Bring main back into a consistent state with other branches

- Due to misuse of rebase command, main was transiently
  in an inconsistent state.

- This repairs the damage, and adds a few post-release
  patches that ensure stable conda installs on Mac and Windows.
This commit is contained in:
Lincoln Stein
2022-11-03 15:44:06 -04:00
370 changed files with 32709 additions and 9854 deletions

View File

@ -8,7 +8,7 @@ hide:
## **Interactive Command Line Interface**
The `invoke.py` script, located in `scripts/dream.py`, provides an interactive
The `invoke.py` script, located in `scripts/`, provides an interactive
interface to image generation similar to the "invoke mothership" bot that Stable
AI provided on its Discord server.
@ -86,6 +86,7 @@ overridden on a per-prompt basis (see [List of prompt arguments](#list-of-prompt
| `--model <modelname>` | | `stable-diffusion-1.4` | Loads model specified in configs/models.yaml. Currently one of "stable-diffusion-1.4" or "laion400m" |
| `--full_precision` | `-F` | `False` | Run in slower full-precision mode. Needed for Macintosh M1/M2 hardware and some older video cards. |
| `--png_compression <0-9>` | `-z<0-9>` | 6 | Select level of compression for output files, from 0 (no compression) to 9 (max compression) |
| `--safety-checker` | | False | Activate safety checker for NSFW and other potentially disturbing imagery |
| `--web` | | `False` | Start in web server mode |
| `--host <ip addr>` | | `localhost` | Which network interface web server should listen on. Set to 0.0.0.0 to listen on any. |
| `--port <port>` | | `9090` | Which port web server should listen for requests on. |
@ -97,7 +98,6 @@ overridden on a per-prompt basis (see [List of prompt arguments](#list-of-prompt
| `--embedding_path <path>` | | `None` | Path to pre-trained embedding manager checkpoints, for custom models |
| `--gfpgan_dir` | | `src/gfpgan` | Path to where GFPGAN is installed. |
| `--gfpgan_model_path` | | `experiments/pretrained_models/GFPGANv1.4.pth` | Path to GFPGAN model file, relative to `--gfpgan_dir`. |
| `--device <device>` | `-d<device>` | `torch.cuda.current_device()` | Device to run SD on, e.g. "cuda:0" |
| `--free_gpu_mem` | | `False` | Free GPU memory after sampling, to allow image decoding and saving in low VRAM conditions |
| `--precision` | | `auto` | Set model precision, default is selected by device. Options: auto, float32, float16, autocast |
@ -151,12 +151,14 @@ Here are the invoke> command that apply to txt2img:
| --cfg_scale <float>| -C<float> | 7.5 | How hard to try to match the prompt to the generated image; any number greater than 1.0 works, but the useful range is roughly 5.0 to 20.0 |
| --seed <int> | -S<int> | None | Set the random seed for the next series of images. This can be used to recreate an image generated previously.|
| --sampler <sampler>| -A<sampler>| k_lms | Sampler to use. Use -h to get list of available samplers. |
| --karras_max <int> | | 29 | When using k_* samplers, set the maximum number of steps before shifting from using the Karras noise schedule (good for low step counts) to the LatentDiffusion noise schedule (good for high step counts) This value is sticky. [29] |
| --hires_fix | | | Larger images often have duplication artefacts. This option suppresses duplicates by generating the image at low res, and then using img2img to increase the resolution |
| `--png_compression <0-9>` | `-z<0-9>` | 6 | Select level of compression for output files, from 0 (no compression) to 9 (max compression) |
| --png_compression <0-9> | -z<0-9> | 6 | Select level of compression for output files, from 0 (no compression) to 9 (max compression) |
| --grid | -g | False | Turn on grid mode to return a single image combining all the images generated by this prompt |
| --individual | -i | True | Turn off grid mode (deprecated; leave off --grid instead) |
| --outdir <path> | -o<path> | outputs/img_samples | Temporarily change the location of these images |
| --seamless | | False | Activate seamless tiling for interesting effects |
| --seamless_axes | | x,y | Specify which axes to use circular convolution on. |
| --log_tokenization | -t | False | Display a color-coded list of the parsed tokens derived from the prompt |
| --skip_normalization| -x | False | Weighted subprompts will not be normalized. See [Weighted Prompts](./OTHER.md#weighted-prompts) |
| --upscale <int> <float> | -U <int> <float> | -U 1 0.75| Upscale image by magnification factor (2, 4), and set strength of upscaling (0.0-1.0). If strength not set, will default to 0.75. |
@ -210,11 +212,40 @@ accepts additional options:
[Inpainting](./INPAINTING.md) for details.
inpainting accepts all the arguments used for txt2img and img2img, as
well as the --mask (-M) argument:
well as the --mask (-M) and --text_mask (-tm) arguments:
| Argument <img width="100" align="right"/> | Shortcut | Default | Description |
|--------------------|------------|---------------------|--------------|
| `--init_mask <path>` | `-M<path>` | `None` |Path to an image the same size as the initial_image, with areas for inpainting made transparent.|
| `--invert_mask ` | | False |If true, invert the mask so that transparent areas are opaque and vice versa.|
| `--text_mask <prompt> [<float>]` | `-tm <prompt> [<float>]` | <none> | Create a mask from a text prompt describing part of the image|
The mask may either be an image with transparent areas, in which case
the inpainting will occur in the transparent areas only, or a black
and white image, in which case all black areas will be painted into.
`--text_mask` (short form `-tm`) is a way to generate a mask using a
text description of the part of the image to replace. For example, if
you have an image of a breakfast plate with a bagel, toast and
scrambled eggs, you can selectively mask the bagel and replace it with
a piece of cake this way:
~~~
invoke> a piece of cake -I /path/to/breakfast.png -tm bagel
~~~
The algorithm uses <a
href="https://github.com/timojl/clipseg">clipseg</a> to classify
different regions of the image. The classifier puts out a confidence
score for each region it identifies. Generally regions that score
above 0.5 are reliable, but if you are getting too much or too little
masking you can adjust the threshold down (to get more mask), or up
(to get less). In this example, by passing `-tm` a higher value, we
are insisting on a more stringent classification.
~~~
invoke> a piece of cake -I /path/to/breakfast.png -tm bagel 0.6
~~~
# Other Commands
@ -256,12 +287,20 @@ Some examples:
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
# Model selection and importation
### !mask
This command takes an image, a text prompt, and uses the `clipseg`
algorithm to automatically generate a mask of the area that matches
the text prompt. It is useful for debugging the text masking process
prior to inpainting with the `--text_mask` argument. See
[INPAINTING.md] for details.
## Model selection and importation
The CLI allows you to add new models on the fly, as well as to switch
among them rapidly without leaving the script.
## !models
### !models
This prints out a list of the models defined in `config/models.yaml'.
The active model is bold-faced
@ -273,7 +312,7 @@ laion400m not loaded <no description>
waifu-diffusion not loaded Waifu Diffusion v1.3
</pre>
## !switch <model>
### !switch <model>
This quickly switches from one model to another without leaving the
CLI script. `invoke.py` uses a memory caching system; once a model
@ -319,7 +358,7 @@ laion400m not loaded <no description>
waifu-diffusion cached Waifu Diffusion v1.3
</pre>
## !import_model <path/to/model/weights>
### !import_model <path/to/model/weights>
This command imports a new model weights file into InvokeAI, makes it
available for image generation within the script, and writes out the
@ -344,7 +383,7 @@ automatically.
Example:
<pre>
invoke> <b>!import_model models/ldm/stable-diffusion-v1/ model-epoch08-float16.ckpt</b>
invoke> <b>!import_model models/ldm/stable-diffusion-v1/model-epoch08-float16.ckpt</b>
>> Model import in process. Please enter the values needed to configure this model:
Name for this model: <b>waifu-diffusion</b>
@ -371,7 +410,7 @@ OK to import [n]? <b>y</b>
invoke>
</pre>
##!edit_model <name_of_model>
###!edit_model <name_of_model>
The `!edit_model` command can be used to modify a model that is
already defined in `config/models.yaml`. Call it with the short
@ -407,20 +446,12 @@ OK to import [n]? y
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
```
# History processing
## History processing
The CLI provides a series of convenient commands for reviewing previous
actions, retrieving them, modifying them, and re-running them.
```bash
invoke> !fetch 0000015.8929913.png
# the script returns the next line, ready for editing and running:
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
was not generated by InvokeAI.
### `!history`
### !history
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
@ -445,20 +476,41 @@ invoke> !20
invoke> watercolor of beautiful woman sitting under tree wearing broad hat and flowing garment -v0.2 -n6 -S2878767194
```
## !fetch
### !fetch
This command retrieves the generation parameters from a previously
generated image and either loads them into the command line. You may
provide either the name of a file in the current output directory, or
a full file path.
generated image and either loads them into the command line
(Linux|Mac), or prints them out in a comment for copy-and-paste
(Windows). You may provide either the name of a file in the current
output directory, or a full file path. Specify path to a folder with
image png files, and wildcard *.png to retrieve the dream command used
to generate the images, and save them to a file commands.txt for
further processing.
~~~
This example loads the generation command for a single png file:
```bash
invoke> !fetch 0000015.8929913.png
# the script returns the next line, ready for editing and running:
invoke> a fantastic alien landscape -W 576 -H 512 -s 60 -A plms -C 7.5
```
This one fetches the generation commands from a batch of files and
stores them into `selected.txt`:
```bash
invoke> !fetch outputs\selected-imgs\*.png selected.txt
```
### !replay
This command replays a text file generated by !fetch or created manually
~~~
invoke> !replay outputs\selected-imgs\selected.txt
~~~
Note that this command may behave unexpectedly if given a PNG file that
Note that these commands may behave unexpectedly if given a PNG file that
was not generated by InvokeAI.
### !search <search string>

View File

@ -120,8 +120,6 @@ 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"`:
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
invoke> "fire" -s10 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png --strength 0.7
```

View File

@ -34,9 +34,188 @@ original unedited image and the masked (partially transparent) image:
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.
## **Masking using Text**
### Inpainting is not changing the masked region enough!
You can also create a mask using a text prompt to select the part of
the image you want to alter, using the <a
href="https://github.com/timojl/clipseg">clipseg</a> algorithm. This
works on any image, not just ones generated by InvokeAI.
The `--text_mask` (short form `-tm`) option takes two arguments. The
first argument is a text description of the part of the image you wish
to mask (paint over). If the text description contains a space, you must
surround it with quotation marks. The optional second argument is the
minimum threshold for the mask classifier's confidence score, described
in more detail below.
To see how this works in practice, here's an image of a still life
painting that I got off the web.
<img src="../assets/still-life-scaled.jpg">
You can selectively mask out the
orange and replace it with a baseball in this way:
~~~
invoke> a baseball -I /path/to/still_life.png -tm orange
~~~
<img src="../assets/still-life-inpainted.png">
The clipseg classifier produces a confidence score for each region it
identifies. Generally regions that score above 0.5 are reliable, but
if you are getting too much or too little masking you can adjust the
threshold down (to get more mask), or up (to get less). In this
example, by passing `-tm` a higher value, we are insisting on a tigher
mask. However, if you make it too high, the orange may not be picked
up at all!
~~~
invoke> a baseball -I /path/to/breakfast.png -tm orange 0.6
~~~
The `!mask` command may be useful for debugging problems with the
text2mask feature. The syntax is `!mask /path/to/image.png -tm <text>
<threshold>`
It will generate three files:
- The image with the selected area highlighted.
- it will be named XXXXX.<imagename>.<prompt>.selected.png
- The image with the un-selected area highlighted.
- it will be named XXXXX.<imagename>.<prompt>.deselected.png
- The image with the selected area converted into a black and white
image according to the threshold level
- it will be named XXXXX.<imagename>.<prompt>.masked.png
The `.masked.png` file can then be directly passed to the `invoke>`
prompt in the CLI via the `-M` argument. Do not attempt this with
the `selected.png` or `deselected.png` files, as they contain some
transparency throughout the image and will not produce the desired
results.
Here is an example of how `!mask` works:
```
invoke> !mask ./test-pictures/curly.png -tm hair 0.5
>> generating masks from ./test-pictures/curly.png
>> Initializing clipseg model for text to mask inference
Outputs:
[941.1] outputs/img-samples/000019.curly.hair.deselected.png: !mask ./test-pictures/curly.png -tm hair 0.5
[941.2] outputs/img-samples/000019.curly.hair.selected.png: !mask ./test-pictures/curly.png -tm hair 0.5
[941.3] outputs/img-samples/000019.curly.hair.masked.png: !mask ./test-pictures/curly.png -tm hair 0.5
```
**Original image "curly.png"**
<img src="../assets/outpainting/curly.png">
**000019.curly.hair.selected.png**
<img src="../assets/inpainting/000019.curly.hair.selected.png">
**000019.curly.hair.deselected.png**
<img src="../assets/inpainting/000019.curly.hair.deselected.png">
**000019.curly.hair.masked.png**
<img src="../assets/inpainting/000019.curly.hair.masked.png">
It looks like we selected the hair pretty well at the 0.5 threshold
(which is the default, so we didn't actually have to specify it), so
let's have some fun:
```
invoke> medusa with cobras -I ./test-pictures/curly.png -M 000019.curly.hair.masked.png -C20
>> loaded input image of size 512x512 from ./test-pictures/curly.png
...
Outputs:
[946] outputs/img-samples/000024.801380492.png: "medusa with cobras" -s 50 -S 801380492 -W 512 -H 512 -C 20.0 -I ./test-pictures/curly.png -A k_lms -f 0.75
```
<img src="../assets/inpainting/000024.801380492.png">
You can also skip the `!mask` creation step and just select the masked
region directly:
```
invoke> medusa with cobras -I ./test-pictures/curly.png -tm hair -C20
```
## Using the RunwayML inpainting model
The [RunwayML Inpainting Model
v1.5](https://huggingface.co/runwayml/stable-diffusion-inpainting) is
a specialized version of [Stable Diffusion
v1.5](https://huggingface.co/spaces/runwayml/stable-diffusion-v1-5)
that contains extra channels specifically designed to enhance
inpainting and outpainting. While it can do regular `txt2img` and
`img2img`, it really shines when filling in missing regions. It has an
almost uncanny ability to blend the new regions with existing ones in
a semantically coherent way.
To install the inpainting model, follow the
[instructions](INSTALLING-MODELS.md) for installing a new model. You
may use either the CLI (`invoke.py` script) or directly edit the
`configs/models.yaml` configuration file to do this. The main thing to
watch out for is that the the model `config` option must be set up to
use `v1-inpainting-inference.yaml` rather than the `v1-inference.yaml`
file that is used by Stable Diffusion 1.4 and 1.5.
After installation, your `models.yaml` should contain an entry that
looks like this one:
inpainting-1.5:
weights: models/ldm/stable-diffusion-v1/sd-v1-5-inpainting.ckpt
description: SD inpainting v1.5
config: configs/stable-diffusion/v1-inpainting-inference.yaml
vae: models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt
width: 512
height: 512
As shown in the example, you may include a VAE fine-tuning weights
file as well. This is strongly recommended.
To use the custom inpainting model, launch `invoke.py` with the
argument `--model inpainting-1.5` or alternatively from within the
script use the `!switch inpainting-1.5` command to load and switch to
the inpainting model.
You can now do inpainting and outpainting exactly as described above,
but there will (likely) be a noticeable improvement in
coherence. Txt2img and Img2img will work as well.
There are a few caveats to be aware of:
1. The inpainting model is larger than the standard model, and will
use nearly 4 GB of GPU VRAM. This makes it unlikely to run on
a 4 GB graphics card.
2. When operating in Img2img mode, the inpainting model is much less
steerable than the standard model. It is great for making small
changes, such as changing the pattern of a fabric, or slightly
changing a subject's expression or hair, but the model will
resist making the dramatic alterations that the standard
model lets you do.
3. While the `--hires` option works fine with the inpainting model,
some special features, such as `--embiggen` are disabled.
4. Prompt weighting (`banana++ sushi`) and merging work well with
the inpainting model, but prompt swapping (a ("fluffy cat").swap("smiling dog") eating a hotdog`)
will not have any effect due to the way the model is set up.
You may use text masking (with `-tm thing-to-mask`) as an
effective replacement.
5. The model tends to oversharpen image if you use high step or CFG
values. If you need to do large steps, use the standard model.
6. The `--strength` (`-f`) option has no effect on the inpainting
model due to its fundamental differences with the standard
model. It will always take the full number of steps you specify.
## Troubleshooting
Here are some troubleshooting tips for inpainting and outpainting.
## Inpainting is not changing the masked region enough!
One of the things to understand about how inpainting works is that it
is equivalent to running img2img on just the masked (transparent)

View File

@ -26,6 +26,12 @@ for each `invoke>` prompt as shown here:
invoke> "pond garden with lotus by claude monet" --seamless -s100 -n4
```
By default this will tile on both the X and Y axes. However, you can also specify specific axes to tile on with `--seamless_axes`.
Possible values are `x`, `y`, and `x,y`:
```python
invoke> "pond garden with lotus by claude monet" --seamless --seamless_axes=x -s100 -n4
```
---
## **Shortcuts: Reusing Seeds**
@ -69,6 +75,23 @@ combination of integers and floating point numbers, and they do not need to add
---
## **Filename Format**
The argument `--fnformat` allows to specify the filename of the
image. Supported wildcards are all arguments what can be set such as
`perlin`, `seed`, `threshold`, `height`, `width`, `gfpgan_strength`,
`sampler_name`, `steps`, `model`, `upscale`, `prompt`, `cfg_scale`,
`prefix`.
The following prompt
```bash
dream> a red car --steps 25 -C 9.8 --perlin 0.1 --fnformat {prompt}_steps.{steps}_cfg.{cfg_scale}_perlin.{perlin}.png
```
generates a file with the name: `outputs/img-samples/a red car_steps.25_cfg.9.8_perlin.0.1.png`
---
## **Thresholding and Perlin Noise Initialization Options**
Two new options are the thresholding (`--threshold`) and the perlin noise initialization (`--perlin`) options. Thresholding limits the range of the latent values during optimization, which helps combat oversaturation with higher CFG scale values. Perlin noise initialization starts with a percentage (a value ranging from 0 to 1) of perlin noise mixed into the initial noise. Both features allow for more variations and options in the course of generating images.

View File

@ -15,13 +15,52 @@ InvokeAI supports two versions of outpainting, one called "outpaint"
and the other "outcrop." They work slightly differently and each has
its advantages and drawbacks.
### Outpainting
Outpainting is the same as inpainting, except that the painting occurs
in the regions outside of the original image. To outpaint using the
`invoke.py` command line script, prepare an image in which the borders
to be extended are pure black. Add an alpha channel (if there isn't one
already), and make the borders completely transparent and the interior
completely opaque. If you wish to modify the interior as well, you may
create transparent holes in the transparency layer, which `img2img` will
paint into as usual.
Pass the image as the argument to the `-I` switch as you would for
regular inpainting:
invoke> a stream by a river -I /path/to/transparent_img.png
You'll likely be delighted by the results.
### Tips
1. Do not try to expand the image too much at once. Generally it is best
to expand the margins in 64-pixel increments. 128 pixels often works,
but your mileage may vary depending on the nature of the image you are
trying to outpaint into.
2. There are a series of switches that can be used to adjust how the
inpainting algorithm operates. In particular, you can use these to
minimize the seam that sometimes appears between the original image
and the extended part. These switches are:
--seam_size SEAM_SIZE Size of the mask around the seam between original and outpainted image (0)
--seam_blur SEAM_BLUR The amount to blur the seam inwards (0)
--seam_strength STRENGTH The img2img strength to use when filling the seam (0.7)
--seam_steps SEAM_STEPS The number of steps to use to fill the seam. (10)
--tile_size TILE_SIZE The tile size to use for filling outpaint areas (32)
### Outcrop
The `outcrop` extension allows you to extend the image in 64 pixel
increments in any dimension. You can apply the module to any image
previously-generated by InvokeAI. Note that it will **not** work with
arbitrary photographs or Stable Diffusion images created by other
implementations.
The `outcrop` extension gives you a convenient `!fix` postprocessing
command that allows you to extend a previously-generated image in 64
pixel increments in any direction. You can apply the module to any
image previously-generated by InvokeAI. Note that it works with
arbitrary PNG photographs, but not currently with JPG or other
formats. Outcropping is particularly effective when combined with the
[runwayML custom inpainting
model](INPAINTING.md#using-the-runwayml-inpainting-model).
Consider this image:
@ -33,23 +72,24 @@ 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!
```bash
invoke> !fix images/curly.png --outcrop top 64 right 64
invoke> !fix images/curly.png --outcrop top 128 right 64 bottom 64
```
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
amount. You can use any combination of top|left|right|bottom, and
of the image by 128 pixels, and the right and bottom of the image by
64 pixels. You can use any combination of top|left|right|bottom, and
specify any number of pixels to extend. You can also abbreviate
`--outcrop` to `-c`.
The result looks like this:
<figure markdown>
![curly_woman_outcrop](../assets/outpainting/curly-outcrop.png)
![curly_woman_outcrop](../assets/outpainting/curly-outcrop-2.png)
</figure>
The new image is actually slightly larger than the original (576x576,
because 64 pixels were added to the top and right sides.)
The new image is larger than the original (576x704)
because 64 pixels were added to the top and right sides. You will
need enough VRAM to process an image of this size.
A number of caveats:
@ -64,6 +104,17 @@ you'll get a slightly different result. You can run it repeatedly
until you get an image you like. Unfortunately `!fix` does not
currently respect the `-n` (`--iterations`) argument.
3. Your results will be _much_ better if you use the `inpaint-1.5`
model released by runwayML and installed by default by
`scripts/preload_models.py`. This model was trained specifically to
harmoniously fill in image gaps. The standard model will work as well,
but you may notice color discontinuities at the border.
4. When using the `inpaint-1.5` model, you may notice subtle changes
to the area within the original image. This is because the model
performs an encoding/decoding on the image as a whole. This does not
occur with the standard model.
## Outpaint
The `outpaint` extension does the same thing, but with subtle

View File

@ -45,7 +45,7 @@ Here's a prompt that depicts what it does.
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 pony 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`
<figure markdown>
![step1](../assets/negative_prompt_walkthru/step1.png)
@ -84,6 +84,109 @@ Getting close - but there's no sense in having a saddle when our horse doesn't h
---
## **Prompt Syntax Features**
The InvokeAI prompting language has the following features:
### Attention weighting
Append a word or phrase with `-` or `+`, or a weight between `0` and `2` (`1`=default), to decrease or increase "attention" (= a mix of per-token CFG weighting multiplier and, for `-`, a weighted blend with the prompt without the term).
The following syntax is recognised:
* single words without parentheses: `a tall thin man picking apricots+`
* single or multiple words with parentheses: `a tall thin man picking (apricots)+` `a tall thin man picking (apricots)-` `a tall thin man (picking apricots)+` `a tall thin man (picking apricots)-`
* more effect with more symbols `a tall thin man (picking apricots)++`
* nesting `a tall thin man (picking apricots+)++` (`apricots` effectively gets `+++`)
* all of the above with explicit numbers `a tall thin man picking (apricots)1.1` `a tall thin man (picking (apricots)1.3)1.1`. (`+` is equivalent to 1.1, `++` is pow(1.1,2), `+++` is pow(1.1,3), etc; `-` means 0.9, `--` means pow(0.9,2), etc.)
* attention also applies to `[unconditioning]` so `a tall thin man picking apricots [(ladder)0.01]` will *very gently* nudge SD away from trying to draw the man on a ladder
You can use this to increase or decrease the amount of something. Starting from this prompt of `a man picking apricots from a tree`, let's see what happens if we increase and decrease how much attention we want Stable Diffusion to pay to the word `apricots`:
![an AI generated image of a man picking apricots from a tree](../assets/prompt_syntax/apricots-0.png)
Using `-` to reduce apricot-ness:
| `a man picking apricots- from a tree` | `a man picking apricots-- from a tree` | `a man picking apricots--- from a tree` |
| -- | -- | -- |
| ![an AI generated image of a man picking apricots from a tree, with smaller apricots](../assets/prompt_syntax/apricots--1.png) | ![an AI generated image of a man picking apricots from a tree, with even smaller and fewer apricots](../assets/prompt_syntax/apricots--2.png) | ![an AI generated image of a man picking apricots from a tree, with very few very small apricots](../assets/prompt_syntax/apricots--3.png) |
Using `+` to increase apricot-ness:
| `a man picking apricots+ from a tree` | `a man picking apricots++ from a tree` | `a man picking apricots+++ from a tree` | `a man picking apricots++++ from a tree` | `a man picking apricots+++++ from a tree` |
| -- | -- | -- | -- | -- |
| ![an AI generated image of a man picking apricots from a tree, with larger, more vibrant apricots](../assets/prompt_syntax/apricots-1.png) | ![an AI generated image of a man picking apricots from a tree with even larger, even more vibrant apricots](../assets/prompt_syntax/apricots-2.png) | ![an AI generated image of a man picking apricots from a tree, but the man has been replaced by a pile of apricots](../assets/prompt_syntax/apricots-3.png) | ![an AI generated image of a man picking apricots from a tree, but the man has been replaced by a mound of giant melting-looking apricots](../assets/prompt_syntax/apricots-4.png) | ![an AI generated image of a man picking apricots from a tree, but the man and the leaves and parts of the ground have all been replaced by giant melting-looking apricots](../assets/prompt_syntax/apricots-5.png) |
You can also change the balance between different parts of a prompt. For example, below is a `mountain man`:
![an AI generated image of a mountain man](../assets/prompt_syntax/mountain-man.png)
And here he is with more mountain:
| `mountain+ man` | `mountain++ man` | `mountain+++ man` |
| -- | -- | -- |
| ![](../assets/prompt_syntax/mountain1-man.png) | ![](../assets/prompt_syntax/mountain2-man.png) | ![](../assets/prompt_syntax/mountain3-man.png) |
Or, alternatively, with more man:
| `mountain man+` | `mountain man++` | `mountain man+++` | `mountain man++++` |
| -- | -- | -- | -- |
| ![](../assets/prompt_syntax/mountain-man1.png) | ![](../assets/prompt_syntax/mountain-man2.png) | ![](../assets/prompt_syntax/mountain-man3.png) | ![](../assets/prompt_syntax/mountain-man4.png) |
### Blending between prompts
* `("a tall thin man picking apricots", "a tall thin man picking pears").blend(1,1)`
* The existing prompt blending using `:<weight>` will continue to be supported - `("a tall thin man picking apricots", "a tall thin man picking pears").blend(1,1)` is equivalent to `a tall thin man picking apricots:1 a tall thin man picking pears:1` in the old syntax.
* Attention weights can be nested inside blends.
* Non-normalized blends are supported by passing `no_normalize` as an additional argument to the blend weights, eg `("a tall thin man picking apricots", "a tall thin man picking pears").blend(1,-1,no_normalize)`. very fun to explore local maxima in the feature space, but also easy to produce garbage output.
See the section below on "Prompt Blending" for more information about how this works.
### Cross-Attention Control ('prompt2prompt')
Sometimes an image you generate is almost right, and you just want to
change one detail without affecting the rest. You could use a photo editor and inpainting
to overpaint the area, but that's a pain. Here's where `prompt2prompt`
comes in handy.
Generate an image with a given prompt, record the seed of the image,
and then use the `prompt2prompt` syntax to substitute words in the
original prompt for words in a new prompt. This works for `img2img` as well.
* `a ("fluffy cat").swap("smiling dog") eating a hotdog`.
* quotes optional: `a (fluffy cat).swap(smiling dog) eating a hotdog`.
* for single word substitutions parentheses are also optional: `a cat.swap(dog) eating a hotdog`.
* Supports options `s_start`, `s_end`, `t_start`, `t_end` (each 0-1) loosely corresponding to bloc97's `prompt_edit_spatial_start/_end` and `prompt_edit_tokens_start/_end` but with the math swapped to make it easier to intuitively understand.
* Example usage:`a (cat).swap(dog, s_end=0.3) eating a hotdog` - the `s_end` argument means that the "spatial" (self-attention) edit will stop having any effect after 30% (=0.3) of the steps have been done, leaving Stable Diffusion with 70% of the steps where it is free to decide for itself how to reshape the cat-form into a dog form.
* The numbers represent a percentage through the step sequence where the edits should happen. 0 means the start (noisy starting image), 1 is the end (final image).
* For img2img, the step sequence does not start at 0 but instead at (1-strength) - so if strength is 0.7, s_start and s_end must both be greater than 0.3 (1-0.7) to have any effect.
* Convenience option `shape_freedom` (0-1) to specify how much "freedom" Stable Diffusion should have to change the shape of the subject being swapped.
* `a (cat).swap(dog, shape_freedom=0.5) eating a hotdog`.
The `prompt2prompt` code is based off [bloc97's
colab](https://github.com/bloc97/CrossAttentionControl).
Note that `prompt2prompt` is not currently working with the runwayML
inpainting model, and may never work due to the way this model is set
up. If you attempt to use `prompt2prompt` you will get the original
image back. However, since this model is so good at inpainting, a
good substitute is to use the `clipseg` text masking option:
```
invoke> a fluffy cat eating a hotdot
Outputs:
[1010] outputs/000025.2182095108.png: a fluffy cat eating a hotdog
invoke> a smiling dog eating a hotdog -I 000025.2182095108.png -tm cat
```
### Escaping parantheses () and speech marks ""
If the model you are using has parentheses () or speech marks "" as
part of its syntax, you will need to "escape" these using a backslash,
so that`(my_keyword)` becomes `\(my_keyword\)`. Otherwise, the prompt
parser will attempt to interpret the parentheses as part of the prompt
syntax and it will get confused.
## **Prompt Blending**
You may blend together different sections of the prompt to explore the

View File

@ -0,0 +1,58 @@
# **WebUI Hotkey List**
## General
| Setting | Hotkey |
| ------------ | ---------------------- |
| a | Set All Parameters |
| s | Set Seed |
| u | Upscale |
| r | Restoration |
| i | Show Metadata |
| Ddl | Delete Image |
| alt + a | Focus prompt input |
| shift + i | Send To Image to Image |
| ctrl + enter | Start processing |
| shift + x | cancel Processing |
| shift + d | Toggle Dark Mode |
| ` | Toggle console |
## Tabs
| Setting | Hotkey |
| ------- | ------------------------- |
| 1 | Go to Text To Image Tab |
| 2 | Go to Image to Image Tab |
| 3 | Go to Inpainting Tab |
| 4 | Go to Outpainting Tab |
| 5 | Go to Nodes Tab |
| 6 | Go to Post Processing Tab |
## Gallery
| Setting | Hotkey |
| ------------ | ------------------------------- |
| g | Toggle Gallery |
| left arrow | Go to previous image in gallery |
| right arrow | Go to next image in gallery |
| shift + p | Pin gallery |
| shift + up | Increase gallery image size |
| shift + down | Decrease gallery image size |
| shift + r | Reset image gallery size |
## Inpainting
| Setting | Hotkey |
| -------------------------- | --------------------- |
| [ | Decrease brush size |
| ] | Increase brush size |
| alt + [ | Decrease mask opacity |
| alt + ] | Increase mask opacity |
| b | Select brush |
| e | Select eraser |
| ctrl + z | Undo brush stroke |
| ctrl + shift + z, ctrl + y | Redo brush stroke |
| h | Hide mask |
| shift + m | Invert mask |
| shift + c | Clear mask |
| shift + j | Expand canvas |