "A fantasy landscape, trending on artstation" -I /Users/<your-user>/Pictures/sketch-mountains-input.jpg --strength 0.75 --steps 100 -n4
```
If you're on a Linux container on your Mac
```Shell
dream> "A fantasy landscape, trending on artstation" -I /data/sketch-mountains-input.jpg --strength 0.75 --steps 50 -n1
invoke> "A fantasy landscape, trending on artstation" -I /data/sketch-mountains-input.jpg --strength 0.75 --steps 50 -n1
```
## Web Interface
You can use the `dream` script with a graphical web interface. Start the web
You can use the `invoke` script with a graphical web interface. Start the web
server with:
```Shell
python3 scripts/dream.py --full_precision --web
python3 scripts/invoke.py --full_precision --web
```
If it's running on your Mac point your Mac web browser to http://127.0.0.1:9090

8
docs/installation/INSTALL_LINUX.md
View File

@ -89,16 +89,16 @@ This will create InvokeAI folder where you will follow the rest of the steps.
```
# for the pre-release weights use the -l or --liaon400m switch
(ldm) ~/InvokeAI$ python3 scripts/dream.py -l
(ldm) ~/InvokeAI$ python3 scripts/invoke.py -l
# for the post-release weights do not use the switch
(ldm) ~/InvokeAI$ python3 scripts/dream.py
(ldm) ~/InvokeAI$ python3 scripts/invoke.py
# for additional configuration switches and arguments, use -h or --help
(ldm) ~/InvokeAI$ python3 scripts/dream.py -h
(ldm) ~/InvokeAI$ python3 scripts/invoke.py -h
```
9. Subsequently, to relaunch the script, be sure to run "conda activate ldm" (step 5, second command), enter the `InvokeAI` directory, and then launch the dream script (step 8). If you forget to activate the ldm environment, the script will fail with multiple `ModuleNotFound` errors.
9. Subsequently, to relaunch the script, be sure to run "conda activate ldm" (step 5, second command), enter the `InvokeAI` directory, and then launch the invoke script (step 8). If you forget to activate the ldm environment, the script will fail with multiple `ModuleNotFound` errors.
## Updating to newer versions of the script

225
docs/installation/INSTALL_MAC.md
View File

@ -2,145 +2,113 @@
title: macOS
---
# :fontawesome-brands-apple: macOS
Invoke AI runs quite well on M1 Macs and we have a number of M1 users
in the community.
While the repo does run on Intel Macs, we only have a couple
reports. If you have an Intel Mac and run into issues, please create
an issue on Github and we will do our best to help.
## Requirements
- macOS 12.3 Monterey or later
- Python
- Patience
- Apple Silicon or Intel Mac
- About 10GB of storage (and 10GB of data if your internet connection has data caps)
- Any M1 Macs or an Intel Macs with 4GB+ of VRAM (ideally more)
Things have moved really fast and so these instructions change often which makes
them outdated pretty fast. One of the problems is that there are so many
different ways to run this.
## Installation
We are trying to build a testing setup so that when we make changes it doesn't
always break.
First you need to download a large checkpoint file.
## How to
1. Sign up at https://huggingface.co
2. Go to the [Stable diffusion diffusion model page](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original)
3. Accept the terms and click Access Repository
4. Download [sd-v1-4.ckpt (4.27 GB)](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/blob/main/sd-v1-4.ckpt) and note where you have saved it (probably the Downloads folder). You may want to move it somewhere else for longer term storage - SD needs this file to run.
(this hasn't been 100% tested yet)
While that is downloading, open Terminal and run the following
commands one at a time, reading the comments and taking care to run
the appropriate command for your Mac's architecture (Intel or M1).
First get the weights checkpoint download started since it's big and will take
some time:
Do not just copy and paste the whole thing into your terminal!
1. Sign up at [huggingface.co](https://huggingface.co)
2. Go to the
[Stable diffusion diffusion model page](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original)
3. Accept the terms and click Access Repository:
4. Download
[sd-v1-4.ckpt (4.27 GB)](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/blob/main/sd-v1-4.ckpt)
and note where you have saved it (probably the Downloads folder)
```bash
# Install brew (and Xcode command line tools):
/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
While that is downloading, open a Terminal and run the following commands:
# Now there are two options to get the Python (miniconda) environment up and running:
# 1. Alongside pyenv
# 2. Standalone
#
# If you don't know what we are talking about, choose 2.
#
# If you are familiar with python environments, you'll know there are other options
# for setting up the environment - you are on your own if you go one of those routes.
##### BEGIN TWO DIFFERENT OPTIONS #####
!!! todo "Homebrew"
### BEGIN OPTION 1: Installing alongside pyenv ###
brew install pyenv-virtualenv # you might have this from before, no problem
pyenv install anaconda3-2022.05
pyenv virtualenv anaconda3-2022.05
eval "$(pyenv init -)"
pyenv activate anaconda3-2022.05
### END OPTION 1 ###
=== "no brew installation yet"
```bash title="install brew (and Xcode command line tools)"
/bin/bash -c \
"$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
```
### BEGIN OPTION 2: Installing standalone ###
# Install cmake, protobuf, and rust:
brew install cmake protobuf rust
=== "brew is already installed"
Only if you installed protobuf in a previous version of this tutorial, otherwise skip
# BEGIN ARCHITECTURE-DEPENDENT STEP #
# For M1: install miniconda (M1 arm64 version):
curl https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-arm64.sh -o Miniconda3-latest-MacOSX-arm64.sh
/bin/bash Miniconda3-latest-MacOSX-arm64.sh
`#!bash brew uninstall protobuf`
# For Intel: install miniconda (Intel x86-64 version):
curl https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-x86_64.sh -o Miniconda3-latest-MacOSX-x86_64.sh
/bin/bash Miniconda3-latest-MacOSX-x86_64.sh
# END ARCHITECTURE-DEPENDENT STEP #
!!! todo "Conda Installation"
### END OPTION 2 ###
Now there are two different ways to set up the Python (miniconda) environment:
1. Standalone
2. with pyenv
If you don't know what we are talking about, choose Standalone
##### END TWO DIFFERENT OPTIONS #####
=== "Standalone"
```bash
# install cmake and rust:
brew install cmake rust
```
=== "M1 arm64"
```bash title="Install miniconda for M1 arm64"
curl https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-arm64.sh \
-o Miniconda3-latest-MacOSX-arm64.sh
/bin/bash Miniconda3-latest-MacOSX-arm64.sh
```
=== "Intel x86_64"
```bash title="Install miniconda for Intel"
curl https://repo.anaconda.com/miniconda/Miniconda3-latest-MacOSX-x86_64.sh \
-o Miniconda3-latest-MacOSX-x86_64.sh
/bin/bash Miniconda3-latest-MacOSX-x86_64.sh
```
=== "with pyenv"
```{.bash .annotate}
brew install rust pyenv-virtualenv # (1)!
pyenv install anaconda3-2022.05
pyenv virtualenv anaconda3-2022.05
eval "$(pyenv init -)"
pyenv activate anaconda3-2022.05
```
1. You might already have this installed, if that is the case just continue.
```{.bash .annotate title="local repo setup"}
# clone the repo
# Clone the Invoke AI repo
git clone https://github.com/invoke-ai/InvokeAI.git
cd InvokeAI
<<<<<<< HEAD
# wait until the checkpoint file has downloaded, then proceed
### WAIT FOR THE CHECKPOINT FILE TO DOWNLOAD, THEN PROCEED ###
# We will leave the big checkpoint wherever you stashed it for long-term storage,
# and make a link to it from the repo's folder. This allows you to use it for
# other repos, and if you need to delete Invoke AI, you won't have to download it again.
# create symlink to checkpoint
# Make the directory in the repo for the symlink
mkdir -p models/ldm/stable-diffusion-v1/
PATH_TO_CKPT="$HOME/Downloads" # (1)!
# This is the folder where you put the checkpoint file `sd-v1-4.ckpt`
PATH_TO_CKPT="$HOME/Downloads"
ln -s "$PATH_TO_CKPT/sd-v1-4.ckpt" \
models/ldm/stable-diffusion-v1/model.ckpt
```
# Create a link to the checkpoint
ln -s "$PATH_TO_CKPT/sd-v1-4.ckpt" models/ldm/stable-diffusion-v1/model.ckpt
1. or wherever you saved sd-v1-4.ckpt
# BEGIN ARCHITECTURE-DEPENDENT STEP #
# For M1: Create the environment & install packages
PIP_EXISTS_ACTION=w CONDA_SUBDIR=osx-arm64 conda env create -f environment-mac.yaml
!!! todo "create Conda Environment"
# For Intel: Create the environment & install packages
PIP_EXISTS_ACTION=w CONDA_SUBDIR=osx-64 conda env create -f environment-mac.yaml
# END ARCHITECTURE-DEPENDENT STEP #
=== "M1 arm64"
# Activate the environment (you need to do this every time you want to run SD)
conda activate ldm
```bash
PIP_EXISTS_ACTION=w CONDA_SUBDIR=osx-arm64 \
conda env create \
-f environment-mac.yml \
&& conda activate ldm
```
=== "Intel x86_64"
```bash
PIP_EXISTS_ACTION=w CONDA_SUBDIR=osx-64 \
conda env create \
-f environment-mac.yml \
&& conda activate ldm
```
```{.bash .annotate title="preload models and run script"}
# only need to do this once
# This will download some bits and pieces and make take a while
python scripts/preload_models.py
# now you can run SD in CLI mode
python scripts/dream.py --full_precision # (1)!
# Run SD!
python scripts/dream.py
```
# or run the web interface!
python scripts/dream.py --web
python scripts/invoke.py --web
# The original scripts should work as well.
python scripts/orig_scripts/txt2img.py \
@ -155,7 +123,7 @@ it isn't required but wont hurt.
## Common problems
After you followed all the instructions and try to run dream.py, you might
After you followed all the instructions and try to run invoke.py, you might
get several errors. Here's the errors I've seen and found solutions for.
### Is it slow?
@ -172,13 +140,13 @@ python ./scripts/orig_scripts/txt2img.py \
### Doesn't work anymore?
PyTorch nightly includes support for MPS. Because of this, this setup is
inherently unstable. One morning I woke up and it no longer worked no matter
what I did until I switched to miniforge. However, I have another Mac that works
just fine with Anaconda. If you can't get it to work, please search a little
first because many of the errors will get posted and solved. If you can't find a
solution please
[create an issue](https://github.com/invoke-ai/InvokeAI/issues).
PyTorch nightly includes support for MPS. Because of this, this setup
is inherently unstable. One morning I woke up and it no longer worked
no matter what I did until I switched to miniforge. However, I have
another Mac that works just fine with Anaconda. If you can't get it to
work, please search a little first because many of the errors will get
posted and solved. If you can't find a solution please [create an
issue](https://github.com/invoke-ai/InvokeAI/issues).
One debugging step is to update to the latest version of PyTorch nightly.
@ -220,9 +188,9 @@ There are several causes of these errors:
"(ldm)" then you activated it. If it begins with "(base)" or something else
you haven't.
2. You might've run `./scripts/preload_models.py` or `./scripts/dream.py`
2. You might've run `./scripts/preload_models.py` or `./scripts/invoke.py`
instead of `python ./scripts/preload_models.py` or
`python ./scripts/dream.py`. The cause of this error is long so it's below.
`python ./scripts/invoke.py`. The cause of this error is long so it's below.
<!-- I could not find out where the error is, otherwise would have marked it as a footnote -->
@ -378,8 +346,8 @@ python scripts/preload_models.py
WARNING: this will be slower than running natively on MPS.
```
This fork already includes a fix for this in
[environment-mac.yml](https://github.com/invoke-ai/InvokeAI/blob/main/environment-mac.yml).
The InvokeAI version includes this fix in
[environment-mac.yaml](https://github.com/invoke-ai/InvokeAI/blob/main/environment-mac.yaml).
### "Could not build wheels for tokenizers"
@ -463,13 +431,10 @@ C.
You don't have a virus. It's part of the project. Here's
[Rick](https://github.com/invoke-ai/InvokeAI/blob/main/assets/rick.jpeg)
and here's
[the code](https://github.com/invoke-ai/InvokeAI/blob/69ae4b35e0a0f6ee1af8bb9a5d0016ccb27e36dc/scripts/txt2img.py#L79)
that swaps him in. It's a NSFW filter, which IMO, doesn't work very good (and we
call this "computer vision", sheesh).
Actually, this could be happening because there's not enough RAM. You could try
the `model.half()` suggestion or specify smaller output images.
and here's [the
code](https://github.com/invoke-ai/InvokeAI/blob/69ae4b35e0a0f6ee1af8bb9a5d0016ccb27e36dc/scripts/txt2img.py#L79)
that swaps him in. It's a NSFW filter, which IMO, doesn't work very
good (and we call this "computer vision", sheesh).
---
@ -492,11 +457,9 @@ return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backen
RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
```
Update to the latest version of invoke-ai/InvokeAI. We were patching
pytorch but we found a file in stable-diffusion that we could change instead.
This is a 32-bit vs 16-bit problem.
---
Update to the latest version of invoke-ai/InvokeAI. We were
patching pytorch but we found a file in stable-diffusion that we could
change instead. This is a 32-bit vs 16-bit problem.
### The processor must support the Intel bla bla bla
@ -519,7 +482,7 @@ use ARM packages, and use `nomkl` as described above.
May appear when just starting to generate, e.g.:
```bash
dream> clouds
invoke> clouds
Generating: 0%| | 0/1 [00:00<?, ?it/s]/Users/[...]/dev/stable-diffusion/ldm/modules/embedding_manager.py:152: UserWarning: The operator 'aten::nonzero' is not currently supported on the MPS backend and will fall back to run on the CPU. This may have performance implications. (Triggered internally at /Users/runner/work/_temp/anaconda/conda-bld/pytorch_1662016319283/work/aten/src/ATen/mps/MPSFallback.mm:11.)
placeholder_idx = torch.where(
loc("mps_add"("(mpsFileLoc): /AppleInternal/Library/BuildRoots/20d6c351-ee94-11ec-bcaf-7247572f23b4/Library/Caches/com.apple.xbs/Sources/MetalPerformanceShadersGraph/mpsgraph/MetalPerformanceShadersGraph/Core/Files/MPSGraphUtilities.mm":219:0)): error: input types 'tensor<2x1280xf32>' and 'tensor<*xf16>' are not broadcast compatible

6
docs/installation/INSTALL_WINDOWS.md
View File

@ -101,13 +101,13 @@ you may instead create a shortcut to it from within `models\ldm\stable-diffusion
```bash
# for the pre-release weights
python scripts\dream.py -l
python scripts\invoke.py -l
# for the post-release weights
python scripts\dream.py
python scripts\invoke.py
```
10. Subsequently, to relaunch the script, first activate the Anaconda command window (step 3),enter the InvokeAI directory (step 5, `cd \path\to\InvokeAI`), run `conda activate ldm` (step 6b), and then launch the dream script (step 9).
10. Subsequently, to relaunch the script, first activate the Anaconda command window (step 3),enter the InvokeAI directory (step 5, `cd \path\to\InvokeAI`), run `conda activate ldm` (step 6b), and then launch the invoke script (step 9).
**Note:** Tildebyte has written an alternative
["Easy peasy Windows install"](https://github.com/invoke-ai/InvokeAI/wiki/Easy-peasy-Windows-install)

45
environment-mac.yml
View File

@ -3,12 +3,12 @@ channels:
- pytorch
- conda-forge
dependencies:
- python==3.10.5
- python==3.9.13
- pip==22.2.2
# pytorch left unpinned
- pytorch
- torchvision
- pytorch==1.12.1
- torchvision==0.13.1
# I suggest to keep the other deps sorted for convenience.
# To determine what the latest versions should be, run:
@ -27,13 +27,12 @@ dependencies:
- imgaug==0.4.0
- kornia==0.6.7
- mpmath==1.2.1
- nomkl
- nomkl=1.0
- numpy==1.23.2
- omegaconf==2.1.1
- openh264==2.3.0
- onnx==1.12.0
- onnxruntime==1.12.1
- protobuf==3.19.4
- pudb==2022.1
- pytorch-lightning==1.7.5
- scipy==1.9.1
@ -42,22 +41,22 @@ dependencies:
- tensorboard==2.10.0
- torchmetrics==0.9.3
- pip:
- flask==2.1.3
- flask_socketio==5.3.0
- flask_cors==3.0.10
- dependency_injector==4.40.0
- eventlet
- opencv-python==4.6.0
- protobuf==3.20.1
- realesrgan==0.2.5.0
- send2trash==1.8.0
- test-tube==0.7.5
- transformers==4.21.2
- torch-fidelity==0.3.0
- -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
- -e git+https://github.com/openai/CLIP.git@main#egg=clip
- -e git+https://github.com/Birch-san/k-diffusion.git@mps#egg=k_diffusion
- -e git+https://github.com/lstein/GFPGAN@fix-dark-cast-images#egg=gfpgan
- -e .
- flask==2.1.3
- flask_socketio==5.3.0
- flask_cors==3.0.10
- dependency_injector==4.40.0
- eventlet==0.33.1
- opencv-python==4.6.0
- protobuf==3.19.5
- realesrgan==0.2.5.0
- send2trash==1.8.0
- test-tube==0.7.5
- transformers==4.21.2
- torch-fidelity==0.3.0
- -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
- -e git+https://github.com/openai/CLIP.git@main#egg=clip
- -e git+https://github.com/Birch-san/k-diffusion.git@mps#egg=k_diffusion
- -e git+https://github.com/TencentARC/GFPGAN.git#egg=gfpgan
- -e .
variables:
PYTORCH_ENABLE_MPS_FALLBACK: 1

2
environment.yml
View File

@ -36,5 +36,5 @@ dependencies:
- -e git+https://github.com/openai/CLIP.git@main#egg=clip
- -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
- -e git+https://github.com/Birch-san/k-diffusion.git@mps#egg=k_diffusion
- -e git+https://github.com/lstein/GFPGAN@fix-dark-cast-images#egg=gfpgan
- -e git+https://github.com/TencentARC/GFPGAN.git#egg=gfpgan
- -e .

1
frontend/dist/assets/index.4ceb640a.css vendored Normal file
View File

File diff suppressed because one or more lines are too long

483
frontend/dist/assets/index.6cdae835.js vendored Normal file
View File

File diff suppressed because one or more lines are too long

6
frontend/dist/index.html vendored
View File

@ -6,8 +6,8 @@
<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.27eefde8.js"></script>
<link rel="stylesheet" href="/assets/index.c04b2fd8.css">
<script type="module" crossorigin src="/assets/index.6cdae835.js"></script>
<link rel="stylesheet" href="/assets/index.4ceb640a.css">
</head>
<body>
@ -15,4 +15,4 @@
</body>
</html>
</html>

2
frontend/src/features/gallery/CurrentImageDisplay.scss
View File

@ -71,7 +71,7 @@
.next-prev-button-trigger-area {
width: 7rem;
height: 100%;
width: 100%;
width: 15%;
display: grid;
align-items: center;
pointer-events: auto;

8
frontend/src/features/options/AdvancedOptions/Seed/SeedOptions.tsx
View File

@ -16,8 +16,12 @@ const SeedOptions = () => {
<Seed />
<ShuffleSeed />
</Flex>
<Threshold />
<Perlin />
<Flex gap={2}>
<Threshold />
</Flex>
<Flex gap={2}>
<Perlin />
</Flex>
</Flex>
);
};

2
frontend/src/features/options/optionsSlice.ts
View File

@ -252,7 +252,9 @@ export const optionsSlice = createSlice({
if (steps) state.steps = steps;
if (cfg_scale) state.cfgScale = cfg_scale;
if (threshold) state.threshold = threshold;
if (typeof threshold === 'undefined') state.threshold = 0;
if (perlin) state.perlin = perlin;
if (typeof perlin === 'undefined') state.perlin = 0;
if (typeof seamless === 'boolean') state.seamless = seamless;
if (width) state.width = width;
if (height) state.height = height;

2
frontend/src/features/system/SiteHeader.scss
View File

@ -21,7 +21,7 @@
.site-header-right-side {
display: grid;
grid-template-columns: repeat(6, max-content);
grid-template-columns: repeat(7, max-content);
align-items: center;
column-gap: 0.5rem;
}

20
frontend/src/features/system/SiteHeader.tsx
View File

@ -1,7 +1,7 @@
import { IconButton, Link, Tooltip, useColorMode } from '@chakra-ui/react';
import { useHotkeys } from 'react-hotkeys-hook';
import { FaSun, FaMoon, FaGithub } from 'react-icons/fa';
import { FaSun, FaMoon, FaGithub, FaDiscord } from 'react-icons/fa';
import { MdHelp, MdKeyboard, MdSettings } from 'react-icons/md';
import InvokeAILogo from '../../assets/images/logo.png';
@ -70,7 +70,7 @@ const SiteHeader = () => {
icon={
<Link
isExternal
href="http://github.com/lstein/stable-diffusion/issues"
href="http://github.com/invoke-ai/InvokeAI/issues"
>
<MdHelp />
</Link>
@ -85,13 +85,27 @@ const SiteHeader = () => {
fontSize={20}
size={'sm'}
icon={
<Link isExternal href="http://github.com/lstein/stable-diffusion">
<Link isExternal href="http://github.com/invoke-ai/InvokeAI">
<FaGithub />
</Link>
}
/>
</Tooltip>
<Tooltip hasArrow label="Discord" placement={'bottom'}>
<IconButton
aria-label="Link to Discord Server"
variant="link"
fontSize={20}
size={'sm'}
icon={
<Link isExternal href="https://discord.gg/ZmtBAhwWhy">
<FaDiscord />
</Link>
}
/>
</Tooltip>
<Tooltip hasArrow label="Theme" placement={'bottom'}>
<IconButton
aria-label="Toggle Dark Mode"

4
ldm/dream/generator/__init__.py
View File

@ -1,4 +0,0 @@
'''
Initialization file for the ldm.dream.generator package
'''
from .base import Generator

4
ldm/dream/restoration/__init__.py
View File

@ -1,4 +0,0 @@
'''
Initialization file for the ldm.dream.restoration package
'''
from .base import Restoration

92
ldm/generate.py
View File

@ -19,7 +19,7 @@ import cv2
import skimage
from omegaconf import OmegaConf
from ldm.dream.generator.base import downsampling
from ldm.invoke.generator.base import downsampling
from PIL import Image, ImageOps
from torch import nn
from pytorch_lightning import seed_everything, logging
@ -28,33 +28,11 @@ from ldm.util import instantiate_from_config
from ldm.models.diffusion.ddim import DDIMSampler
from ldm.models.diffusion.plms import PLMSSampler
from ldm.models.diffusion.ksampler import KSampler
from ldm.dream.pngwriter import PngWriter
from ldm.dream.args import metadata_from_png
from ldm.dream.image_util import InitImageResizer
from ldm.dream.devices import choose_torch_device, choose_precision
from ldm.dream.conditioning import get_uc_and_c
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)
from ldm.invoke.pngwriter import PngWriter
from ldm.invoke.args import metadata_from_png
from ldm.invoke.image_util import InitImageResizer
from ldm.invoke.devices import choose_torch_device, choose_precision
from ldm.invoke.conditioning import get_uc_and_c
"""Simplified text to image API for stable diffusion/latent diffusion
@ -142,7 +120,8 @@ class Generate:
config = None,
gfpgan=None,
codeformer=None,
esrgan=None
esrgan=None,
free_gpu_mem=False,
):
models = OmegaConf.load(conf)
mconfig = models[model]
@ -169,6 +148,7 @@ class Generate:
self.gfpgan = gfpgan
self.codeformer = codeformer
self.esrgan = esrgan
self.free_gpu_mem = free_gpu_mem
# Note that in previous versions, there was an option to pass the
# device to Generate(). However the device was then ignored, so
@ -295,9 +275,9 @@ class Generate:
def process_image(image,seed):
image.save(f{'images/seed.png'})
The callback used by the prompt2png() can be found in ldm/dream_util.py. It contains code
to create the requested output directory, select a unique informative name for each image, and
write the prompt into the PNG metadata.
The code used to save images to a directory can be found in ldm/invoke/pngwriter.py.
It contains code to create the requested output directory, select a unique informative
name for each image, and write the prompt into the PNG metadata.
"""
# TODO: convert this into a getattr() loop
steps = steps or self.steps
@ -385,7 +365,8 @@ class Generate:
generator = self._make_txt2img()
generator.set_variation(
self.seed, variation_amount, with_variations)
self.seed, variation_amount, with_variations
)
results = generator.generate(
prompt,
iterations=iterations,
@ -521,7 +502,7 @@ class Generate:
)
elif tool == 'outcrop':
from ldm.dream.restoration.outcrop import Outcrop
from ldm.invoke.restoration.outcrop import Outcrop
extend_instructions = {}
for direction,pixels in _pairwise(opt.outcrop):
extend_instructions[direction]=int(pixels)
@ -558,7 +539,7 @@ class Generate:
image_callback = callback,
)
elif tool == 'outpaint':
from ldm.dream.restoration.outpaint import Outpaint
from ldm.invoke.restoration.outpaint import Outpaint
restorer = Outpaint(image,self)
return restorer.process(
opt,
@ -594,18 +575,14 @@ class Generate:
height,
)
if image.width < self.width and image.height < self.height:
print(f'>> WARNING: img2img and inpainting may produce unexpected results with initial images smaller than {self.width}x{self.height} in both dimensions')
# if image has a transparent area and no mask was provided, then try to generate mask
if self._has_transparency(image) and not mask:
print(
'>> Initial image has transparent areas. Will inpaint in these regions.')
if self._check_for_erasure(image):
print(
'>> WARNING: Colors underneath the transparent region seem to have been erased.\n',
'>> Inpainting will be suboptimal. Please preserve the colors when making\n',
'>> a transparency mask, or provide mask explicitly using --init_mask (-M).'
)
if self._has_transparency(image):
self._transparency_check_and_warning(image, mask)
# this returns a torch tensor
init_mask = self._create_init_mask(image,width,height,fit=fit)
init_mask = self._create_init_mask(image, width, height, fit=fit)
if (image.width * image.height) > (self.width * self.height):
print(">> This input is larger than your defaults. If you run out of memory, please use a smaller image.")
@ -621,39 +598,39 @@ class Generate:
def _make_base(self):
if not self.generators.get('base'):
from ldm.dream.generator import Generator
from ldm.invoke.generator import Generator
self.generators['base'] = Generator(self.model, self.precision)
return self.generators['base']
def _make_img2img(self):
if not self.generators.get('img2img'):
from ldm.dream.generator.img2img import Img2Img
from ldm.invoke.generator.img2img import Img2Img
self.generators['img2img'] = Img2Img(self.model, self.precision)
return self.generators['img2img']
def _make_embiggen(self):
if not self.generators.get('embiggen'):
from ldm.dream.generator.embiggen import Embiggen
from ldm.invoke.generator.embiggen import Embiggen
self.generators['embiggen'] = Embiggen(self.model, self.precision)
return self.generators['embiggen']
def _make_txt2img(self):
if not self.generators.get('txt2img'):
from ldm.dream.generator.txt2img import Txt2Img
from ldm.invoke.generator.txt2img import Txt2Img
self.generators['txt2img'] = Txt2Img(self.model, self.precision)
self.generators['txt2img'].free_gpu_mem = self.free_gpu_mem
return self.generators['txt2img']
def _make_txt2img2img(self):
if not self.generators.get('txt2img2'):
from ldm.dream.generator.txt2img2img import Txt2Img2Img
from ldm.invoke.generator.txt2img2img import Txt2Img2Img
self.generators['txt2img2'] = Txt2Img2Img(self.model, self.precision)
self.generators['txt2img2'].free_gpu_mem = self.free_gpu_mem
return self.generators['txt2img2']
def _make_inpaint(self):
if not self.generators.get('inpaint'):
from ldm.dream.generator.inpaint import Inpaint
from ldm.invoke.generator.inpaint import Inpaint
self.generators['inpaint'] = Inpaint(self.model, self.precision)
return self.generators['inpaint']
@ -784,7 +761,7 @@ class Generate:
print(msg)
# Be warned: config is the path to the model config file, not the dream conf file!
# Be warned: config is the path to the model config file, not the invoke conf file!
# Also note that we can get config and weights from self, so why do we need to
# pass them as args?
def _load_model_from_config(self, config, weights):
@ -920,6 +897,17 @@ class Generate:
colored += 1
return colored == 0
def _transparency_check_and_warning(self,image, mask):
if not mask:
print(
'>> Initial image has transparent areas. Will inpaint in these regions.')
if self._check_for_erasure(image):
print(
'>> WARNING: Colors underneath the transparent region seem to have been erased.\n',
'>> Inpainting will be suboptimal. Please preserve the colors when making\n',
'>> a transparency mask, or provide mask explicitly using --init_mask (-M).'
)
def _squeeze_image(self, image):
x, y, resize_needed = self._resolution_check(image.width, image.height)
if resize_needed:

28
ldm/dream/args.py → ldm/invoke/args.py
View File

@ -1,7 +1,7 @@
"""Helper class for dealing with image generation arguments.
The Args class parses both the command line (shell) arguments, as well as the
command string passed at the dream> prompt. It serves as the definitive repository
command string passed at the invoke> prompt. It serves as the definitive repository
of all the arguments used by Generate and their default values, and implements the
preliminary metadata standards discussed here:
@ -19,7 +19,7 @@ To use:
print('oops')
sys.exit(-1)
# read in a command passed to the dream> prompt:
# read in a command passed to the invoke> prompt:
opts = opt.parse_cmd('do androids dream of electric sheep? -H256 -W1024 -n4')
# The Args object acts like a namespace object
@ -64,7 +64,7 @@ To generate a dict representing RFC266 metadata:
This will generate an RFC266 dictionary that can then be turned into a JSON
and written to the PNG file. The optional seeds, weights, model_hash and
postprocesser arguments are not available to the opt object and so must be
provided externally. See how dream.py does it.
provided externally. See how invoke.py does it.
Note that this function was originally called format_metadata() and a wrapper
is provided that issues a deprecation notice.
@ -91,8 +91,8 @@ import re
import copy
import base64
import functools
import ldm.dream.pngwriter
from ldm.dream.conditioning import split_weighted_subprompts
import ldm.invoke.pngwriter
from ldm.invoke.conditioning import split_weighted_subprompts
SAMPLER_CHOICES = [
'ddim',
@ -151,7 +151,7 @@ class Args(object):
'''
Initialize new Args class. It takes two optional arguments, an argparse
parser for switches given on the shell command line, and an argparse
parser for switches given on the dream> CLI line. If one or both are
parser for switches given on the invoke> CLI line. If one or both are
missing, it creates appropriate parsers internally.
'''
self._arg_parser = arg_parser or self._create_arg_parser()
@ -168,7 +168,7 @@ class Args(object):
return None
def parse_cmd(self,cmd_string):
'''Parse a dream>-style command string '''
'''Parse a invoke>-style command string '''
command = cmd_string.replace("'", "\\'")
try:
elements = shlex.split(command)
@ -269,7 +269,7 @@ class Args(object):
if a['with_variations']:
formatted_variations = ','.join(f'{seed}:{weight}' for seed, weight in (a["with_variations"]))
switches.append(f'-V {formatted_variations}')
if 'variations' in a:
if 'variations' in a and len(a['variations'])>0:
switches.append(f'-V {a["variations"]}')
return ' '.join(switches)
@ -509,23 +509,23 @@ class Args(object):
)
return parser
# This creates the parser that processes commands on the dream> command line
# This creates the parser that processes commands on the invoke> command line
def _create_dream_cmd_parser(self):
parser = PagingArgumentParser(
formatter_class=ArgFormatter,
description=
"""
*Image generation:*
dream> a fantastic alien landscape -W576 -H512 -s60 -n4
invoke> a fantastic alien landscape -W576 -H512 -s60 -n4
*postprocessing*
!fix applies upscaling/facefixing to a previously-generated image.
dream> !fix 0000045.4829112.png -G1 -U4 -ft codeformer
invoke> !fix 0000045.4829112.png -G1 -U4 -ft codeformer
*History manipulation*
!fetch retrieves the command used to generate an earlier image.
dream> !fetch 0000015.8929913.png
dream> a fantastic alien landscape -W 576 -H 512 -s 60 -A plms -C 7.5
invoke> !fetch 0000015.8929913.png
invoke> a fantastic alien landscape -W 576 -H 512 -s 60 -A plms -C 7.5
!history lists all the commands issued during the current session.
@ -842,7 +842,7 @@ def metadata_from_png(png_file_path) -> Args:
an Args object containing the image metadata. Note that this
returns a single Args object, not multiple.
'''
meta = ldm.dream.pngwriter.retrieve_metadata(png_file_path)
meta = ldm.invoke.pngwriter.retrieve_metadata(png_file_path)
if 'sd-metadata' in meta and len(meta['sd-metadata'])>0 :
return metadata_loads(meta)[0]
else:

0
ldm/dream/conditioning.py → ldm/invoke/conditioning.py
View File

0
ldm/dream/devices.py → ldm/invoke/devices.py
View File

4
ldm/invoke/generator/__init__.py Normal file
View File

@ -0,0 +1,4 @@
'''
Initialization file for the ldm.invoke.generator package
'''
from .base import Generator

6
ldm/dream/generator/base.py → ldm/invoke/generator/base.py
View File

@ -1,5 +1,5 @@
'''
Base class for ldm.dream.generator.*
Base class for ldm.invoke.generator.*
including img2img, txt2img, and inpaint
'''
import torch
@ -9,7 +9,7 @@ from tqdm import tqdm, trange
from PIL import Image
from einops import rearrange, repeat
from pytorch_lightning import seed_everything
from ldm.dream.devices import choose_autocast
from ldm.invoke.devices import choose_autocast
from ldm.util import rand_perlin_2d
downsampling = 8
@ -21,6 +21,8 @@ class Generator():
self.seed = None
self.latent_channels = model.channels
self.downsampling_factor = downsampling # BUG: should come from model or config
self.perlin = 0.0
self.threshold = 0
self.variation_amount = 0
self.with_variations = []

12
ldm/dream/generator/embiggen.py → ldm/invoke/generator/embiggen.py
View File

@ -1,15 +1,15 @@
'''
ldm.dream.generator.embiggen descends from ldm.dream.generator
and generates with ldm.dream.generator.img2img
ldm.invoke.generator.embiggen descends from ldm.invoke.generator
and generates with ldm.invoke.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.dream.generator.img2img import Img2Img
from ldm.dream.devices import choose_autocast
from ldm.invoke.generator.base import Generator
from ldm.invoke.generator.img2img import Img2Img
from ldm.invoke.devices import choose_autocast
from ldm.models.diffusion.ddim import DDIMSampler
class Embiggen(Generator):
@ -107,7 +107,7 @@ class Embiggen(Generator):
initsuperwidth = round(initsuperwidth*embiggen[0])
initsuperheight = round(initsuperheight*embiggen[0])
if embiggen[1] > 0: # No point in ESRGAN upscaling if strength is set zero
from ldm.dream.restoration.realesrgan import ESRGAN
from ldm.invoke.restoration.realesrgan import ESRGAN
esrgan = ESRGAN()
print(
f'>> ESRGAN upscaling init image prior to cutting with Embiggen with strength {embiggen[1]}')

6
ldm/dream/generator/img2img.py → ldm/invoke/generator/img2img.py
View File

@ -1,11 +1,11 @@
'''
ldm.dream.generator.img2img descends from ldm.dream.generator
ldm.invoke.generator.img2img descends from ldm.invoke.generator
'''
import torch
import numpy as np
from ldm.dream.devices import choose_autocast
from ldm.dream.generator.base import Generator
from ldm.invoke.devices import choose_autocast
from ldm.invoke.generator.base import Generator
from ldm.models.diffusion.ddim import DDIMSampler
class Img2Img(Generator):

8
ldm/dream/generator/inpaint.py → ldm/invoke/generator/inpaint.py
View File

@ -1,12 +1,12 @@
'''
ldm.dream.generator.inpaint descends from ldm.dream.generator
ldm.invoke.generator.inpaint descends from ldm.invoke.generator
'''
import torch
import numpy as np
from einops import rearrange, repeat
from ldm.dream.devices import choose_autocast
from ldm.dream.generator.img2img import Img2Img
from ldm.invoke.devices import choose_autocast
from ldm.invoke.generator.img2img import Img2Img
from ldm.models.diffusion.ddim import DDIMSampler
from ldm.models.diffusion.ksampler import KSampler
@ -27,7 +27,7 @@ class Inpaint(Img2Img):
# klms samplers not supported yet, so ignore previous sampler
if isinstance(sampler,KSampler):
print(
f">> sampler '{sampler.__class__.__name__}' is not yet supported for inpainting, using DDIMSampler instead."
f">> Using recommended DDIM sampler for inpainting."
)
sampler = DDIMSampler(self.model, device=self.model.device)

4
ldm/dream/generator/txt2img.py → ldm/invoke/generator/txt2img.py
View File

@ -1,10 +1,10 @@
'''
ldm.dream.generator.txt2img inherits from ldm.dream.generator
ldm.invoke.generator.txt2img inherits from ldm.invoke.generator
'''
import torch
import numpy as np
from ldm.dream.generator.base import Generator
from ldm.invoke.generator.base import Generator
class Txt2Img(Generator):
def __init__(self, model, precision):

18
ldm/dream/generator/txt2img2img.py → ldm/invoke/generator/txt2img2img.py
View File

@ -1,11 +1,11 @@
'''
ldm.dream.generator.txt2img inherits from ldm.dream.generator
ldm.invoke.generator.txt2img inherits from ldm.invoke.generator
'''
import torch
import numpy as np
import math
from ldm.dream.generator.base import Generator
from ldm.invoke.generator.base import Generator
from ldm.models.diffusion.ddim import DDIMSampler
@ -64,7 +64,7 @@ class Txt2Img2Img(Generator):
)
print(
f"\n>> Interpolating from {init_width}x{init_height} to {width}x{height}"
f"\n>> Interpolating from {init_width}x{init_height} to {width}x{height} using DDIM sampling"
)
# resizing
@ -75,17 +75,19 @@ class Txt2Img2Img(Generator):
)
t_enc = int(strength * steps)
ddim_sampler = DDIMSampler(self.model, device=self.model.device)
ddim_sampler.make_schedule(
ddim_num_steps=steps, ddim_eta=ddim_eta, verbose=False
)
x = self.get_noise(width,height,False)
z_enc = sampler.stochastic_encode(
z_enc = ddim_sampler.stochastic_encode(
samples,
torch.tensor([t_enc]).to(self.model.device),
noise=x
noise=self.get_noise(width,height,False)
)
# decode it
samples = sampler.decode(
samples = ddim_sampler.decode(
z_enc,
c,
t_enc,

0
ldm/dream/image_util.py → ldm/invoke/image_util.py
View File

0
ldm/dream/log.py → ldm/invoke/log.py
View File

0
ldm/dream/pngwriter.py → ldm/invoke/pngwriter.py
View File

12
ldm/dream/readline.py → ldm/invoke/readline.py
View File

@ -1,17 +1,17 @@
"""
Readline helper functions for dream.py (linux and mac only).
Readline helper functions for invoke.py.
You may import the global singleton `completer` to get access to the
completer object itself. This is useful when you want to autocomplete
seeds:
from ldm.dream.readline import completer
from ldm.invoke.readline import completer
completer.add_seed(18247566)
completer.add_seed(9281839)
"""
import os
import re
import atexit
from ldm.dream.args import Args
from ldm.invoke.args import Args
# ---------------readline utilities---------------------
try:
@ -20,7 +20,7 @@ try:
except (ImportError,ModuleNotFoundError):
readline_available = False
IMG_EXTENSIONS = ('.png','.jpg','.jpeg')
IMG_EXTENSIONS = ('.png','.jpg','.jpeg','.PNG','.JPG','.JPEG','.gif','.GIF')
COMMANDS = (
'--steps','-s',
'--seed','-S',
@ -74,7 +74,7 @@ class Completer(object):
def complete(self, text, state):
'''
Completes dream command line.
Completes invoke command line.
BUG: it doesn't correctly complete files that have spaces in the name.
'''
buffer = readline.get_line_buffer()
@ -287,7 +287,7 @@ def get_completer(opt:Args)->Completer:
readline.parse_and_bind('set skip-completed-text on')
readline.parse_and_bind('set show-all-if-ambiguous on')
histfile = os.path.join(os.path.expanduser(opt.outdir), '.dream_history')
histfile = os.path.join(os.path.expanduser(opt.outdir), '.invoke_history')
try:
readline.read_history_file(histfile)
readline.set_history_length(1000)

4
ldm/invoke/restoration/__init__.py Normal file
View File

@ -0,0 +1,4 @@
'''
Initialization file for the ldm.invoke.restoration package
'''
from .base import Restoration

6
ldm/dream/restoration/base.py → ldm/invoke/restoration/base.py
View File

@ -23,16 +23,16 @@ class Restoration():
# Face Restore Models
def load_gfpgan(self, gfpgan_dir, gfpgan_model_path):
from ldm.dream.restoration.gfpgan import GFPGAN
from ldm.invoke.restoration.gfpgan import GFPGAN
return GFPGAN(gfpgan_dir, gfpgan_model_path)
def load_codeformer(self):
from ldm.dream.restoration.codeformer import CodeFormerRestoration
from ldm.invoke.restoration.codeformer import CodeFormerRestoration
return CodeFormerRestoration()
# Upscale Models
def load_esrgan(self, esrgan_bg_tile=400):
from ldm.dream.restoration.realesrgan import ESRGAN
from ldm.invoke.restoration.realesrgan import ESRGAN
esrgan = ESRGAN(esrgan_bg_tile)
print('>> ESRGAN Initialized')
return esrgan;

6
ldm/dream/restoration/codeformer.py → ldm/invoke/restoration/codeformer.py
View File

@ -8,7 +8,7 @@ pretrained_model_url = 'https://github.com/sczhou/CodeFormer/releases/download/v
class CodeFormerRestoration():
def __init__(self,
codeformer_dir='ldm/dream/restoration/codeformer',
codeformer_dir='ldm/invoke/restoration/codeformer',
codeformer_model_path='weights/codeformer.pth') -> None:
self.model_path = os.path.join(codeformer_dir, codeformer_model_path)
self.codeformer_model_exists = os.path.isfile(self.model_path)
@ -27,7 +27,7 @@ class CodeFormerRestoration():
from basicsr.utils.download_util import load_file_from_url
from basicsr.utils import img2tensor, tensor2img
from facexlib.utils.face_restoration_helper import FaceRestoreHelper
from ldm.dream.restoration.codeformer_arch import CodeFormer
from ldm.invoke.restoration.codeformer_arch import CodeFormer
from torchvision.transforms.functional import normalize
from PIL import Image
@ -35,7 +35,7 @@ class CodeFormerRestoration():
cf = cf_class(dim_embd=512, codebook_size=1024, n_head=8, n_layers=9, connect_list=['32', '64', '128', '256']).to(device)
checkpoint_path = load_file_from_url(url=pretrained_model_url, model_dir=os.path.abspath('ldm/dream/restoration/codeformer/weights'), progress=True)
checkpoint_path = load_file_from_url(url=pretrained_model_url, model_dir=os.path.abspath('ldm/invoke/restoration/codeformer/weights'), progress=True)
checkpoint = torch.load(checkpoint_path)['params_ema']
cf.load_state_dict(checkpoint)
cf.eval()

0
ldm/dream/restoration/codeformer/weights/README → ldm/invoke/restoration/codeformer/weights/README
View File

2
ldm/dream/restoration/codeformer_arch.py → ldm/invoke/restoration/codeformer_arch.py
View File

@ -5,7 +5,7 @@ from torch import nn, Tensor
import torch.nn.functional as F
from typing import Optional, List
from ldm.dream.restoration.vqgan_arch import *
from ldm.invoke.restoration.vqgan_arch import *
from basicsr.utils import get_root_logger
from basicsr.utils.registry import ARCH_REGISTRY

0
ldm/dream/restoration/gfpgan.py → ldm/invoke/restoration/gfpgan.py
View File

0
ldm/dream/restoration/outcrop.py → ldm/invoke/restoration/outcrop.py
View File

2
ldm/dream/restoration/outpaint.py → ldm/invoke/restoration/outpaint.py
View File

@ -13,8 +13,6 @@ class Outpaint(object):
seed = old_opt.seed
prompt = old_opt.prompt
print(f'DEBUG: old seed={seed}, old prompt = {prompt}')
def wrapped_callback(img,seed,**kwargs):
image_callback(img,seed,use_prefix=prefix,**kwargs)

0
ldm/dream/restoration/realesrgan.py → ldm/invoke/restoration/realesrgan.py
View File

0
ldm/dream/restoration/vqgan_arch.py → ldm/invoke/restoration/vqgan_arch.py
View File

4
ldm/dream/server.py → ldm/invoke/server.py
View File

@ -4,9 +4,9 @@ import copy
import base64
import mimetypes
import os
from ldm.dream.args import Args, metadata_dumps
from ldm.invoke.args import Args, metadata_dumps
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from ldm.dream.pngwriter import PngWriter
from ldm.invoke.pngwriter import PngWriter
from threading import Event
def build_opt(post_data, seed, gfpgan_model_exists):

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

@ -4,7 +4,7 @@ import torch
import numpy as np
from tqdm import tqdm
from functools import partial
from ldm.dream.devices import choose_torch_device
from ldm.invoke.devices import choose_torch_device
from ldm.models.diffusion.sampler import Sampler
from ldm.modules.diffusionmodules.util import noise_like

11
ldm/models/diffusion/ksampler.py
View File

@ -2,7 +2,7 @@
import k_diffusion as K
import torch
import torch.nn as nn
from ldm.dream.devices import choose_torch_device
from ldm.invoke.devices import choose_torch_device
from ldm.models.diffusion.sampler import Sampler
from ldm.util import rand_perlin_2d
from ldm.modules.diffusionmodules.util import (
@ -57,8 +57,9 @@ class KSampler(Sampler):
schedule,
steps=model.num_timesteps,
)
self.ds = None
self.s_in = None
self.sigmas = None
self.ds = None
self.s_in = None
def forward(self, x, sigma, uncond, cond, cond_scale):
x_in = torch.cat([x] * 2)
@ -190,7 +191,7 @@ class KSampler(Sampler):
'uncond': unconditional_conditioning,
'cond_scale': unconditional_guidance_scale,
}
print(f'>> Sampling with k_{self.schedule}')
print(f'>> Sampling with k_{self.schedule} starting at step {len(self.sigmas)-S-1} of {len(self.sigmas)-1} ({S} new sampling steps)')
return (
K.sampling.__dict__[f'sample_{self.schedule}'](
model_wrap_cfg, x, sigmas, extra_args=extra_args,
@ -199,6 +200,8 @@ class KSampler(Sampler):
None,
)
# this code will support inpainting if and when ksampler API modified or
# a workaround is found.
@torch.no_grad()
def p_sample(
self,

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

@ -4,7 +4,7 @@ import torch
import numpy as np
from tqdm import tqdm
from functools import partial
from ldm.dream.devices import choose_torch_device
from ldm.invoke.devices import choose_torch_device
from ldm.models.diffusion.sampler import Sampler
from ldm.modules.diffusionmodules.util import noise_like

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

@ -8,7 +8,7 @@ import torch
import numpy as np
from tqdm import tqdm
from functools import partial
from ldm.dream.devices import choose_torch_device
from ldm.invoke.devices import choose_torch_device
from ldm.modules.diffusionmodules.util import (
make_ddim_sampling_parameters,

2
ldm/modules/encoders/modules.py
View File

@ -5,7 +5,7 @@ import clip
from einops import rearrange, repeat
from transformers import CLIPTokenizer, CLIPTextModel
import kornia
from ldm.dream.devices import choose_torch_device
from ldm.invoke.devices import choose_torch_device
from ldm.modules.x_transformer import (
Encoder,

2
notebooks/notebook_helpers.py
View File

@ -14,7 +14,7 @@ from ldm.models.diffusion.ddim import DDIMSampler
from ldm.util import ismap
import time
from omegaconf import OmegaConf
from ldm.dream.devices import choose_torch_device
from ldm.invoke.devices import choose_torch_device
def download_models(mode):

6
requirements-linux-arm64.txt
View File

@ -20,6 +20,6 @@ torchmetrics==0.6.0
transformers==4.19.2
-e git+https://github.com/openai/CLIP.git@main#egg=clip
-e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
git+https://github.com/lstein/k-diffusion.git@master#egg=k-diffusion
-e git+https://github.com/lstein/GFPGAN@fix-dark-cast-images#egg=gfpgan
-e .
-e git+https://github.com/lstein/k-diffusion.git@master#egg=k-diffusion
-e git+https://github.com/TencentARC/GFPGAN.git#egg=gfpgan
-e .

3
requirements-mac-MPS-CPU.txt
View File

@ -1,8 +1,5 @@
-r requirements.txt
--pre
--extra-index-url https://download.pytorch.org/whl/nightly/cpu --trusted-host https://download.pytorch.org
protobuf==3.19.4
torch
torchvision

3
requirements.txt
View File

@ -31,6 +31,7 @@ flaskwebgui==0.3.7
send2trash
dependency_injector==4.40.0
eventlet
realesrgan
git+https://github.com/openai/CLIP.git@main#egg=clip
git+https://github.com/Birch-san/k-diffusion.git@mps#egg=k-diffusion
git+https://github.com/lstein/GFPGAN@fix-dark-cast-images#egg=gfpgan
git+https://github.com/TencentARC/GFPGAN.git#egg=gfpgan

571
scripts/dream.py
View File

@ -1,571 +1,12 @@
#!/usr/bin/env python3
# Copyright (c) 2022 Lincoln D. Stein (https://github.com/lstein)
import os
import re
import sys
import shlex
import copy
import warnings
import time
import traceback
sys.path.append('.') # corrects a weird problem on Macs
from ldm.dream.readline import get_completer
from ldm.dream.args import Args, metadata_dumps, metadata_from_png, dream_cmd_from_png
from ldm.dream.pngwriter import PngWriter, retrieve_metadata, write_metadata
from ldm.dream.image_util import make_grid
from ldm.dream.log import write_log
from omegaconf import OmegaConf
from backend.invoke_ai_web_server import InvokeAIWebServer
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)
def main():
"""Initialize command-line parsers and the diffusion model"""
opt = Args()
args = opt.parse_args()
if not args:
sys.exit(-1)
if args.laion400m:
print('--laion400m flag has been deprecated. Please use --model laion400m instead.')
sys.exit(-1)
if args.weights:
print('--weights argument has been deprecated. Please edit ./configs/models.yaml, and select the weights using --model instead.')
sys.exit(-1)
print('* Initializing, be patient...\n')
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()
# Loading Face Restoration and ESRGAN Modules
try:
gfpgan, codeformer, esrgan = None, None, None
if opt.restore or opt.esrgan:
from ldm.dream.restoration import Restoration
restoration = Restoration()
if opt.restore:
gfpgan, codeformer = restoration.load_face_restore_models(opt.gfpgan_dir, opt.gfpgan_model_path)
else:
print('>> Face restoration disabled')
if opt.esrgan:
esrgan = restoration.load_esrgan(opt.esrgan_bg_tile)
else:
print('>> Upscaling disabled')
else:
print('>> Face restoration and upscaling disabled')
except (ModuleNotFoundError, ImportError):
print(traceback.format_exc(), file=sys.stderr)
print('>> You may need to install the ESRGAN and/or GFPGAN modules')
# 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
try:
gen = Generate(
conf = opt.conf,
model = opt.model,
sampler_name = opt.sampler_name,
embedding_path = opt.embedding_path,
full_precision = opt.full_precision,
precision = opt.precision,
gfpgan=gfpgan,
codeformer=codeformer,
esrgan=esrgan
)
except (FileNotFoundError, IOError, KeyError) as e:
print(f'{e}. Aborting.')
sys.exit(-1)
# make sure the output directory exists
if not os.path.exists(opt.outdir):
os.makedirs(opt.outdir)
# 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
gen.load_model()
#set additional option
gen.free_gpu_mem = opt.free_gpu_mem
# web server loops forever
if opt.web or opt.gui:
invoke_ai_web_server_loop(gen, gfpgan, codeformer, esrgan)
sys.exit(0)
if not infile:
print(
"\n* Initialization done! Awaiting your command (-h for help, 'q' to quit)"
)
main_loop(gen, opt, infile)
# TODO: main_loop() has gotten busy. Needs to be refactored.
def main_loop(gen, opt, infile):
"""prompt/read/execute loop"""
done = False
path_filter = re.compile(r'[<>:"/\\|?*]')
last_results = list()
model_config = OmegaConf.load(opt.conf)[opt.model]
# The readline completer reads history from the .dream_history file located in the
# output directory specified at the time of script launch. We do not currently support
# changing the history file midstream when the output directory is changed.
completer = get_completer(opt)
output_cntr = completer.get_current_history_length()+1
# os.pathconf is not available on Windows
if hasattr(os, 'pathconf'):
path_max = os.pathconf(opt.outdir, 'PC_PATH_MAX')
name_max = os.pathconf(opt.outdir, 'PC_NAME_MAX')
else:
path_max = 260
name_max = 255
while not done:
operation = 'generate' # default operation, alternative is 'postprocess'
if completer:
completer.set_default_dir(opt.outdir)
try:
command = get_next_command(infile)
except EOFError:
done = True
continue
# skip empty lines
if not command.strip():
continue
if command.startswith(('#', '//')):
continue
if len(command.strip()) == 1 and command.startswith('q'):
done = True
break
if command.startswith('!'):
subcommand = command[1:]
if subcommand.startswith('dream'): # in case a stored prompt still contains the !dream command
command = command.replace('!dream ','',1)
elif subcommand.startswith('fix'):
command = command.replace('!fix ','',1)
operation = 'postprocess'
elif subcommand.startswith('fetch'):
file_path = command.replace('!fetch ','',1)
retrieve_dream_command(opt,file_path,completer)
continue
elif subcommand.startswith('history'):
completer.show_history()
continue
elif subcommand.startswith('search'):
search_str = command.replace('!search ','',1)
completer.show_history(search_str)
continue
elif subcommand.startswith('clear'):
completer.clear_history()
continue
elif re.match('^(\d+)',subcommand):
command_no = re.match('^(\d+)',subcommand).groups()[0]
command = completer.get_line(int(command_no))
completer.set_line(command)
continue
else: # not a recognized subcommand, so give the --help text
command = '-h'
if opt.parse_cmd(command) is None:
continue
if opt.init_img:
try:
if not opt.prompt:
oldargs = metadata_from_png(opt.init_img)
opt.prompt = oldargs.prompt
print(f'>> Retrieved old prompt "{opt.prompt}" from {opt.init_img}')
except (OSError, AttributeError, KeyError):
pass
if len(opt.prompt) == 0:
print('\nTry again with a prompt!')
continue
# width and height are set by model if not specified
if not opt.width:
opt.width = model_config.width
if not opt.height:
opt.height = model_config.height
# retrieve previous value of init image if requested
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
# try to relativize pathnames
for attr in ('init_img','init_mask','init_color','embedding_path'):
if getattr(opt,attr) and not os.path.exists(getattr(opt,attr)):
basename = getattr(opt,attr)
path = os.path.join(opt.outdir,basename)
setattr(opt,attr,path)
# retrieve previous value of seed if requested
if opt.seed is not None and opt.seed < 0:
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
if opt.strength is None:
opt.strength = 0.75 if opt.out_direction is None else 0.83
if opt.with_variations is not None:
opt.with_variations = split_variations(opt.with_variations)
if opt.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
# 39 is the length of '######.##########.##########-##.png', plus two separators and a NUL
subdir = subdir[:(path_max - 39 - len(os.path.abspath(opt.outdir)))]
current_outdir = os.path.join(opt.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:
if not os.path.exists(opt.outdir):
os.makedirs(opt.outdir)
current_outdir = opt.outdir
# Here is where the images are actually generated!
last_results = []
try:
file_writer = PngWriter(current_outdir)
results = [] # list of filename, prompt pairs
grid_images = dict() # seed -> Image, only used if `opt.grid`
prior_variations = opt.with_variations or []
prefix = file_writer.unique_prefix()
def image_writer(image, seed, upscaled=False, first_seed=None, use_prefix=None):
# note the seed is the seed of the current image
# the first_seed is the original seed that noise is added to
# when the -v switch is used to generate variations
nonlocal prior_variations
nonlocal prefix
if use_prefix is not None:
prefix = use_prefix
path = None
if opt.grid:
grid_images[seed] = image
else:
postprocessed = upscaled if upscaled else operation=='postprocess'
filename, formatted_dream_prompt = prepare_image_metadata(
opt,
prefix,
seed,
operation,
prior_variations,
postprocessed,
first_seed
)
path = file_writer.save_image_and_prompt_to_png(
image = image,
dream_prompt = formatted_dream_prompt,
metadata = metadata_dumps(
opt,
seeds = [seed if opt.variation_amount==0 and len(prior_variations)==0 else first_seed],
model_hash = gen.model_hash,
),
name = filename,
)
# update rfc metadata
if operation == 'postprocess':
tool = re.match('postprocess:(\w+)',opt.last_operation).groups()[0]
add_postprocessing_to_metadata(
opt,
opt.prompt,
filename,
tool,
formatted_dream_prompt,
)
if (not postprocessed) or opt.save_original:
# only append to results if we didn't overwrite an earlier output
results.append([path, formatted_dream_prompt])
# so that the seed autocompletes (on linux|mac when -S or --seed specified
if completer:
completer.add_seed(seed)
completer.add_seed(first_seed)
last_results.append([path, seed])
if operation == 'generate':
catch_ctrl_c = infile is None # if running interactively, we catch keyboard interrupts
opt.last_operation='generate'
gen.prompt2image(
image_callback=image_writer,
catch_interrupts=catch_ctrl_c,
**vars(opt)
)
elif operation == 'postprocess':
print(f'>> fixing {opt.prompt}')
opt.last_operation = do_postprocess(gen,opt,image_writer)
if opt.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'
formatted_dream_prompt = opt.dream_prompt_str(seed=first_seed,grid=True,iterations=len(grid_images))
formatted_dream_prompt += f' # {grid_seeds}'
metadata = metadata_dumps(
opt,
seeds = grid_seeds,
model_hash = gen.model_hash
)
path = file_writer.save_image_and_prompt_to_png(
image = grid_img,
dream_prompt = formatted_dream_prompt,
metadata = metadata,
name = filename
)
results = [[path, formatted_dream_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')
output_cntr = write_log(results, log_path ,('txt', 'md'), output_cntr)
print()
if operation == 'postprocess':
completer.add_history(f'!fix {command}')
else:
completer.add_history(command)
print('goodbye!')
def do_postprocess (gen, opt, callback):
file_path = opt.prompt # treat the prompt as the file pathname
if os.path.dirname(file_path) == '': #basename given
file_path = os.path.join(opt.outdir,file_path)
tool=None
if opt.gfpgan_strength > 0:
tool = opt.facetool
elif opt.embiggen:
tool = 'embiggen'
elif opt.upscale:
tool = 'upscale'
elif opt.out_direction:
tool = 'outpaint'
elif opt.outcrop:
tool = 'outcrop'
opt.save_original = True # do not overwrite old image!
opt.last_operation = f'postprocess:{tool}'
try:
gen.apply_postprocessor(
image_path = file_path,
tool = tool,
gfpgan_strength = opt.gfpgan_strength,
codeformer_fidelity = opt.codeformer_fidelity,
save_original = opt.save_original,
upscale = opt.upscale,
out_direction = opt.out_direction,
outcrop = opt.outcrop,
callback = callback,
opt = opt,
)
except OSError:
print(f'** {file_path}: file could not be read')
return
except (KeyError, AttributeError):
print(traceback.format_exc(), file=sys.stderr)
return
return opt.last_operation
def add_postprocessing_to_metadata(opt,original_file,new_file,tool,command):
original_file = original_file if os.path.exists(original_file) else os.path.join(opt.outdir,original_file)
new_file = new_file if os.path.exists(new_file) else os.path.join(opt.outdir,new_file)
meta = retrieve_metadata(original_file)['sd-metadata']
img_data = meta['image']
pp = img_data.get('postprocessing',[]) or []
pp.append(
{
'tool':tool,
'dream_command':command,
}
)
meta['image']['postprocessing'] = pp
write_metadata(new_file,meta)
def prepare_image_metadata(
opt,
prefix,
seed,
operation='generate',
prior_variations=[],
postprocessed=False,
first_seed=None
):
if postprocessed and opt.save_original:
filename = choose_postprocess_name(opt,prefix,seed)
else:
filename = f'{prefix}.{seed}.png'
if opt.variation_amount > 0:
first_seed = first_seed or seed
this_variation = [[seed, opt.variation_amount]]
opt.with_variations = prior_variations + this_variation
formatted_dream_prompt = opt.dream_prompt_str(seed=first_seed)
elif len(prior_variations) > 0:
formatted_dream_prompt = opt.dream_prompt_str(seed=first_seed)
elif operation == 'postprocess':
formatted_dream_prompt = '!fix '+opt.dream_prompt_str(seed=seed)
else:
formatted_dream_prompt = opt.dream_prompt_str(seed=seed)
return filename,formatted_dream_prompt
def choose_postprocess_name(opt,prefix,seed) -> str:
match = re.search('postprocess:(\w+)',opt.last_operation)
if match:
modifier = match.group(1) # will look like "gfpgan", "upscale", "outpaint" or "embiggen"
else:
modifier = 'postprocessed'
counter = 0
filename = None
available = False
while not available:
if counter == 0:
filename = f'{prefix}.{seed}.{modifier}.png'
else:
filename = f'{prefix}.{seed}.{modifier}-{counter:02d}.png'
available = not os.path.exists(os.path.join(opt.outdir,filename))
counter += 1
return filename
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()
if len(command)>0:
print(f'#{command}')
return command
def invoke_ai_web_server_loop(gen, gfpgan, codeformer, esrgan):
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__), '..'))
)
invoke_ai_web_server = InvokeAIWebServer(generate=gen, gfpgan=gfpgan, codeformer=codeformer, esrgan=esrgan)
try:
invoke_ai_web_server.run()
except KeyboardInterrupt:
pass
def split_variations(variations_string) -> list:
# shotgun parsing, woo
parts = []
broken = False # python doesn't have labeled loops...
for part in variations_string.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:
return None
elif len(parts) == 0:
return None
else:
return parts
def retrieve_dream_command(opt,file_path,completer):
'''
Given a full or partial path to a previously-generated image file,
will retrieve and format the dream command used to generate the image,
and pop it into the readline buffer (linux, Mac), or print out a comment
for cut-and-paste (windows)
'''
dir,basename = os.path.split(file_path)
if len(dir) == 0:
path = os.path.join(opt.outdir,basename)
else:
path = file_path
try:
cmd = dream_cmd_from_png(path)
except OSError:
print(f'** {path}: file could not be read')
return
except (KeyError, AttributeError):
print(f'** {path}: file has no metadata')
return
completer.set_line(cmd)
if __name__ == '__main__':
main()

4
scripts/images2prompt.py
View File

@ -1,12 +1,12 @@
#!/usr/bin/env python3
'''This script reads the "Dream" Stable Diffusion prompt embedded in files generated by dream.py'''
'''This script reads the "Invoke" Stable Diffusion prompt embedded in files generated by invoke.py'''
import sys
from PIL import Image,PngImagePlugin
if len(sys.argv) < 2:
print("Usage: file2prompt.py <file1.png> <file2.png> <file3.png>...")
print("This script opens up the indicated dream.py-generated PNG file(s) and prints out the prompt used to generate them.")
print("This script opens up the indicated invoke.py-generated PNG file(s) and prints out the prompt used to generate them.")
exit(-1)
filenames = sys.argv[1:]

573
scripts/invoke.py Normal file
View File

@ -0,0 +1,573 @@
#!/usr/bin/env python3
# Copyright (c) 2022 Lincoln D. Stein (https://github.com/lstein)
import os
import re
import sys
import shlex
import copy
import warnings
import time
import traceback
sys.path.append('.') # corrects a weird problem on Macs
from ldm.invoke.readline import get_completer
from ldm.invoke.args import Args, metadata_dumps, metadata_from_png, dream_cmd_from_png
from ldm.invoke.pngwriter import PngWriter, retrieve_metadata, write_metadata
from ldm.invoke.image_util import make_grid
from ldm.invoke.log import write_log
from omegaconf import OmegaConf
from backend.invoke_ai_web_server import InvokeAIWebServer
def main():
"""Initialize command-line parsers and the diffusion model"""
opt = Args()
args = opt.parse_args()
if not args:
sys.exit(-1)
if args.laion400m:
print('--laion400m flag has been deprecated. Please use --model laion400m instead.')
sys.exit(-1)
if args.weights:
print('--weights argument has been deprecated. Please edit ./configs/models.yaml, and select the weights using --model instead.')
sys.exit(-1)
print('* Initializing, be patient...\n')
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()
# Loading Face Restoration and ESRGAN Modules
try:
gfpgan, codeformer, esrgan = None, None, None
if opt.restore or opt.esrgan:
from ldm.invoke.restoration import Restoration
restoration = Restoration()
if opt.restore:
gfpgan, codeformer = restoration.load_face_restore_models(opt.gfpgan_dir, opt.gfpgan_model_path)
else:
print('>> Face restoration disabled')
if opt.esrgan:
esrgan = restoration.load_esrgan(opt.esrgan_bg_tile)
else:
print('>> Upscaling disabled')
else:
print('>> Face restoration and upscaling disabled')
except (ModuleNotFoundError, ImportError):
print(traceback.format_exc(), file=sys.stderr)
print('>> You may need to install the ESRGAN and/or GFPGAN modules')
# 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
try:
gen = Generate(
conf = opt.conf,
model = opt.model,
sampler_name = opt.sampler_name,
embedding_path = opt.embedding_path,
full_precision = opt.full_precision,
precision = opt.precision,
gfpgan=gfpgan,
codeformer=codeformer,
esrgan=esrgan,
free_gpu_mem=opt.free_gpu_mem,
)
except (FileNotFoundError, IOError, KeyError) as e:
print(f'{e}. Aborting.')
sys.exit(-1)
# make sure the output directory exists
if not os.path.exists(opt.outdir):
os.makedirs(opt.outdir)
# 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
gen.load_model()
# web server loops forever
if opt.web or opt.gui:
invoke_ai_web_server_loop(gen, gfpgan, codeformer, esrgan)
sys.exit(0)
if not infile:
print(
"\n* Initialization done! Awaiting your command (-h for help, 'q' to quit)"
)
main_loop(gen, opt, infile)
# TODO: main_loop() has gotten busy. Needs to be refactored.
def main_loop(gen, opt, infile):
"""prompt/read/execute loop"""
done = False
path_filter = re.compile(r'[<>:"/\\|?*]')
last_results = list()
model_config = OmegaConf.load(opt.conf)[opt.model]
# The readline completer reads history from the .dream_history file located in the
# output directory specified at the time of script launch. We do not currently support
# changing the history file midstream when the output directory is changed.
completer = get_completer(opt)
output_cntr = completer.get_current_history_length()+1
# os.pathconf is not available on Windows
if hasattr(os, 'pathconf'):
path_max = os.pathconf(opt.outdir, 'PC_PATH_MAX')
name_max = os.pathconf(opt.outdir, 'PC_NAME_MAX')
else:
path_max = 260
name_max = 255
while not done:
operation = 'generate' # default operation, alternative is 'postprocess'
if completer:
completer.set_default_dir(opt.outdir)
try:
command = get_next_command(infile)
except EOFError:
done = True
continue
# skip empty lines
if not command.strip():
continue
if command.startswith(('#', '//')):
continue
if len(command.strip()) == 1 and command.startswith('q'):
done = True
break
if command.startswith('!'):
subcommand = command[1:]
if subcommand.startswith('dream'): # in case a stored prompt still contains the !dream command
command = command.replace('!dream ','',1)
elif subcommand.startswith('fix'):
command = command.replace('!fix ','',1)
operation = 'postprocess'
elif subcommand.startswith('fetch'):
file_path = command.replace('!fetch ','',1)
retrieve_dream_command(opt,file_path,completer)
continue
elif subcommand.startswith('history'):
completer.show_history()
continue
elif subcommand.startswith('search'):
search_str = command.replace('!search ','',1)
completer.show_history(search_str)
continue
elif subcommand.startswith('clear'):
completer.clear_history()
continue
elif re.match('^(\d+)',subcommand):
command_no = re.match('^(\d+)',subcommand).groups()[0]
command = completer.get_line(int(command_no))
completer.set_line(command)
continue
else: # not a recognized subcommand, so give the --help text
command = '-h'
if opt.parse_cmd(command) is None:
continue
if opt.init_img:
try:
if not opt.prompt:
oldargs = metadata_from_png(opt.init_img)
opt.prompt = oldargs.prompt
print(f'>> Retrieved old prompt "{opt.prompt}" from {opt.init_img}')
except (OSError, AttributeError, KeyError):
pass
if len(opt.prompt) == 0:
print('\nTry again with a prompt!')
continue
# width and height are set by model if not specified
if not opt.width:
opt.width = model_config.width
if not opt.height:
opt.height = model_config.height
# retrieve previous value of init image if requested
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
# try to relativize pathnames
for attr in ('init_img','init_mask','init_color','embedding_path'):
if getattr(opt,attr) and not os.path.exists(getattr(opt,attr)):
basename = getattr(opt,attr)
path = os.path.join(opt.outdir,basename)
setattr(opt,attr,path)
# retrieve previous value of seed if requested
if opt.seed is not None and opt.seed < 0:
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
if opt.strength is None:
opt.strength = 0.75 if opt.out_direction is None else 0.83
if opt.with_variations is not None:
opt.with_variations = split_variations(opt.with_variations)
if opt.prompt_as_dir and operation == 'generate':
# sanitize the prompt to a valid folder name
subdir = path_filter.sub('_', opt.prompt)[:name_max].rstrip(' .')
# truncate path to maximum allowed length
# 39 is the length of '######.##########.##########-##.png', plus two separators and a NUL
subdir = subdir[:(path_max - 39 - len(os.path.abspath(opt.outdir)))]
current_outdir = os.path.join(opt.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:
if not os.path.exists(opt.outdir):
os.makedirs(opt.outdir)
current_outdir = opt.outdir
# write out the history at this point
if operation == 'postprocess':
completer.add_history(f'!fix {command}')
else:
completer.add_history(command)
# Here is where the images are actually generated!
last_results = []
try:
file_writer = PngWriter(current_outdir)
results = [] # list of filename, prompt pairs
grid_images = dict() # seed -> Image, only used if `opt.grid`
prior_variations = opt.with_variations or []
prefix = file_writer.unique_prefix()
def image_writer(image, seed, upscaled=False, first_seed=None, use_prefix=None):
# note the seed is the seed of the current image
# the first_seed is the original seed that noise is added to
# when the -v switch is used to generate variations
nonlocal prior_variations
nonlocal prefix
if use_prefix is not None:
prefix = use_prefix
path = None
if opt.grid:
grid_images[seed] = image
else:
postprocessed = upscaled if upscaled else operation=='postprocess'
filename, formatted_dream_prompt = prepare_image_metadata(
opt,
prefix,
seed,
operation,
prior_variations,
postprocessed,
first_seed
)
path = file_writer.save_image_and_prompt_to_png(
image = image,
dream_prompt = formatted_dream_prompt,
metadata = metadata_dumps(
opt,
seeds = [seed if opt.variation_amount==0 and len(prior_variations)==0 else first_seed],
model_hash = gen.model_hash,
),
name = filename,
)
# update rfc metadata
if operation == 'postprocess':
tool = re.match('postprocess:(\w+)',opt.last_operation).groups()[0]
add_postprocessing_to_metadata(
opt,
opt.prompt,
filename,
tool,
formatted_dream_prompt,
)
if (not postprocessed) or opt.save_original:
# only append to results if we didn't overwrite an earlier output
results.append([path, formatted_dream_prompt])
# so that the seed autocompletes (on linux|mac when -S or --seed specified
if completer:
completer.add_seed(seed)
completer.add_seed(first_seed)
last_results.append([path, seed])
if operation == 'generate':
catch_ctrl_c = infile is None # if running interactively, we catch keyboard interrupts
opt.last_operation='generate'
gen.prompt2image(
image_callback=image_writer,
catch_interrupts=catch_ctrl_c,
**vars(opt)
)
elif operation == 'postprocess':
print(f'>> fixing {opt.prompt}')
opt.last_operation = do_postprocess(gen,opt,image_writer)
if opt.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'
formatted_dream_prompt = opt.dream_prompt_str(seed=first_seed,grid=True,iterations=len(grid_images))
formatted_dream_prompt += f' # {grid_seeds}'
metadata = metadata_dumps(
opt,
seeds = grid_seeds,
model_hash = gen.model_hash
)
path = file_writer.save_image_and_prompt_to_png(
image = grid_img,
dream_prompt = formatted_dream_prompt,
metadata = metadata,
name = filename
)
results = [[path, formatted_dream_prompt]]
except AssertionError as e:
print(e)
continue
except OSError as e:
print(e)
continue
print('Outputs:')
log_path = os.path.join(current_outdir, 'invoke_log')
output_cntr = write_log(results, log_path ,('txt', 'md'), output_cntr)
print()
print('goodbye!')
def do_postprocess (gen, opt, callback):
file_path = opt.prompt # treat the prompt as the file pathname
if os.path.dirname(file_path) == '': #basename given
file_path = os.path.join(opt.outdir,file_path)
tool=None
if opt.gfpgan_strength > 0:
tool = opt.facetool
elif opt.embiggen:
tool = 'embiggen'
elif opt.upscale:
tool = 'upscale'
elif opt.out_direction:
tool = 'outpaint'
elif opt.outcrop:
tool = 'outcrop'
opt.save_original = True # do not overwrite old image!
opt.last_operation = f'postprocess:{tool}'
try:
gen.apply_postprocessor(
image_path = file_path,
tool = tool,
gfpgan_strength = opt.gfpgan_strength,
codeformer_fidelity = opt.codeformer_fidelity,
save_original = opt.save_original,
upscale = opt.upscale,
out_direction = opt.out_direction,
outcrop = opt.outcrop,
callback = callback,
opt = opt,
)
except OSError:
print(traceback.format_exc(), file=sys.stderr)
print(f'** {file_path}: file could not be read')
return
except (KeyError, AttributeError):
print(traceback.format_exc(), file=sys.stderr)
return
return opt.last_operation
def add_postprocessing_to_metadata(opt,original_file,new_file,tool,command):
original_file = original_file if os.path.exists(original_file) else os.path.join(opt.outdir,original_file)
new_file = new_file if os.path.exists(new_file) else os.path.join(opt.outdir,new_file)
meta = retrieve_metadata(original_file)['sd-metadata']
img_data = meta['image']
pp = img_data.get('postprocessing',[]) or []
pp.append(
{
'tool':tool,
'dream_command':command,
}
)
meta['image']['postprocessing'] = pp
write_metadata(new_file,meta)
def prepare_image_metadata(
opt,
prefix,
seed,
operation='generate',
prior_variations=[],
postprocessed=False,
first_seed=None
):
if postprocessed and opt.save_original:
filename = choose_postprocess_name(opt,prefix,seed)
else:
filename = f'{prefix}.{seed}.png'
if opt.variation_amount > 0:
first_seed = first_seed or seed
this_variation = [[seed, opt.variation_amount]]
opt.with_variations = prior_variations + this_variation
formatted_dream_prompt = opt.dream_prompt_str(seed=first_seed)
elif len(prior_variations) > 0:
formatted_dream_prompt = opt.dream_prompt_str(seed=first_seed)
elif operation == 'postprocess':
formatted_dream_prompt = '!fix '+opt.dream_prompt_str(seed=seed)
else:
formatted_dream_prompt = opt.dream_prompt_str(seed=seed)
return filename,formatted_dream_prompt
def choose_postprocess_name(opt,prefix,seed) -> str:
match = re.search('postprocess:(\w+)',opt.last_operation)
if match:
modifier = match.group(1) # will look like "gfpgan", "upscale", "outpaint" or "embiggen"
else:
modifier = 'postprocessed'
counter = 0
filename = None
available = False
while not available:
if counter == 0:
filename = f'{prefix}.{seed}.{modifier}.png'
else:
filename = f'{prefix}.{seed}.{modifier}-{counter:02d}.png'
available = not os.path.exists(os.path.join(opt.outdir,filename))
counter += 1
return filename
def get_next_command(infile=None) -> str: # command string
if infile is None:
command = input('invoke> ')
else:
command = infile.readline()
if not command:
raise EOFError
else:
command = command.strip()
if len(command)>0:
print(f'#{command}')
return command
def invoke_ai_web_server_loop(gen, gfpgan, codeformer, esrgan):
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__), '..'))
)
invoke_ai_web_server = InvokeAIWebServer(generate=gen, gfpgan=gfpgan, codeformer=codeformer, esrgan=esrgan)
try:
invoke_ai_web_server.run()
except KeyboardInterrupt:
pass
def split_variations(variations_string) -> list:
# shotgun parsing, woo
parts = []
broken = False # python doesn't have labeled loops...
for part in variations_string.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:
return None
elif len(parts) == 0:
return None
else:
return parts
def retrieve_dream_command(opt,file_path,completer):
'''
Given a full or partial path to a previously-generated image file,
will retrieve and format the dream command used to generate the image,
and pop it into the readline buffer (linux, Mac), or print out a comment
for cut-and-paste (windows)
'''
dir,basename = os.path.split(file_path)
if len(dir) == 0:
path = os.path.join(opt.outdir,basename)
else:
path = file_path
try:
cmd = dream_cmd_from_png(path)
except OSError:
print(f'** {path}: file could not be read')
return
except (KeyError, AttributeError):
print(f'** {path}: file has no metadata')
return
completer.set_line(cmd)
if __name__ == '__main__':
main()

2
scripts/orig_scripts/img2img.py
View File

@ -18,7 +18,7 @@ from pytorch_lightning import seed_everything
from ldm.util import instantiate_from_config
from ldm.models.diffusion.ddim import DDIMSampler
from ldm.models.diffusion.plms import PLMSSampler
from ldm.dream.devices import choose_torch_device
from ldm.invoke.devices import choose_torch_device
def chunk(it, size):

2
scripts/orig_scripts/inpaint.py
View File

@ -6,7 +6,7 @@ import numpy as np
import torch
from main import instantiate_from_config
from ldm.models.diffusion.ddim import DDIMSampler
from ldm.dream.devices import choose_torch_device
from ldm.invoke.devices import choose_torch_device
def make_batch(image, mask, device):
image = np.array(Image.open(image).convert("RGB"))

2
scripts/orig_scripts/txt2img.py
View File

@ -18,7 +18,7 @@ import torch.nn as nn
from ldm.util import instantiate_from_config
from ldm.models.diffusion.ddim import DDIMSampler
from ldm.models.diffusion.plms import PLMSSampler
from ldm.dream.devices import choose_torch_device
from ldm.invoke.devices import choose_torch_device
def chunk(it, size):
it = iter(it)

56
scripts/preload_models.py
View File

@ -15,13 +15,13 @@ import urllib.request
transformers.logging.set_verbosity_error()
# this will preload the Bert tokenizer fles
print('preloading bert tokenizer...')
print('preloading bert tokenizer...', end='')
tokenizer = BertTokenizerFast.from_pretrained('bert-base-uncased')
print('...success')
# this will download requirements for Kornia
print('preloading Kornia requirements (ignore the deprecation warnings)...')
print('preloading Kornia requirements...', end='')
with warnings.catch_warnings():
warnings.filterwarnings('ignore', category=DeprecationWarning)
import kornia
@ -29,12 +29,12 @@ print('...success')
version = 'openai/clip-vit-large-patch14'
print('preloading CLIP model (Ignore the deprecation warnings)...')
print('preloading CLIP model...',end='')
sys.stdout.flush()
tokenizer = CLIPTokenizer.from_pretrained(version)
transformer = CLIPTextModel.from_pretrained(version)
print('\n\n...success')
print('...success')
# In the event that the user has installed GFPGAN and also elected to use
# RealESRGAN, this will attempt to download the model needed by RealESRGANer
@ -47,7 +47,7 @@ except ModuleNotFoundError:
pass
if gfpgan:
print('Loading models from RealESRGAN and facexlib')
print('Loading models from RealESRGAN and facexlib...',end='')
try:
from realesrgan.archs.srvgg_arch import SRVGGNetCompact
from facexlib.utils.face_restoration_helper import FaceRestoreHelper
@ -65,27 +65,41 @@ if gfpgan:
print('Error loading ESRGAN:')
print(traceback.format_exc())
try:
import urllib.request
model_url = 'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth'
model_dest = 'src/gfpgan/experiments/pretrained_models/GFPGANv1.4.pth'
print('Loading models from GFPGAN')
import urllib.request
for model in (
[
'https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth',
'src/gfpgan/experiments/pretrained_models/GFPGANv1.4.pth'
],
[
'https://github.com/xinntao/facexlib/releases/download/v0.1.0/detection_Resnet50_Final.pth',
'./gfpgan/weights/detection_Resnet50_Final.pth'
],
[
'https://github.com/xinntao/facexlib/releases/download/v0.2.2/parsing_parsenet.pth',
'./gfpgan/weights/parsing_parsenet.pth'
],
):
model_url,model_dest = model
try:
if not os.path.exists(model_dest):
print(f'Downloading gfpgan model file {model_url}...',end='')
os.makedirs(os.path.dirname(model_dest), exist_ok=True)
urllib.request.urlretrieve(model_url,model_dest)
print('...success')
except Exception:
import traceback
print('Error loading GFPGAN:')
print(traceback.format_exc())
if not os.path.exists(model_dest):
print('downloading gfpgan model file...')
urllib.request.urlretrieve(model_url,model_dest)
except Exception:
import traceback
print('Error loading GFPGAN:')
print(traceback.format_exc())
print('...success')
print('preloading CodeFormer model file...')
print('preloading CodeFormer model file...',end='')
try:
import urllib.request
model_url = 'https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth'
model_dest = 'ldm/dream/restoration/codeformer/weights/codeformer.pth'
model_dest = 'ldm/invoke/restoration/codeformer/weights/codeformer.pth'
if not os.path.exists(model_dest):
print('downloading codeformer model file...')
print('Downloading codeformer model file...')
os.makedirs(os.path.dirname(model_dest), exist_ok=True)
urllib.request.urlretrieve(model_url,model_dest)
except Exception:

4
scripts/sd-metadata.py
View File

@ -2,11 +2,11 @@
import sys
import json
from ldm.dream.pngwriter import retrieve_metadata
from ldm.invoke.pngwriter import retrieve_metadata
if len(sys.argv) < 2:
print("Usage: file2prompt.py <file1.png> <file2.png> <file3.png>...")
print("This script opens up the indicated dream.py-generated PNG file(s) and prints out their metadata.")
print("This script opens up the indicated invoke.py-generated PNG file(s) and prints out their metadata.")
exit(-1)
filenames = sys.argv[1:]

2
server/application.py
View File

@ -10,7 +10,7 @@ from flask_cors import CORS
from flask_socketio import SocketIO
from omegaconf import OmegaConf
from dependency_injector.wiring import inject, Provide
from ldm.dream.args import Args
from ldm.invoke.args import Args
from server import views
from server.containers import Container
from server.services import GeneratorService, SignalService

8
server/services.py
View File

@ -12,12 +12,12 @@ import shlex
from threading import Thread
import time
from flask_socketio import SocketIO, join_room, leave_room
from ldm.dream.args import Args
from ldm.dream.generator import embiggen
from ldm.invoke.args import Args
from ldm.invoke.generator import embiggen
from PIL import Image
from ldm.dream.pngwriter import PngWriter
from ldm.dream.server import CanceledException
from ldm.invoke.pngwriter import PngWriter
from ldm.invoke.server import CanceledException
from ldm.generate import Generate
from server.models import DreamResult, JobRequest, PaginatedItems, ProgressType, Signal

6
setup.py
View File

@ -1,8 +1,8 @@
from setuptools import setup, find_packages
setup(
name='stable-diffusion',
version='1.15.0-dev',
name='invoke-ai',
version='2.0.0',
description='',
packages=find_packages(),
install_requires=[
@ -10,4 +10,4 @@ setup(
'numpy',
'tqdm',
],
)
)