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

more updates to many docs, including:

Browse Source 
- better readability in dark mode since color change
- better looking changelog
- fix images which where not loading
- also center most of the images
- fix some syntax errors like
  - headlines ending with a colon
  - codeblocks with wrong fences
  - codeblocks without shell
- update conda prompts from ldm to invokeai
- ....
This commit is contained in:
mauwii 2022-10-11 22:10:35 +02:00 committed by Lincoln Stein
parent 8ea07f3bb0
commit 1c687d6d03
14 changed files with 253 additions and 193 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
docs/CHANGELOG.md
View File

@ -4,7 +4,7 @@ title: Changelog
# :octicons-log-16: **Changelog** # :octicons-log-16: **Changelog**
- v2.0.0 (9 October 2022) ## v2.0.0 <small>(9 October 2022)</small>
- `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains - `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains
for backward compatibility. for backward compatibility.
@ -31,7 +31,7 @@ title: Changelog
- Deprecated `--full_precision` / `-F`. Simply omit it and `invoke.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`. configure. To switch away from auto use the new flag like `--precision=float32`.
- v1.14 (11 September 2022) ## v1.14 <small>(11 September 2022)</small>
- Memory optimizations for small-RAM cards. 512x512 now possible on 4 GB GPUs. - Memory optimizations for small-RAM cards. 512x512 now possible on 4 GB GPUs.
- Full support for Apple hardware with M1 or M2 chips. - Full support for Apple hardware with M1 or M2 chips.
@ -41,7 +41,7 @@ title: Changelog
- Improved web server GUI. - Improved web server GUI.
- Lots of code and documentation cleanups. - Lots of code and documentation cleanups.
- v1.13 (3 September 2022 ## v1.13 <small>(3 September 2022)</small>
- Support image variations (see [VARIATIONS](features/VARIATIONS.md) - Support image variations (see [VARIATIONS](features/VARIATIONS.md)
([Kevin Gibbons](https://github.com/bakkot) and many contributors and reviewers) ([Kevin Gibbons](https://github.com/bakkot) and many contributors and reviewers)
@ -61,7 +61,7 @@ title: Changelog
--- ---
## v1.12 (28 August 2022) ## v1.12 <small>(28 August 2022)</small>
- Improved file handling, including ability to read prompts from standard input. - Improved file handling, including ability to read prompts from standard input.
(kudos to [Yunsaki](https://github.com/yunsaki) (kudos to [Yunsaki](https://github.com/yunsaki)
@ -75,7 +75,7 @@ title: Changelog
--- ---
## v1.11 (26 August 2022) ## v1.11 <small>(26 August 2022)</small>
- NEW FEATURE: Support upscaling and face enhancement using the GFPGAN module. (kudos to [Oceanswave](https://github.com/Oceanswave) - NEW FEATURE: Support upscaling and face enhancement using the GFPGAN module. (kudos to [Oceanswave](https://github.com/Oceanswave)
- 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. - 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.
@ -88,13 +88,13 @@ title: Changelog
--- ---
## v1.10 (25 August 2022) ## v1.10 <small>(25 August 2022)</small>
- A barebones but fully functional interactive web server for online generation of txt2img and img2img. - A barebones but fully functional interactive web server for online generation of txt2img and img2img.
--- ---
## v1.09 (24 August 2022) ## v1.09 <small>(24 August 2022)</small>
- A new -v option allows you to generate multiple variants of an initial image - A new -v option allows you to generate multiple variants of an initial image
in img2img mode. (kudos to [Oceanswave](https://github.com/Oceanswave). [ in img2img mode. (kudos to [Oceanswave](https://github.com/Oceanswave). [
@ -104,7 +104,7 @@ title: Changelog
--- ---
## v1.08 (24 August 2022) ## v1.08 <small>(24 August 2022)</small>
- Escape single quotes on the invoke> command before trying to parse. This avoids - Escape single quotes on the invoke> command before trying to parse. This avoids
parse errors. parse errors.
@ -115,7 +115,7 @@ title: Changelog
--- ---
## v1.07 (23 August 2022) ## v1.07 <small>(23 August 2022)</small>
- Image filenames will now never fill gaps in the sequence, but will be assigned the - Image filenames will now never fill gaps in the sequence, but will be assigned the
next higher name in the chosen directory. This ensures that the alphabetic and chronological next higher name in the chosen directory. This ensures that the alphabetic and chronological
@ -123,14 +123,14 @@ title: Changelog
--- ---
## v1.06 (23 August 2022) ## v1.06 <small>(23 August 2022)</small>
- Added weighted prompt support contributed by [xraxra](https://github.com/xraxra) - Added weighted prompt support contributed by [xraxra](https://github.com/xraxra)
- Example of using weighted prompts to tweak a demonic figure contributed by [bmaltais](https://github.com/bmaltais) - Example of using weighted prompts to tweak a demonic figure contributed by [bmaltais](https://github.com/bmaltais)
--- ---
## v1.05 (22 August 2022 - after the drop) ## v1.05 <small>(22 August 2022 - after the drop)</small>
- Filenames now use the following formats: - Filenames now use the following formats:
000010.95183149.png -- Two files produced by the same command (e.g. -n2), 000010.95183149.png -- Two files produced by the same command (e.g. -n2),
@ -148,7 +148,7 @@ title: Changelog
--- ---
## v1.04 (22 August 2022 - after the drop) ## v1.04 <small>(22 August 2022 - after the drop)</small>
- Updated README to reflect installation of the released weights. - Updated README to reflect installation of the released weights.
- Suppressed very noisy and inconsequential warning when loading the frozen CLIP - Suppressed very noisy and inconsequential warning when loading the frozen CLIP
@ -156,14 +156,14 @@ title: Changelog
--- ---
## v1.03 (22 August 2022) ## v1.03 <small>(22 August 2022)</small>
- The original txt2img and img2img scripts from the CompViz repository have been moved into - The original txt2img and img2img scripts from the CompViz repository have been moved into
a subfolder named "orig_scripts", to reduce confusion. a subfolder named "orig_scripts", to reduce confusion.
--- ---
## v1.02 (21 August 2022) ## v1.02 <small>(21 August 2022)</small>
- A copy of the prompt and all of its switches and options is now stored in the corresponding - A copy of the prompt and all of its switches and options is now stored in the corresponding
image in a tEXt metadata field named "Dream". You can read the prompt using scripts/images2prompt.py, image in a tEXt metadata field named "Dream". You can read the prompt using scripts/images2prompt.py,
@ -172,7 +172,7 @@ title: Changelog
--- ---
## v1.01 (21 August 2022) ## v1.01 <small>(21 August 2022)</small>
- added k_lms sampling. - added k_lms sampling.
**Please run "conda env update" to load the k_lms dependencies!!** **Please run "conda env update" to load the k_lms dependencies!!**

4
docs/features/CLI.md
View File

@ -34,7 +34,7 @@ The script is confirmed to work on Linux, Windows and Mac systems.
currently rudimentary, but a much better replacement is on its way. currently rudimentary, but a much better replacement is on its way.
```bash ```bash
(ldm) ~/stable-diffusion$ python3 ./scripts/invoke.py (invokeai) ~/stable-diffusion$ python3 ./scripts/invoke.py
* Initializing, be patient... * Initializing, be patient...
Loading model from models/ldm/text2img-large/model.ckpt Loading model from models/ldm/text2img-large/model.ckpt
(...more initialization messages...) (...more initialization messages...)
@ -51,7 +51,7 @@ invoke> "there's a fly in my soup" -n6 -g
invoke> q invoke> q
# this shows how to retrieve the prompt stored in the saved image's metadata # 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 (invokeai) ~/stable-diffusion$ python ./scripts/images2prompt.py outputs/img_samples/*.png
00009.png: "ashley judd riding a camel" -s150 -S 416354203 00009.png: "ashley judd riding a camel" -s150 -S 416354203
00010.png: "ashley judd riding a camel" -s150 -S 1362479620 00010.png: "ashley judd riding a camel" -s150 -S 1362479620
00011.png: "there's a fly in my soup" -n6 -g -S 2685670268 00011.png: "there's a fly in my soup" -n6 -g -S 2685670268

12
docs/features/INPAINTING.md
View File

@ -50,28 +50,28 @@ We are hoping to get rid of the need for this workaround in an upcoming release.
1. Open image in Photoshop 1. Open image in Photoshop
![step1](../assets/step1.png) <div align="center" markdown>![step1](../assets/step1.png)</div>
2. Use any of the selection tools (Marquee, Lasso, or Wand) to select the area you desire to inpaint. 2. Use any of the selection tools (Marquee, Lasso, or Wand) to select the area you desire to inpaint.
![step2](../assets/step2.png) <div align="center" markdown>![step2](../assets/step2.png)</div>
3. Because we'll be applying a mask over the area we want to preserve, you should now select the inverse by using the ++shift+ctrl+i++ shortcut, or right clicking and using the "Select Inverse" option. 3. Because we'll be applying a mask over the area we want to preserve, you should now select the inverse by using the ++shift+ctrl+i++ shortcut, or right clicking and using the "Select Inverse" option.
4. You'll now create a mask by selecting the image layer, and Masking the selection. Make sure that you don't delete any of the undrlying image, or your inpainting results will be dramatically impacted. 4. You'll now create a mask by selecting the image layer, and Masking the selection. Make sure that you don't delete any of the undrlying image, or your inpainting results will be dramatically impacted.
![step4](../assets/step4.png) <div align="center" markdown>![step4](../assets/step4.png)</div>
5. Make sure to hide any background layers that are present. You should see the mask applied to your image layer, and the image on your canvas should display the checkered background. 5. Make sure to hide any background layers that are present. You should see the mask applied to your image layer, and the image on your canvas should display the checkered background.
![step5](../assets/step5.png) <div align="center" markdown>![step5](../assets/step5.png)</div>
6. Save the image as a transparent PNG by using `File`-->`Save a Copy` from the menu bar, or by using the keyboard shortcut ++alt+ctrl+s++ 6. Save the image as a transparent PNG by using `File`-->`Save a Copy` from the menu bar, or by using the keyboard shortcut ++alt+ctrl+s++
![step6](../assets/step6.png) <div align="center" markdown>![step6](../assets/step6.png)</div>
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! 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) <div align="center" markdown>![step7](../assets/step7.png)</div>
8. In the export dialogue, Make sure the "Save colour values from transparent pixels" checkbox is selected. 8. In the export dialogue, Make sure the "Save colour values from transparent pixels" checkbox is selected.

18
docs/features/OTHER.md
View File

@ -6,11 +6,13 @@ title: Others
## **Google Colab** ## **Google Colab**
Stable Diffusion AI Notebook: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/lstein/stable-diffusion/blob/main/notebooks/Stable_Diffusion_AI_Notebook.ipynb) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg){ align="right" }](https://colab.research.google.com/github/lstein/stable-diffusion/blob/main/notebooks/Stable_Diffusion_AI_Notebook.ipynb)
Open and follow instructions to use an isolated environment running Dream. Open and follow instructions to use an isolated environment running Dream.
Output Example: ![Colab Notebook](../assets/colab_notebook.png) Output Example:
![Colab Notebook](../assets/colab_notebook.png)
--- ---
@ -29,12 +31,12 @@ invoke> "pond garden with lotus by claude monet" --seamless -s100 -n4
## **Shortcuts: Reusing Seeds** ## **Shortcuts: Reusing Seeds**
Since it is so common to reuse seeds while refining a prompt, there is now a shortcut as of version Since it is so common to reuse seeds while refining a prompt, there is now a shortcut as of version
1.11. Provide a `**-S**` (or `**--seed**`) switch of `-1` to use the seed of the most recent image 1.11. Provide a `-S` (or `--seed`) switch of `-1` to use the seed of the most recent image
generated. If you produced multiple images with the `**-n**` switch, then you can go back further generated. If you produced multiple images with the `-n` switch, then you can go back further
using -2, -3, etc. up to the first image generated by the previous command. Sorry, but you can't go using `-2`, `-3`, etc. up to the first image generated by the previous command. Sorry, but you can't go
back further than one command. back further than one command.
Here's an example of using this to do a quick refinement. It also illustrates using the new `**-G**` Here's an example of using this to do a quick refinement. It also illustrates using the new `-G`
switch to turn on upscaling and face enhancement (see previous section): switch to turn on upscaling and face enhancement (see previous section):
```bash ```bash
@ -54,7 +56,7 @@ outputs/img-samples/000040.3498014304.png: "a cute child playing hopscotch" -G1.
## **Weighted Prompts** ## **Weighted Prompts**
You may weight different sections of the prompt to tell the sampler to attach different levels of 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 priority to them, by adding `:<percent>` to the end of the section you wish to up- or downweight. For
example consider this prompt: example consider this prompt:
```bash ```bash
@ -122,7 +124,7 @@ internet. In the following runs, it will load up the cached versions of the requ
`.cache` directory of the system. `.cache` directory of the system.
```bash ```bash
(ldm) ~/stable-diffusion$ python3 ./scripts/preload_models.py (invokeai) ~/stable-diffusion$ python3 ./scripts/preload_models.py
preloading bert tokenizer... preloading bert tokenizer...
Downloading: 100%|██████████████████████████████████| 28.0/28.0 [00:00<00:00, 49.3kB/s] Downloading: 100%|██████████████████████████████████| 28.0/28.0 [00:00<00:00, 49.3kB/s]
Downloading: 100%|██████████████████████████████████| 226k/226k [00:00<00:00, 2.79MB/s] Downloading: 100%|██████████████████████████████████| 226k/226k [00:00<00:00, 2.79MB/s]

35
docs/features/OUTPAINTING.md
View File

@ -25,14 +25,16 @@ implementations.
Consider this image: Consider this image:
<div align="center" markdown>
![curly_woman](../assets/outpainting/curly.png) ![curly_woman](../assets/outpainting/curly.png)
</div>
Pretty nice, but it's annoying that the top of her head is cut 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! off. She's also a bit off center. Let's fix that!
~~~~ ```bash
invoke> !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 This is saying to apply the `outcrop` extension by extending the top
of the image by 64 pixels, and the right of the image by the same of the image by 64 pixels, and the right of the image by the same
@ -42,7 +44,9 @@ specify any number of pixels to extend. You can also abbreviate
The result looks like this: The result looks like this:
<div align="center" markdown>
![curly_woman_outcrop](../assets/outpainting/curly-outcrop.png) ![curly_woman_outcrop](../assets/outpainting/curly-outcrop.png)
</div>
The new image is actually slightly larger than the original (576x576, The new image is actually slightly larger than the original (576x576,
because 64 pixels were added to the top and right sides.) because 64 pixels were added to the top and right sides.)
@ -66,33 +70,36 @@ The `outpaint` extension does the same thing, but with subtle
differences. Starting with the same image, here is how we would add an differences. Starting with the same image, here is how we would add an
additional 64 pixels to the top of the image: additional 64 pixels to the top of the image:
~~~ ```bash
invoke> !fix images/curly.png --out_direction top 64 invoke> !fix images/curly.png --out_direction top 64
~~~ ```
(you can abbreviate `--out_direction` as `-D`. (you can abbreviate `--out_direction` as `-D`.
The result is shown here: The result is shown here:
<div align="center" markdown>
![curly_woman_outpaint](../assets/outpainting/curly-outpaint.png) ![curly_woman_outpaint](../assets/outpainting/curly-outpaint.png)
</div>
Although the effect is similar, there are significant differences from Although the effect is similar, there are significant differences from
outcropping: outcropping:
1. You can only specify one direction to extend at a time. - You can only specify one direction to extend at a time.
2. The image is **not** resized. Instead, the image is shifted by the specified - The image is **not** resized. Instead, the image is shifted by the specified
number of pixels. If you look carefully, you'll see that less of the lady's number of pixels. If you look carefully, you'll see that less of the lady's
torso is visible in the image. torso is visible in the image.
3. Because the image dimensions remain the same, there's no rounding - Because the image dimensions remain the same, there's no rounding
to multiples of 64. to multiples of 64.
4. Attempting to outpaint larger areas will frequently give rise to ugly - Attempting to outpaint larger areas will frequently give rise to ugly
ghosting effects. ghosting effects.
5. For best results, try increasing the step number. - For best results, try increasing the step number.
6. If you don't specify a pixel value in -D, it will default to half - If you don't specify a pixel value in `-D`, it will default to half
of the whole image, which is likely not what you want. of the whole image, which is likely not what you want.
Neither `outpaint` nor `outcrop` are perfect, but we continue to tune !!! tip
and improve them. If one doesn't work, try the other. You may also
wish to experiment with other `img2img` arguments, such as `-C`, `-f`
and `-s`.
Neither `outpaint` nor `outcrop` are perfect, but we continue to tune
and improve them. If one doesn't work, try the other. You may also
wish to experiment with other `img2img` arguments, such as `-C`, `-f`
and `-s`.

16
docs/features/POSTPROCESS.md
View File

@ -34,9 +34,9 @@ work. These are loaded when you run `scripts/preload_models.py`. If
GFPAN is failing with an error, please run the following from the GFPAN is failing with an error, please run the following from the
InvokeAI directory: InvokeAI directory:
~~~~ ```bash
python scripts/preload_models.py python scripts/preload_models.py
~~~~ ```
If you do not run this script in advance, the GFPGAN module will attempt 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 to download the models files the first time you try to perform facial
@ -89,13 +89,13 @@ too.
### Example Usage ### Example Usage
```bash ```bash
invoke> 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: This also works with img2img:
```bash ```bash
invoke> 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 !!! note
@ -129,14 +129,14 @@ You can use `-ft` prompt argument to swap between CodeFormer and the
default GFPGAN. The above mentioned `-G` prompt argument will allow default GFPGAN. The above mentioned `-G` prompt argument will allow
you to control the strength of the restoration effect. you to control the strength of the restoration effect.
### Usage: ### Usage
The following command will perform face restoration with CodeFormer instead of The following command will perform face restoration with CodeFormer instead of
the default gfpgan. the default gfpgan.
`<prompt> -G 0.8 -ft codeformer` `<prompt> -G 0.8 -ft codeformer`
### Other Options: ### Other Options
- `-cf` - cf or CodeFormer Fidelity takes values between `0` and `1`. 0 produces - `-cf` - cf or CodeFormer Fidelity takes values between `0` and `1`. 0 produces
high quality results but low accuracy and 1 produces lower quality results but high quality results but low accuracy and 1 produces lower quality results but
@ -162,7 +162,7 @@ previously-generated file. Just use the syntax `!fix path/to/file.png
2X for a file named `./outputs/img-samples/000044.2945021133.png`, 2X for a file named `./outputs/img-samples/000044.2945021133.png`,
just run: just run:
``` ```bash
invoke> !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
``` ```
@ -170,7 +170,7 @@ A new file named `000044.2945021133.fixed.png` will be created in the output
directory. Note that the `!fix` command does not replace the original file, directory. Note that the `!fix` command does not replace the original file,
unlike the behavior at generate time. unlike the behavior at generate time.
### Disabling: ### Disabling
If, for some reason, you do not wish to load the GFPGAN and/or ESRGAN libraries, If, for some reason, you do not wish to load the GFPGAN and/or ESRGAN libraries,
you can disable them on the invoke.py command line with the `--no_restore` and you can disable them on the invoke.py command line with the `--no_restore` and

42
docs/features/PROMPTS.md
View File

@ -2,7 +2,7 @@
title: Prompting Features title: Prompting Features
--- ---
# :octicons-command-palette-24: Prompting Features # :octicons-command-palette-16: Prompting Features
## **Reading Prompts from a File** ## **Reading Prompts from a File**
@ -19,14 +19,15 @@ innovative packaging for a squid's dinner -S137038382
Then pass this file's name to `invoke.py` when you invoke it: Then pass this file's name to `invoke.py` when you invoke it:
```bash ```bash
(ldm) ~/stable-diffusion$ python3 scripts/invoke.py --from_file "path/to/prompts.txt" (invokeai) ~/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 `-`: You may read a series of prompts from standard input by providing a filename of `-`:
```bash ```bash
(ldm) ~/stable-diffusion$ echo "a beautiful day" | python3 scripts/invoke.py --from_file - (invokeai) ~/stable-diffusion$ echo "a beautiful day" | python3 scripts/invoke.py --from_file -
``` ```
--- ---
## **Negative and Unconditioned Prompts** ## **Negative and Unconditioned Prompts**
@ -34,7 +35,7 @@ You may read a series of prompts from standard input by providing a filename of
Any words between a pair of square brackets will instruct Stable Any words between a pair of square brackets will instruct Stable
Diffusion to attempt to ban the concept from the generated image. Diffusion to attempt to ban the concept from the generated image.
```bash ```text
this is a test prompt [not really] to make you understand [cool] how this works. this is a test prompt [not really] to make you understand [cool] how this works.
``` ```
@ -46,25 +47,33 @@ original prompt:
`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180` `#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
<div align="center" markdown>
![step1](../assets/negative_prompt_walkthru/step1.png) ![step1](../assets/negative_prompt_walkthru/step1.png)
</div>
That image has a woman, so if we want the horse without a rider, we can influence the image not to have a woman by putting [woman] in the prompt, like this: That image has a woman, so if we want the horse without a rider, we can influence the image not to have a woman by putting [woman] in the prompt, like this:
`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180` `#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
<div align="center" markdown>
![step2](../assets/negative_prompt_walkthru/step2.png) ![step2](../assets/negative_prompt_walkthru/step2.png)
</div>
That's nice - but say we also don't want the image to be quite so blue. We can add "blue" to the list of negative prompts, so it's now [woman blue]: That's nice - but say we also don't want the image to be quite so blue. We can add "blue" to the list of negative prompts, so it's now [woman blue]:
`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180` `#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
<div align="center" markdown>
![step3](../assets/negative_prompt_walkthru/step3.png) ![step3](../assets/negative_prompt_walkthru/step3.png)
</div>
Getting close - but there's no sense in having a saddle when our horse doesn't have a rider, so we'll add one more negative prompt: [woman blue saddle]. Getting close - but there's no sense in having a saddle when our horse doesn't have a rider, so we'll add one more negative prompt: [woman blue saddle].
`#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180` `#!bash "A fantastical translucent poney made of water and foam, ethereal, radiant, hyperalism, scottish folklore, digital painting, artstation, concept art, smooth, 8 k frostbite 3 engine, ultra detailed, art by artgerm and greg rutkowski and magali villeneuve [woman blue saddle]" -s 20 -W 512 -H 768 -C 7.5 -A k_euler_a -S 1654590180`
<div align="center" markdown>
![step4](../assets/negative_prompt_walkthru/step4.png) ![step4](../assets/negative_prompt_walkthru/step4.png)
</div>
!!! notes "Notes about this feature:" !!! notes "Notes about this feature:"
@ -101,44 +110,58 @@ illustrate, here are three images generated using various combinations
of blend weights. As usual, unless you fix the seed, the prompts will give you of blend weights. As usual, unless you fix the seed, the prompts will give you
different results each time you run them. different results each time you run them.
---
<div align="center" markdown>
### "blue sphere, red cube, hybrid" ### "blue sphere, red cube, hybrid"
</div>
This example doesn't use melding at all and represents the default way This example doesn't use melding at all and represents the default way
of mixing concepts. of mixing concepts.
<img src="../assets/prompt-blending/blue-sphere-red-cube-hybrid.png" width=256> <div align="center" markdown>
![blue-sphere-red-cube-hyprid](../assets/prompt-blending/blue-sphere-red-cube-hybrid.png)
</div>
It's interesting to see how the AI expressed the concept of "cube" as 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 the four quadrants of the enclosing frame. If you look closely, there
is depth there, so the enclosing frame is actually a cube. is depth there, so the enclosing frame is actually a cube.
<div align="center" markdown>
### "blue sphere:0.25 red cube:0.75 hybrid" ### "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> ![blue-sphere-25-red-cube-75](../assets/prompt-blending/blue-sphere-0.25-red-cube-0.75-hybrid.png)
</div>
Now that's interesting. We get neither a blue sphere nor a red cube, 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 but a red sphere embedded in a brick wall, which represents a melding
of concepts within the AI's "latent space" of semantic of concepts within the AI's "latent space" of semantic
representations. Where is Ludwig Wittgenstein when you need him? representations. Where is Ludwig Wittgenstein when you need him?
<div align="center" markdown>
### "blue sphere:0.75 red cube:0.25 hybrid" ### "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> ![blue-sphere-75-red-cube-25](../assets/prompt-blending/blue-sphere-0.75-red-cube-0.25-hybrid.png)
</div>
Definitely more blue-spherey. The cube is gone entirely, but it's Definitely more blue-spherey. The cube is gone entirely, but it's
really cool abstract art. really cool abstract art.
<div align="center" markdown>
### "blue sphere:0.5 red cube:0.5 hybrid" ### "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> ![blue-sphere-5-red-cube-5-hybrid](../assets/prompt-blending/blue-sphere-0.5-red-cube-0.5-hybrid.png)
</div>
Whoa...! I see blue and red, but no spheres or cubes. Is the word 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? "hybrid" summoning up the concept of some sort of scifi creature?
Let's find out. Let's find out.
<div align="center" markdown>
### "blue sphere:0.5 red cube:0.5" ### "blue sphere:0.5 red cube:0.5"
<img src="../assets/prompt-blending/blue-sphere-0.5-red-cube-0.5.png" width=256> ![blue-sphere-5-red-cube-5](../assets/prompt-blending/blue-sphere-0.5-red-cube-0.5.png)
</div>
Indeed, removing the word "hybrid" produces an image that is more like Indeed, removing the word "hybrid" produces an image that is more like
what we'd expect. what we'd expect.
@ -146,4 +169,3 @@ what we'd expect.
In conclusion, prompt blending is great for exploring creative space, In conclusion, prompt blending is great for exploring creative space,
but can be difficult to direct. A forthcoming release of InvokeAI will but can be difficult to direct. A forthcoming release of InvokeAI will
feature more deterministic prompt weighting. feature more deterministic prompt weighting.

23
docs/features/TEXTUAL_INVERSION.md
View File

@ -23,13 +23,13 @@ As the default backend is not available on Windows, if you're using that
platform, set the environment variable `PL_TORCH_DISTRIBUTED_BACKEND` to `gloo` platform, set the environment variable `PL_TORCH_DISTRIBUTED_BACKEND` to `gloo`
```bash ```bash
python3 ./main.py --base ./configs/stable-diffusion/v1-finetune.yaml \ python3 ./main.py -t \
--actual_resume ./models/ldm/stable-diffusion-v1/model.ckpt \ --base ./configs/stable-diffusion/v1-finetune.yaml \
-t \ --actual_resume ./models/ldm/stable-diffusion-v1/model.ckpt \
-n my_cat \ -n my_cat \
--gpus 0 \ --gpus 0 \
--data_root D:/textual-inversion/my_cat \ --data_root D:/textual-inversion/my_cat \
--init_word 'cat' --init_word 'cat'
``` ```
During the training process, files will be created in During the training process, files will be created in
@ -59,7 +59,8 @@ Once the model is trained, specify the trained .pt or .bin file when starting
invoke using invoke using
```bash ```bash
python3 ./scripts/invoke.py --embedding_path /path/to/embedding.pt python3 ./scripts/invoke.py \
--embedding_path /path/to/embedding.pt
``` ```
Then, to utilize your subject at the invoke prompt Then, to utilize your subject at the invoke prompt
@ -80,9 +81,9 @@ LDM checkpoints using:
```bash ```bash
python3 ./scripts/merge_embeddings.py \ python3 ./scripts/merge_embeddings.py \
--manager_ckpts /path/to/first/embedding.pt \ --manager_ckpts /path/to/first/embedding.pt \
[</path/to/second/embedding.pt>,[...]] \ [</path/to/second/embedding.pt>,[...]] \
--output_path /path/to/output/embedding.pt --output_path /path/to/output/embedding.pt
``` ```
Credit goes to rinongal and the repository Credit goes to rinongal and the repository

22
docs/features/VARIATIONS.md
View File

@ -25,10 +25,11 @@ variations to create the desired image of Xena, Warrior Princess.
## Step 1 -- Find a base image that you like ## Step 1 -- Find a base image that you like
The prompt we will use throughout is The prompt we will use throughout is:
`lucy lawless as xena, warrior princess, character portrait, high resolution.`
This will be indicated as `prompt` in the examples below. `#!bash "lucy lawless as xena, warrior princess, character portrait, high resolution."`
This will be indicated as `#!bash "prompt"` in the examples below.
First we let SD create a series of images in the usual way, in this case First we let SD create a series of images in the usual way, in this case
requesting six iterations: requesting six iterations:
@ -45,7 +46,10 @@ Outputs:
./outputs/Xena/000001.3357757885.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S3357757885 ./outputs/Xena/000001.3357757885.png: "prompt" -s50 -W512 -H512 -C7.5 -Ak_lms -S3357757885
``` ```
<figure markdown>
![var1](../assets/variation_walkthru/000001.3357757885.png) ![var1](../assets/variation_walkthru/000001.3357757885.png)
<figcaption> Seed 3357757885 looks nice </figcaption>
</figure>
--- ---
@ -77,9 +81,15 @@ used to generate it.
This gives us a series of closely-related variations, including the two shown This gives us a series of closely-related variations, including the two shown
here. here.
<figure markdown>
![var2](../assets/variation_walkthru/000002.3647897225.png) ![var2](../assets/variation_walkthru/000002.3647897225.png)
<figcaption>subseed 3647897225</figcaption>
</figure>
<figure markdown>
![var3](../assets/variation_walkthru/000002.1614299449.png) ![var3](../assets/variation_walkthru/000002.1614299449.png)
<figcaption>subseed 1614299449</figcaption>
</figure>
I like the expression on Xena's face in the first one (subseed 3647897225), and I like the expression on Xena's face in the first one (subseed 3647897225), and
the armor on her shoulder in the second one (subseed 1614299449). Can we combine the armor on her shoulder in the second one (subseed 1614299449). Can we combine
@ -97,7 +107,10 @@ Outputs:
Here we are providing equal weights (0.1 and 0.1) for both the subseeds. The Here we are providing equal weights (0.1 and 0.1) for both the subseeds. The
resulting image is close, but not exactly what I wanted: resulting image is close, but not exactly what I wanted:
<figure markdown>
![var4](../assets/variation_walkthru/000003.1614299449.png) ![var4](../assets/variation_walkthru/000003.1614299449.png)
<figcaption> subseed 1614299449 </figcaption>
</figure>
We could either try combining the images with different weights, or we can We could either try combining the images with different weights, or we can
generate more variations around the almost-but-not-quite image. We do the generate more variations around the almost-but-not-quite image. We do the
@ -118,7 +131,10 @@ Outputs:
This produces six images, all slight variations on the combination of the chosen This produces six images, all slight variations on the combination of the chosen
two images. Here's the one I like best: two images. Here's the one I like best:
<figure markdown>
![var5](../assets/variation_walkthru/000004.3747154981.png) ![var5](../assets/variation_walkthru/000004.3747154981.png)
<figcaption> subseed 3747154981 </figcaption>
</figure>
As you can see, this is a very powerful tool, which when combined with subprompt As you can see, this is a very powerful tool, which when combined with subprompt
weighting, gives you great control over the content and quality of your weighting, gives you great control over the content and quality of your

167
docs/features/WEB.md
View File

@ -9,7 +9,7 @@ server (see screenshot). To use it, run the `invoke.py` script by
adding the `--web` option: adding the `--web` option:
```bash ```bash
(ldm) ~/InvokeAI$ python3 scripts/invoke.py --web (invokeai) ~/InvokeAI$ python3 scripts/invoke.py --web
``` ```
You can then connect to the server by pointing your web browser at You can then connect to the server by pointing your web browser at
@ -19,7 +19,7 @@ either the IP address of the host you are running it on, or the
wildcard `0.0.0.0`. For example: wildcard `0.0.0.0`. For example:
```bash ```bash
(ldm) ~/InvokeAI$ python3 scripts/invoke.py --web --host 0.0.0.0 (invokeai) ~/InvokeAI$ python3 scripts/invoke.py --web --host 0.0.0.0
``` ```
# Quick guided walkthrough of the WebGUI's features # Quick guided walkthrough of the WebGUI's features
@ -55,7 +55,9 @@ 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 highlighted area in the screenshot below) which select among a series
of tabs for performing different types of operations. of tabs for performing different types of operations.
<figure markdown>
![Invoke Web Server - Control Panel](../assets/invoke-web-server-2.png){:width="512px"} ![Invoke Web Server - Control Panel](../assets/invoke-web-server-2.png){:width="512px"}
</figure>
From top to bottom, these are: From top to bottom, these are:
@ -88,51 +90,51 @@ using its IP address or domain name.
#### Basics #### Basics
3. Generate an image by typing *strawberry sushi* into the large 1. Generate an image by typing *strawberry sushi* into the large
prompt field on the upper left and then clicking on the Invoke button 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 (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 image of sushi in the image panel, and a new thumbnail in the gallery
on the right. on the right.
If you need more room on the screen, you can turn the gallery off 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 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 turn it back on later by clicking the image icon that appears in the
gallery's place. gallery's place.
The images are written into the directory indicated by the `--outdir` The images are written into the directory indicated by the `--outdir`
option provided at script launch time. By default, this is option provided at script launch time. By default, this is
`outputs/img-samples` under the InvokeAI directory. `outputs/img-samples` under the InvokeAI directory.
4. Generate a bunch of strawberry sushi images by increasing the 2. Generate a bunch of strawberry sushi images by increasing the
number of requested images by adjusting the Images counter just below number of requested images by adjusting the Images counter just below
the Camera button. As each is generated, it will be added to the 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 gallery. You can switch the active image by clicking on the gallery
thumbnails. thumbnails.
5. Try playing with different settings, including image width and 3. Try playing with different settings, including image width and
height, the Sampler, the Steps and the CFG scale. height, the Sampler, the Steps and the CFG scale.
Image *Width* and *Height* do what you'd expect. However, be aware that Image *Width* and *Height* do what you'd expect. However, be aware that
larger images consume more VRAM memory and take longer to generate. larger images consume more VRAM memory and take longer to generate.
The *Sampler* controls how the AI selects the image to display. Some The *Sampler* controls how the AI selects the image to display. Some
samplers are more "creative" than others and will produce a wider samplers are more "creative" than others and will produce a wider
range of variations (see next section). Some samplers run faster than range of variations (see next section). Some samplers run faster than
others. others.
*Steps* controls how many noising/denoising/sampling steps the AI will *Steps* controls how many noising/denoising/sampling steps the AI will
take. The higher this value, the more refined the image will be, but 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 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 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 work on further, and then regenerate it using a higher number of
steps. steps.
The *CFG Scale* controls how hard the AI tries to match the generated 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 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 generally values greater than 20 won't improve things much, and values
lower than 5 will produce unexpected images. There are complex lower than 5 will produce unexpected images. There are complex
interactions between *Steps*, *CFG Scale* and the *Sampler*, so interactions between *Steps*, *CFG Scale* and the *Sampler*, so
experiment to find out what works for you. experiment to find out what works for you.
6. To regenerate a previously-generated image, select the image you 6. To regenerate a previously-generated image, select the image you
want and click *Use All*. This loads the text prompt and other want and click *Use All*. This loads the text prompt and other
@ -140,8 +142,8 @@ original settings into the control panel. If you then press *Invoke*
it will regenerate the image exactly. You can also selectively modify it will regenerate the image exactly. You can also selectively modify
the prompt or other settings to tweak the image. the prompt or other settings to tweak the image.
Alternatively, you may click on *Use Seed* to load just the image's Alternatively, you may click on *Use Seed* to load just the image's
seed, and leave other settings unchanged. seed, and leave other settings unchanged.
7. To regenerate a Stable Diffusion image that was generated by 7. To regenerate a Stable Diffusion image that was generated by
another SD package, you need to know its text prompt and its another SD package, you need to know its text prompt and its
@ -154,21 +156,21 @@ steps and dimensions, but it will (usually) be close.
#### Variations on a theme #### Variations on a theme
5. Let's try generating some variations. Select your favorite sushi 1. Let's try generating some variations. Select your favorite sushi
image from the gallery to load it. Then select "Use All" from the list 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 of buttons above. This will load up all the settings used to generate
this image, including its unique seed. this image, including its unique seed.
Go down to the Variations section of the Control Panel and set the 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 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 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 `4`. Press the `invoke` button. This will generate a series of related
images. To obtain smaller variations, just lower the Variation images. To obtain smaller variations, just lower the Variation
Amount. You may also experiment with changing the Sampler. Some Amount. You may also experiment with changing the Sampler. Some
samplers generate more variability than others. *k_euler_a* is samplers generate more variability than others. *k_euler_a* is
particularly creative, while *ddim* is pretty conservative. particularly creative, while *ddim* is pretty conservative.
6. For even more variations, experiment with increasing the setting 2. For even more variations, experiment with increasing the setting
for *Perlin*. This adds a bit of noise to the image generation for *Perlin*. This adds a bit of noise to the image generation
process. Note that values of Perlin noise greater than 0.15 produce process. Note that values of Perlin noise greater than 0.15 produce
poor images for several of the samplers. poor images for several of the samplers.
@ -181,7 +183,7 @@ particular issues with generating reallistic eyes. InvokeAI provides
the ability to reconstruct faces using either the GFPGAN or CodeFormer the ability to reconstruct faces using either the GFPGAN or CodeFormer
libraries. For more information see [POSTPROCESS](POSTPROCESS.md). libraries. For more information see [POSTPROCESS](POSTPROCESS.md).
7. Invoke a prompt that generates a mangled face. A prompt that often 1. 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 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 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 touching up, load it into the Image panel, and press the button with
@ -190,15 +192,16 @@ 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 all goes well, the eyes and other aspects of the face will be improved
(see the second screenshot) (see the second screenshot)
![Invoke Web Server - Original Image](../assets/invoke-web-server-3.png) ![Invoke Web Server - Original Image](../assets/invoke-web-server-3.png)
![Invoke Web Server - Retouched Image](../assets/invoke-web-server-4.png)
The facial reconstruction *Strength* field adjusts how aggressively ![Invoke Web Server - Retouched Image](../assets/invoke-web-server-4.png)
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 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.
2. "Upscaling" is the process of increasing the size of an image while
retaining the sharpness. InvokeAI uses an external library called retaining the sharpness. InvokeAI uses an external library called
"ESRGAN" to do this. To invoke upscaling, simply select an image and "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 press the *HD* button above it. You can select between 2X and 4X
@ -206,7 +209,7 @@ upscaling, and adjust the upscaling strength, which has much the same
meaning as in facial reconstruction. Try running this on one of your meaning as in facial reconstruction. Try running this on one of your
previously-generated images. previously-generated images.
9. Finally, you can run facial reconstruction and/or upscaling 3. Finally, you can run facial reconstruction and/or upscaling
automatically after each Invocation. Go to the Advanced Options automatically after each Invocation. Go to the Advanced Options
section of the Control Panel and turn on *Restore Face* and/or section of the Control Panel and turn on *Restore Face* and/or
*Upscale*. *Upscale*.
@ -224,28 +227,32 @@ and
[Lincoln-and-Parrot-512-transparent.png](../assets/Lincoln-and-Parrot-512-transparent.png). [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. 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 1. Click on the *Image to Image* tab icon, which is the second icon
from the top on the left-hand side of the screen: from the top on the left-hand side of the screen:
![Invoke Web Server - Image to Image Icon](../assets/invoke-web-server-5.png) <figure markdown>
![Invoke Web Server - Image to Image Icon](../assets/invoke-web-server-5.png)
</figure>
This will bring you to a screen similar to the one shown here: This will bring you to a screen similar to the one shown here:
![Invoke Web Server - Image to Image Tab](../assets/invoke-web-server-6.png){:width="640px"} <figure markdown>
![Invoke Web Server - Image to Image Tab](../assets/invoke-web-server-6.png){:width="640px"}
</figure>
Drag-and-drop the Lincoln-and-Parrot image into the Image panel, or 2. 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 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 an area marked *Initial Image*. (The WebGUI will also load the most
recently-generated image from the gallery into a section on the left, recently-generated image from the gallery into a section on the left,
but this image will be replaced in the next step.) but this image will be replaced in the next step.)
11. Go to the prompt box and type *old sea captain with raven on 3. 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 shoulder* and press Invoke. A derived image will appear to the right
of the original one: of the original one:
![Invoke Web Server - Image to Image example](../assets/invoke-web-server-7.png){:width="640px"} ![Invoke Web Server - Image to Image example](../assets/invoke-web-server-7.png){:width="640px"}
12. Experiment with the different settings. The most influential one 4. Experiment with the different settings. The most influential one
in Image to Image is *Image to Image Strength* located about midway 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 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 from 0.0 to 0.99. The higher the value, the more of the original image
@ -255,7 +262,7 @@ the Sampler and CFG Scale also influence the final result. You can
also generate variations in the same way as described in Text to also generate variations in the same way as described in Text to
Image. Image.
13. What if we only want to change certain part(s) of the image and 5. 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 leave the rest intact? This is called Inpainting, and a future version
of the InvokeAI web server will provide an interactive painting canvas 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 on which you can directly draw the areas you wish to Inpaint into. For
@ -263,18 +270,20 @@ 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 to make one or more regions of the image transparent as described in
[INPAINTING.md] and uploading that. [INPAINTING.md] and uploading that.
The file The file
[Lincoln-and-Parrot-512-transparent.png](../assets/Lincoln-and-Parrot-512-transparent.png) [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 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 has been replaced with transparency. Click on the "x" in the upper
right of the Initial Image and upload the transparent version. Using right of the Initial Image and upload the transparent version. Using
the same prompt "old sea captain with raven on shoulder" try Invoking the same prompt "old sea captain with raven on shoulder" try Invoking
an image. This time, only the parrot will be replaced, leaving the an image. This time, only the parrot will be replaced, leaving the
rest of the original image intact: rest of the original image intact:
<figure markdown>
![Invoke Web Server - Inpainting](../assets/invoke-web-server-8.png){:width="640px"} ![Invoke Web Server - Inpainting](../assets/invoke-web-server-8.png){:width="640px"}
</figure>
14. Would you like to modify a previously-generated image using the 6. Would you like to modify a previously-generated image using the
Image to Image facility? Easy! While in the Image to Image panel, Image to Image facility? Easy! While in the Image to Image panel,
hover over any of the gallery images to see a little menu of icons pop hover over any of the gallery images to see a little menu of icons pop
up. Click the picture icon to instantly send the selected image to up. Click the picture icon to instantly send the selected image to
@ -299,19 +308,15 @@ updates!
## Reference ## Reference
### Additional Options ### Additional Options
`--web_develop` - Starts the web server in development mode.
`--web_verbose` - Enables verbose logging parameter <img width=160 align="right"> | effect
-- | --
`--cors [CORS ...]` - Additional allowed origins, comma-separated `--web_develop` | Starts the web server in development mode.
`--web_verbose` | Enables verbose logging
`--host HOST` - Web server: Host or IP to listen on. Set to 0.0.0.0 to `--cors [CORS ...]` | Additional allowed origins, comma-separated
accept traffic from other devices on your network. `--host HOST` | Web server: Host or IP to listen on. Set to 0.0.0.0 to accept traffic from other devices on your network.
`--port PORT` | Web server: Port to listen on
`--port PORT` - Web server: Port to listen on `--gui` | Start InvokeAI GUI - This is the "desktop mode" version of the web app. It uses Flask to create a desktop app experience of the webserver.
`--gui` - Start InvokeAI GUI - This is the "desktop mode" version of the web app. It uses Flask
to create a desktop app experience of the webserver.
### Web Specific Features ### Web Specific Features

44
docs/help/SAMPLER_CONVERGENCE.md
View File

@ -14,12 +14,12 @@ In this document, we will talk about sampler convergence.
Looking for a short version? Here's a TL;DR in 3 tables. Looking for a short version? Here's a TL;DR in 3 tables.
| Remember | !!! note "Remember"
|:---|
| Results converge as steps (`-s`) are increased (except for `K_DPM_2_A` and `K_EULER_A`). Often at ≥ `-s100`, but may require ≥ `-s700`). | - Results converge as steps (`-s`) are increased (except for `K_DPM_2_A` and `K_EULER_A`). Often at ≥ `-s100`, but may require ≥ `-s700`).
| Producing a batch of candidate images at low (`-s8` to `-s30`) step counts can save you hours of computation. | - Producing a batch of candidate images at low (`-s8` to `-s30`) step counts can save you hours of computation.
| `K_HEUN` and `K_DPM_2` converge in less steps (but are slower). | - `K_HEUN` and `K_DPM_2` converge in less steps (but are slower).
| `K_DPM_2_A` and `K_EULER_A` incorporate a lot of creativity/variability. | - `K_DPM_2_A` and `K_EULER_A` incorporate a lot of creativity/variability.
<div align="center" markdown> <div align="center" markdown>
@ -36,10 +36,11 @@ Looking for a short version? Here's a TL;DR in 3 tables.
</div> </div>
| Suggestions | !!! tip "suggestions"
|:---|
| For most use cases, `K_LMS`, `K_HEUN` and `K_DPM_2` are the best choices (the latter 2 run 0.5x as quick, but tend to converge 2x as quick as `K_LMS`). At very low steps (≤ `-s8`), `K_HEUN` and `K_DPM_2` are not recommended. Use `K_LMS` instead.| For most use cases, `K_LMS`, `K_HEUN` and `K_DPM_2` are the best choices (the latter 2 run 0.5x as quick, but tend to converge 2x as quick as `K_LMS`). At very low steps (≤ `-s8`), `K_HEUN` and `K_DPM_2` are not recommended. Use `K_LMS` instead.
| For variability, use `K_EULER_A` (runs 2x as quick as `K_DPM_2_A`). |
For variability, use `K_EULER_A` (runs 2x as quick as `K_DPM_2_A`).
--- ---
@ -64,15 +65,15 @@ This realization is very useful because it means you don't need to create a batc
You can produce the same 100 images at `-s10` to `-s30` using a K-sampler (since they converge faster), get a rough idea of the final result, choose your 2 or 3 favorite ones, and then run `-s100` on those images to polish some details. You can produce the same 100 images at `-s10` to `-s30` using a K-sampler (since they converge faster), get a rough idea of the final result, choose your 2 or 3 favorite ones, and then run `-s100` on those images to polish some details.
The latter technique is 3-8x as quick. The latter technique is 3-8x as quick.
Example: !!! example
At 60s per 100 steps. At 60s per 100 steps.
(Option A) 60s * 100 images = 6000s (100 images at `-s100`, manually picking 3 favorites) A) 60s * 100 images = 6000s (100 images at `-s100`, manually picking 3 favorites)
(Option B) 6s * 100 images + 60s * 3 images = 780s (100 images at `-s10`, manually picking 3 favorites, and running those 3 at `-s100` to polish details) B) 6s *100 images + 60s* 3 images = 780s (100 images at `-s10`, manually picking 3 favorites, and running those 3 at `-s100` to polish details)
The result is 1 hour and 40 minutes (Option A) vs 13 minutes (Option B). The result is __1 hour and 40 minutes__ for Variant A, vs __13 minutes__ for Variant B.
### *Topic convergance* ### *Topic convergance*
@ -114,9 +115,12 @@ Note also the point of convergence may not be the most desirable state (e.g. I p
Once we understand the concept of sampler convergence, we must look into the performance of each sampler in terms of steps (iterations) per second, as not all samplers run at the same speed. Once we understand the concept of sampler convergence, we must look into the performance of each sampler in terms of steps (iterations) per second, as not all samplers run at the same speed.
On my M1 Max with 64GB of RAM, for a 512x512 image: <div align="center" markdown>
| Sampler | (3 sample average) it/s |
|---|---| On my M1 Max with 64GB of RAM, for a 512x512 image
| Sampler | (3 sample average) it/s |
| :--- | :--- |
| `DDIM` | 1.89 | | `DDIM` | 1.89 |
| `PLMS` | 1.86 | | `PLMS` | 1.86 |
| `K_EULER` | 1.86 | | `K_EULER` | 1.86 |
@ -126,11 +130,13 @@ On my M1 Max with 64GB of RAM, for a 512x512 image:
| `K_DPM_2_A` | 0.95 (slower) | | `K_DPM_2_A` | 0.95 (slower) |
| `K_EULER_A` | 1.86 | | `K_EULER_A` | 1.86 |
</div>
Combining our results with the steps per second of each sampler, three choices come out on top: `K_LMS`, `K_HEUN` and `K_DPM_2` (where the latter two run 0.5x as quick but tend to converge 2x as quick as `K_LMS`). For creativity and a lot of variation between iterations, `K_EULER_A` can be a good choice (which runs 2x as quick as `K_DPM_2_A`). Combining our results with the steps per second of each sampler, three choices come out on top: `K_LMS`, `K_HEUN` and `K_DPM_2` (where the latter two run 0.5x as quick but tend to converge 2x as quick as `K_LMS`). For creativity and a lot of variation between iterations, `K_EULER_A` can be a good choice (which runs 2x as quick as `K_DPM_2_A`).
Additionally, image generation at very low steps (≤ `-s8`) is not recommended for `K_HEUN` and `K_DPM_2`. Use `K_LMS` instead. Additionally, image generation at very low steps (≤ `-s8`) is not recommended for `K_HEUN` and `K_DPM_2`. Use `K_LMS` instead.
<img width="397" alt="192044949-67d5d441-a0d5-4d5a-be30-5dda4fc28a00-min" src="https://user-images.githubusercontent.com/50542132/192046823-2714cb29-bbf3-4eb1-9213-e27a0963905c.png"> ![K-compare](https://user-images.githubusercontent.com/50542132/192046823-2714cb29-bbf3-4eb1-9213-e27a0963905c.png){ width=600}
### *Three key points* ### *Three key points*

8
docs/help/TROUBLESHOOT.md
View File

@ -1,5 +1,7 @@
--- ---
title: F.A.Q. title: F.A.Q.
hide:
- toc
--- ---
# :material-frequently-asked-questions: F.A.Q. # :material-frequently-asked-questions: F.A.Q.
@ -63,7 +65,7 @@ Reinstall the stable diffusion modules. Enter the `stable-diffusion` directory a
### **QUESTION** ### **QUESTION**
`invoke.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** ### **SOLUTION**
@ -87,9 +89,7 @@ Usually this will be sufficient, but if you start to see errors about
missing or incorrect modules, use the command `pip install -e .` missing or incorrect modules, use the command `pip install -e .`
and/or `conda env update` (These commands won't break anything.) and/or `conda env update` (These commands won't break anything.)
`pip install -e .` and/or `pip install -e .` and/or `conda env update -f environment.yaml`
`conda env update -f environment.yaml`
(These commands won't break anything.) (These commands won't break anything.)

16
docs/installation/INSTALL_MAC.md
View File

@ -124,18 +124,18 @@ While that is downloading, open Terminal and run the following commands one at a
conda activate invokeai conda activate invokeai
# This will download some bits and pieces and make take a while # This will download some bits and pieces and make take a while
python scripts/preload_models.py (invokeai) python scripts/preload_models.py
# Run SD! # Run SD!
python scripts/dream.py (invokeai) python scripts/dream.py
# or run the web interface! # or run the web interface!
python scripts/invoke.py --web (invokeai) python scripts/invoke.py --web
# The original scripts should work as well. # The original scripts should work as well.
python scripts/orig_scripts/txt2img.py \ (invokeai) python scripts/orig_scripts/txt2img.py \
--prompt "a photograph of an astronaut riding a horse" \ --prompt "a photograph of an astronaut riding a horse" \
--plms --plms
``` ```
!!! info !!! info
@ -207,7 +207,7 @@ conda update \
There are several causes of these errors: There are several causes of these errors:
1. Did you remember to `conda activate ldm`? If your terminal prompt begins with 1. Did you remember to `conda activate ldm`? If your terminal prompt begins with
"(ldm)" then you activated it. If it begins with "(base)" or something else "(invokeai)" then you activated it. If it begins with "(base)" or something else
you haven't. you haven't.
2. You might've run `./scripts/preload_models.py` or `./scripts/invoke.py` 2. You might've run `./scripts/preload_models.py` or `./scripts/invoke.py`
@ -289,7 +289,7 @@ should actually be the _same python_, which you can verify by comparing the
output of `python3 -V` and `python -V`. output of `python3 -V` and `python -V`.
```bash ```bash
(ldm) % which python (invokeai) % which python
/Users/name/miniforge3/envs/ldm/bin/python /Users/name/miniforge3/envs/ldm/bin/python
``` ```

3
mkdocs.yml
View File

@ -2,7 +2,7 @@
site_name: Stable Diffusion Toolkit Docs site_name: Stable Diffusion Toolkit Docs
site_url: https://invoke-ai.github.io/InvokeAI site_url: https://invoke-ai.github.io/InvokeAI
site_author: mauwii site_author: mauwii
dev_addr: "127.0.0.1:8080" dev_addr: '127.0.0.1:8080'
# Repository # Repository
repo_name: 'invoke-ai/InvokeAI' repo_name: 'invoke-ai/InvokeAI'
@ -26,6 +26,7 @@ theme:
name: Switch to dark mode name: Switch to dark mode
- media: '(prefers-color-scheme: dark)' - media: '(prefers-color-scheme: dark)'
scheme: slate scheme: slate
primary: blue
toggle: toggle:
icon: material/lightbulb-outline icon: material/lightbulb-outline
name: Switch to light mode name: Switch to light mode