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

updated postprocessing, prompts, img2img and web docs

Browse Source
This commit is contained in:
Lincoln Stein 2023-05-29 10:55:57 -04:00
parent 00cb8a0c64
commit a0b6654f6a
14 changed files with 93 additions and 324 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
docs/CHANGELOG.md
View File

@ -494,7 +494,7 @@ sections describe what's new for InvokeAI.
[Manual Installation](installation/020_INSTALL_MANUAL.md). [Manual Installation](installation/020_INSTALL_MANUAL.md).
- The ability to save frequently-used startup options (model to load, steps, - The ability to save frequently-used startup options (model to load, steps,
sampler, etc) in a `.invokeai` file. See sampler, etc) in a `.invokeai` file. See
[Client](features/CLI.md) [Client](deprecated/CLI.md)
- Support for AMD GPU cards (non-CUDA) on Linux machines. - Support for AMD GPU cards (non-CUDA) on Linux machines.
- Multiple bugs and edge cases squashed. - Multiple bugs and edge cases squashed.
@ -617,7 +617,7 @@ sections describe what's new for InvokeAI.
- `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains for - `dream.py` script renamed `invoke.py`. A `dream.py` script wrapper remains for
backward compatibility. backward compatibility.
- Completely new WebGUI - launch with `python3 scripts/invoke.py --web` - Completely new WebGUI - launch with `python3 scripts/invoke.py --web`
- Support for [inpainting](features/INPAINTING.md) and - Support for [inpainting](deprecated/INPAINTING.md) and
[outpainting](features/OUTPAINTING.md) [outpainting](features/OUTPAINTING.md)
- img2img runs on all k\* samplers - img2img runs on all k\* samplers
- Support for - Support for
@ -629,7 +629,7 @@ sections describe what's new for InvokeAI.
using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E using facial reconstruction, ESRGAN upscaling, outcropping (similar to DALL-E
infinite canvas), and "embiggen" upscaling. See the `!fix` command. infinite canvas), and "embiggen" upscaling. See the `!fix` command.
- New `--hires` option on `invoke>` line allows - New `--hires` option on `invoke>` line allows
[larger images to be created without duplicating elements](features/CLI.md#this-is-an-example-of-txt2img), [larger images to be created without duplicating elements](deprecated/CLI.md#this-is-an-example-of-txt2img),
at the cost of some performance. at the cost of some performance.
- New `--perlin` and `--threshold` options allow you to add and control - New `--perlin` and `--threshold` options allow you to add and control
variation during image generation (see variation during image generation (see
@ -638,7 +638,7 @@ sections describe what's new for InvokeAI.
of images and tweaking of previous settings. of images and tweaking of previous settings.
- Command-line completion in `invoke.py` now works on Windows, Linux and Mac - Command-line completion in `invoke.py` now works on Windows, Linux and Mac
platforms. platforms.
- Improved [command-line completion behavior](features/CLI.md) New commands - Improved [command-line completion behavior](deprecated/CLI.md) New commands
added: added:
- List command-line history with `!history` - List command-line history with `!history`
- Search command-line history with `!search` - Search command-line history with `!search`

BIN
docs/assets/features/restoration-montage.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 4.0 MiB

BIN
docs/assets/features/upscale-dialog.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 310 KiB

BIN
docs/assets/features/upscaling-montage.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 8.3 MiB

10
docs/features/CLI.md → docs/deprecated/CLI.md
View File

@ -205,14 +205,14 @@ Here are the invoke> command that apply to txt2img:
| `--seamless` | | `False` | Activate seamless tiling for interesting effects | | `--seamless` | | `False` | Activate seamless tiling for interesting effects |
| `--seamless_axes` | | `x,y` | Specify which axes to use circular convolution on. | | `--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 | | `--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) | | `--skip_normalization` | `-x` | `False` | Weighted subprompts will not be normalized. See [Weighted Prompts](../features/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. | | `--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. |
| `--facetool_strength <float>` | `-G <float> ` | `-G0` | Fix faces (defaults to using the GFPGAN algorithm); argument indicates how hard the algorithm should try (0.0-1.0) | | `--facetool_strength <float>` | `-G <float> ` | `-G0` | Fix faces (defaults to using the GFPGAN algorithm); argument indicates how hard the algorithm should try (0.0-1.0) |
| `--facetool <name>` | `-ft <name>` | `-ft gfpgan` | Select face restoration algorithm to use: gfpgan, codeformer | | `--facetool <name>` | `-ft <name>` | `-ft gfpgan` | Select face restoration algorithm to use: gfpgan, codeformer |
| `--codeformer_fidelity` | `-cf <float>` | `0.75` | Used along with CodeFormer. Takes values between 0 and 1. 0 produces high quality but low accuracy. 1 produces high accuracy but low quality | | `--codeformer_fidelity` | `-cf <float>` | `0.75` | Used along with CodeFormer. Takes values between 0 and 1. 0 produces high quality but low accuracy. 1 produces high accuracy but low quality |
| `--save_original` | `-save_orig` | `False` | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced. | | `--save_original` | `-save_orig` | `False` | When upscaling or fixing faces, this will cause the original image to be saved rather than replaced. |
| `--variation <float>` | `-v<float>` | `0.0` | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](./VARIATIONS.md). | | `--variation <float>` | `-v<float>` | `0.0` | Add a bit of noise (0.0=none, 1.0=high) to the image in order to generate a series of variations. Usually used in combination with `-S<seed>` and `-n<int>` to generate a series a riffs on a starting image. See [Variations](../features/VARIATIONS.md). |
| `--with_variations <pattern>` | | `None` | Combine two or more variations. See [Variations](./VARIATIONS.md) for now to use this. | | `--with_variations <pattern>` | | `None` | Combine two or more variations. See [Variations](../features/VARIATIONS.md) for now to use this. |
| `--save_intermediates <n>` | | `None` | Save the image from every nth step into an "intermediates" folder inside the output directory | | `--save_intermediates <n>` | | `None` | Save the image from every nth step into an "intermediates" folder inside the output directory |
| `--h_symmetry_time_pct <float>` | | `None` | Create symmetry along the X axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.) | | `--h_symmetry_time_pct <float>` | | `None` | Create symmetry along the X axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.) |
| `--v_symmetry_time_pct <float>` | | `None` | Create symmetry along the Y axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.) | | `--v_symmetry_time_pct <float>` | | `None` | Create symmetry along the Y axis at the desired percent complete of the generation process. (Must be between 0.0 and 1.0; set to a very small number like 0.0001 for just after the first step of generation.) |
@ -257,7 +257,7 @@ additional options:
by `-M`. You may also supply just a single initial image with the areas by `-M`. You may also supply just a single initial image with the areas
to overpaint made transparent, but you must be careful not to destroy to overpaint made transparent, but you must be careful not to destroy
the pixels underneath when you create the transparent areas. See the pixels underneath when you create the transparent areas. See
[Inpainting](./INPAINTING.md) for details. [Inpainting](INPAINTING.md) for details.
inpainting accepts all the arguments used for txt2img and img2img, as well as inpainting accepts all the arguments used for txt2img and img2img, as well as
the --mask (-M) and --text_mask (-tm) arguments: the --mask (-M) and --text_mask (-tm) arguments:
@ -297,7 +297,7 @@ invoke> a piece of cake -I /path/to/breakfast.png -tm bagel 0.6
You can load and use hundreds of community-contributed Textual You can load and use hundreds of community-contributed Textual
Inversion models just by typing the appropriate trigger phrase. Please Inversion models just by typing the appropriate trigger phrase. Please
see [Concepts Library](CONCEPTS.md) for more details. see [Concepts Library](../features/CONCEPTS.md) for more details.
## Other Commands ## Other Commands

0
docs/features/EMBIGGEN.md → docs/deprecated/EMBIGGEN.md
View File

0
docs/features/INPAINTING.md → docs/deprecated/INPAINTING.md
View File

0
docs/features/OUTPAINTING.md → docs/deprecated/OUTPAINTING.md
View File

110
docs/features/IMG2IMG.md
View File

@ -4,86 +4,13 @@ title: Image-to-Image
# :material-image-multiple: Image-to-Image # :material-image-multiple: Image-to-Image
Both the Web and command-line interfaces provide an "img2img" feature InvokeAI provides an "img2img" feature that lets you seed your
that lets you seed your creations with an initial drawing or creations with an initial drawing or photo. This is a really cool
photo. This is a really cool feature that tells stable diffusion to feature that tells stable diffusion to build the prompt on top of the
build the prompt on top of the image you provide, preserving the image you provide, preserving the original's basic shape and layout.
original's basic shape and layout.
See the [WebUI Guide](WEB.md) for a walkthrough of the img2img feature For a walkthrough of using Image-to-Image in the Web UI, see [InvokeAI
in the InvokeAI web server. This document describes how to use img2img Web Server](./WEB.md#image-to-image).
in the command-line tool.
## Basic Usage
Launch the command-line client by launching `invoke.sh`/`invoke.bat`
and choosing option (1). Alternative, activate the InvokeAI
environment and issue the command `invokeai`.
Once the `invoke> ` prompt appears, you can start an img2img render by
pointing to a seed file with the `-I` option as shown here:
!!! example ""
```commandline
tree on a hill with a river, nature photograph, national geographic -I./test-pictures/tree-and-river-sketch.png -f 0.85
```
<figure markdown>
| original image | generated image |
| :------------: | :-------------: |
| ![original-image](https://user-images.githubusercontent.com/50542132/193946000-c42a96d8-5a74-4f8a-b4c3-5213e6cadcce.png){ width=320 } | ![generated-image](https://user-images.githubusercontent.com/111189/194135515-53d4c060-e994-4016-8121-7c685e281ac9.png){ width=320 } |
</figure>
The `--init_img` (`-I`) option gives the path to the seed picture. `--strength`
(`-f`) controls how much the original will be modified, ranging from `0.0` (keep
the original intact), to `1.0` (ignore the original completely). The default is
`0.75`, and ranges from `0.25-0.90` give interesting results. Other relevant
options include `-C` (classification free guidance scale), and `-s` (steps).
Unlike `txt2img`, adding steps will continuously change the resulting image and
it will not converge.
You may also pass a `-v<variation_amount>` option to generate `-n<iterations>`
count variants on the original image. This is done by passing the first
generated image back into img2img the requested number of times. It generates
interesting variants.
Note that the prompt makes a big difference. For example, this slight variation
on the prompt produces a very different image:
<figure markdown>
![](https://user-images.githubusercontent.com/111189/194135220-16b62181-b60c-4248-8989-4834a8fd7fbd.png){ width=320 }
<caption markdown>photograph of a tree on a hill with a river</caption>
</figure>
!!! tip
When designing prompts, think about how the images scraped from the internet were
captioned. Very few photographs will be labeled "photograph" or "photorealistic."
They will, however, be captioned with the publication, photographer, camera model,
or film settings.
If the initial image contains transparent regions, then Stable Diffusion will
only draw within the transparent regions, a process called
[`inpainting`](./INPAINTING.md#creating-transparent-regions-for-inpainting).
However, for this to work correctly, the color information underneath the
transparent needs to be preserved, not erased.
!!! warning "**IMPORTANT ISSUE** "
`img2img` does not work properly on initial images smaller
than 512x512. Please scale your image to at least 512x512 before using it.
Larger images are not a problem, but may run out of VRAM on your GPU card. To
fix this, use the --fit option, which downscales the initial image to fit within
the box specified by width x height:
```
tree on a hill with a river, national geographic -I./test-pictures/big-sketch.png -H512 -W512 --fit
```
## How does it actually work, though?
The main difference between `img2img` and `prompt2img` is the starting point. The main difference between `img2img` and `prompt2img` is the starting point.
While `prompt2img` always starts with pure gaussian noise and progressively While `prompt2img` always starts with pure gaussian noise and progressively
@ -99,10 +26,6 @@ seed `1592514025` develops something like this:
!!! example "" !!! example ""
```bash
invoke> "fire" -s10 -W384 -H384 -S1592514025
```
<figure markdown> <figure markdown>
![latent steps](../assets/img2img/000019.steps.png){ width=720 } ![latent steps](../assets/img2img/000019.steps.png){ width=720 }
</figure> </figure>
@ -157,17 +80,8 @@ Diffusion has less chance to refine itself, so the result ends up inheriting all
the problems of my bad drawing. the problems of my bad drawing.
If you want to try this out yourself, all of these are using a seed of 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 `1592514025` with a width/height of `384`, step count `10`, the
(`k_lms`), and the single-word prompt `"fire"`: `k_lms` sampler, and the single-word prompt `"fire"`.
```bash
invoke> "fire" -s10 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png --strength 0.7
```
The code for rendering intermediates is on my (damian0815's) branch
[document-img2img](https://github.com/damian0815/InvokeAI/tree/document-img2img) -
run `invoke.py` and check your `outputs/img-samples/intermediates` folder while
generating an image.
### Compensating for the reduced step count ### Compensating for the reduced step count
@ -180,10 +94,6 @@ give each generation 20 steps.
Here's strength `0.4` (note step count `50`, which is `20 ÷ 0.4` to make sure SD Here's strength `0.4` (note step count `50`, which is `20 ÷ 0.4` to make sure SD
does `20` steps from my image): does `20` steps from my image):
```bash
invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
```
<figure markdown> <figure markdown>
![000035.1592514025](../assets/img2img/000035.1592514025.png) ![000035.1592514025](../assets/img2img/000035.1592514025.png)
</figure> </figure>
@ -191,10 +101,6 @@ invoke> "fire" -s50 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.4
and here is strength `0.7` (note step count `30`, which is roughly `20 ÷ 0.7` to and here is strength `0.7` (note step count `30`, which is roughly `20 ÷ 0.7` to
make sure SD does `20` steps from my image): make sure SD does `20` steps from my image):
```commandline
invoke> "fire" -s30 -W384 -H384 -S1592514025 -I /tmp/fire-drawing.png -f 0.7
```
<figure markdown> <figure markdown>
![000046.1592514025](../assets/img2img/000046.1592514025.png) ![000046.1592514025](../assets/img2img/000046.1592514025.png)
</figure> </figure>

161
docs/features/POSTPROCESS.md
View File

@ -8,12 +8,6 @@ title: Postprocessing
This extension provides the ability to restore faces and upscale images. This extension provides the ability to restore faces and upscale images.
Face restoration and upscaling can be applied at the time you generate the
images, or at any later time against a previously-generated PNG file, using the
[!fix](#fixing-previously-generated-images) command.
[Outpainting and outcropping](OUTPAINTING.md) can only be applied after the
fact.
## Face Fixing ## Face Fixing
The default face restoration module is GFPGAN. The default upscale is The default face restoration module is GFPGAN. The default upscale is
@ -23,8 +17,7 @@ Real-ESRGAN. For an alternative face restoration module, see
As of version 1.14, environment.yaml will install the Real-ESRGAN package into As of version 1.14, environment.yaml will install the Real-ESRGAN package into
the standard install location for python packages, and will put GFPGAN into a the standard install location for python packages, and will put GFPGAN into a
subdirectory of "src" in the InvokeAI directory. Upscaling with Real-ESRGAN subdirectory of "src" in the InvokeAI directory. Upscaling with Real-ESRGAN
should "just work" without further intervention. Simply pass the `--upscale` should "just work" without further intervention. Simply indicate the desired scale on
(`-U`) option on the `invoke>` command line, or indicate the desired scale on
the popup in the Web GUI. the popup in the Web GUI.
**GFPGAN** requires a series of downloadable model files to work. These are **GFPGAN** requires a series of downloadable model files to work. These are
@ -41,48 +34,75 @@ reconstruction.
### Upscaling ### Upscaling
`-U : <upscaling_factor> <upscaling_strength>` Open the upscaling dialog by clicking on the "expand" icon located
above the image display area in the Web UI:
The upscaling prompt argument takes two values. The first value is a scaling <figure markdown>
factor and should be set to either `2` or `4` only. This will either scale the ![upscale1](../assets/features/upscale-dialog.png)
image 2x or 4x respectively using different models. </figure>
You can set the scaling stength between `0` and `1.0` to control intensity of There are three different upscaling parameters that you can
the of the scaling. This is handy because AI upscalers generally tend to smooth adjust. The first is the scale itself, either 2x or 4x.
out texture details. If you wish to retain some of those for natural looking
results, we recommend using values between `0.5 to 0.8`.
If you do not explicitly specify an upscaling_strength, it will default to 0.75. The second is the "Denoising Strength." Higher values will smooth out
the image and remove digital chatter, but may lose fine detail at
higher values.
Third, "Upscale Strength" allows you to adjust how the You can set the
scaling stength between `0` and `1.0` to control the intensity of the
scaling. AI upscalers generally tend to smooth out texture details. If
you wish to retain some of those for natural looking results, we
recommend using values between `0.5 to 0.8`.
[This figure](../assets/features/upscaling-montage.png) illustrates
the effects of denoising and strength. The original image was 512x512,
4x scaled to 2048x2048. The "original" version on the upper left was
scaled using simple pixel averaging. The remainder use the ESRGAN
upscaling algorithm at different levels of denoising and strength.
<figure markdown>
![upscaling](../assets/features/upscaling-montage.png){ width=720 }
</figure>
Both denoising and strength default to 0.75.
### Face Restoration ### Face Restoration
`-G : <facetool_strength>` InvokeAI offers alternative two face restoration algorithms,
[GFPGAN](https://github.com/TencentARC/GFPGAN) and
[CodeFormer](https://huggingface.co/spaces/sczhou/CodeFormer). These
algorithms improve the appearance of faces, particularly eyes and
mouths. Issues with faces are less common with the latest set of
Stable Diffusion models than with the original 1.4 release, but the
restoration algorithms can still make a noticeable improvement in
certain cases. You can also apply restoration to old photographs you
upload.
This prompt argument controls the strength of the face restoration that is being To access face restoration, click the "smiley face" icon in the
applied. Similar to upscaling, values between `0.5 to 0.8` are recommended. toolbar above the InvokeAI image panel. You will be presented with a
dialog that offers a choice between the two algorithm and sliders that
allow you to adjust their parameters. Alternatively, you may open the
left-hand accordion panel labeled "Face Restoration" and have the
restoration algorithm of your choice applied to generated images
automatically.
You can use either one or both without any conflicts. In cases where you use
both, the image will be first upscaled and then the face restoration process
will be executed to ensure you get the highest quality facial features.
`--save_orig` Like upscaling, there are a number of parameters that adjust the face
restoration output. GFPGAN has a single parameter, `strength`, which
controls how much the algorithm is allowed to adjust the
image. CodeFormer has two parameters, `strength`, and `fidelity`,
which together control the quality of the output image as described in
the [CodeFormer project
page](https://shangchenzhou.com/projects/CodeFormer/). Default values
are 0.75 for both parameters, which achieves a reasonable balance
between changing the image too much and not enough.
When you use either `-U` or `-G`, the final result you get is upscaled or face [This figure](../assets/features/restoration-montage.png) illustrates
modified. If you want to save the original Stable Diffusion generation, you can the effects of adjusting GFPGAN and CodeFormer parameters.
use the `-save_orig` prompt argument to save the original unaffected version
too.
### Example Usage <figure markdown>
![upscaling](../assets/features/restoration-montage.png){ width=720 }
```bash </figure>
invoke> "superman dancing with a panda bear" -U 2 0.6 -G 0.4
```
This also works with img2img:
```bash
invoke> "a man wearing a pineapple hat" -I path/to/your/file.png -U 2 0.5 -G 0.6
```
!!! note !!! note
@ -95,69 +115,8 @@ invoke> "a man wearing a pineapple hat" -I path/to/your/file.png -U 2 0.5 -G 0.6
process is complete. While the image generation is taking place, you will still be able to preview process is complete. While the image generation is taking place, you will still be able to preview
the base images. the base images.
If you wish to stop during the image generation but want to upscale or face
restore a particular generated image, pass it again with the same prompt and
generated seed along with the `-U` and `-G` prompt arguments to perform those
actions.
## CodeFormer Support
This repo also allows you to perform face restoration using
[CodeFormer](https://github.com/sczhou/CodeFormer).
In order to setup CodeFormer to work, you need to download the models like with
GFPGAN. You can do this either by running `invokeai-configure` or by manually
downloading the
[model file](https://github.com/sczhou/CodeFormer/releases/download/v0.1.0/codeformer.pth)
and saving it to `ldm/invoke/restoration/codeformer/weights` folder.
You can use `-ft` prompt argument to swap between CodeFormer and the default
GFPGAN. The above mentioned `-G` prompt argument will allow you to control the
strength of the restoration effect.
### CodeFormer Usage
The following command will perform face restoration with CodeFormer instead of
the default gfpgan.
`<prompt> -G 0.8 -ft codeformer`
### Other Options
- `-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
higher accuacy to your original face.
The following command will perform face restoration with CodeFormer. CodeFormer
will output a result that is closely matching to the input face.
`<prompt> -G 1.0 -ft codeformer -cf 0.9`
The following command will perform face restoration with CodeFormer. CodeFormer
will output a result that is the best restoration possible. This may deviate
slightly from the original face. This is an excellent option to use in
situations when there is very little facial data to work with.
`<prompt> -G 1.0 -ft codeformer -cf 0.1`
## Fixing Previously-Generated Images
It is easy to apply face restoration and/or upscaling to any
previously-generated file. Just use the syntax
`!fix path/to/file.png <options>`. For example, to apply GFPGAN at strength 0.8
and upscale 2X for a file named `./outputs/img-samples/000044.2945021133.png`,
just run:
```bash
invoke> !fix ./outputs/img-samples/000044.2945021133.png -G 0.8 -U 2
```
A new file named `000044.2945021133.fixed.png` will be created in the output
directory. Note that the `!fix` command does not replace the original file,
unlike the behavior at generate time.
## How to disable ## How to disable
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
`--no_upscale` options, respectively. `--no_esrgan` options, respectively.

104
docs/features/PROMPTS.md
View File

@ -4,77 +4,12 @@ title: Prompting-Features
# :octicons-command-palette-24: Prompting-Features # :octicons-command-palette-24: Prompting-Features
## **Reading Prompts from a File**
You can automate `invoke.py` by providing a text file with the prompts you want
to run, one line per prompt. The text file must be composed with a text editor
(e.g. Notepad) and not a word processor. Each line should look like what you
would type at the invoke> prompt:
```bash
"a beautiful sunny day in the park, children playing" -n4 -C10
"stormy weather on a mountain top, goats grazing" -s100
"innovative packaging for a squid's dinner" -S137038382
```
Then pass this file's name to `invoke.py` when you invoke it:
```bash
python scripts/invoke.py --from_file "/path/to/prompts.txt"
```
You may also read a series of prompts from standard input by providing
a filename of `-`. For example, here is a python script that creates a
matrix of prompts, each one varying slightly:
```bash
#!/usr/bin/env python
adjectives = ['sunny','rainy','overcast']
samplers = ['k_lms','k_euler_a','k_heun']
cfg = [7.5, 9, 11]
for adj in adjectives:
for samp in samplers:
for cg in cfg:
print(f'a {adj} day -A{samp} -C{cg}')
```
Its output looks like this (abbreviated):
```bash
a sunny day -Aklms -C7.5
a sunny day -Aklms -C9
a sunny day -Aklms -C11
a sunny day -Ak_euler_a -C7.5
a sunny day -Ak_euler_a -C9
...
a overcast day -Ak_heun -C9
a overcast day -Ak_heun -C11
```
To feed it to invoke.py, pass the filename of "-"
```bash
python matrix.py | python scripts/invoke.py --from_file -
```
When the script is finished, each of the 27 combinations
of adjective, sampler and CFG will be executed.
The command-line interface provides `!fetch` and `!replay` commands
which allow you to read the prompts from a single previously-generated
image or a whole directory of them, write the prompts to a file, and
then replay them. Or you can create your own file of prompts and feed
them to the command-line client from within an interactive session.
See [Command-Line Interface](CLI.md) for details.
---
## **Negative and Unconditioned Prompts** ## **Negative and Unconditioned Prompts**
Any words between a pair of square brackets will instruct Stable Diffusion to Any words between a pair of square brackets will instruct Stable
attempt to ban the concept from the generated image. Diffusion to attempt to ban the concept from the generated image. The
same effect is achieved by placing words in the "Negative Prompts"
textbox in the Web UI.
```text ```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.
@ -87,7 +22,9 @@ Here's a prompt that depicts what it does.
original prompt: original prompt:
`#!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` `#!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"`
`#!bash parameters: steps=20, dimensions=512x768, CFG=7.5, Scheduler=k_euler_a, seed=1654590180`
<figure markdown> <figure markdown>
@ -99,7 +36,8 @@ 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 influence the image not to have a woman by putting [woman] in the prompt, like
this: 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]"`
(same parameters as above)
<figure markdown> <figure markdown>
@ -110,7 +48,8 @@ this:
That's nice - but say we also don't want the image to be quite so blue. We can 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]: 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]"`
(same parameters as above)
<figure markdown> <figure markdown>
@ -121,7 +60,8 @@ add "blue" to the list of negative prompts, so it's now [woman blue]:
Getting close - but there's no sense in having a saddle when our horse doesn't 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]. 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]"`
(same parameters as above)
<figure markdown> <figure markdown>
@ -261,19 +201,6 @@ Prompt2prompt `.swap()` is not compatible with xformers, which will be temporari
The `prompt2prompt` code is based off The `prompt2prompt` code is based off
[bloc97's colab](https://github.com/bloc97/CrossAttentionControl). [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:
```bash
invoke> a fluffy cat eating a hotdog
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 "" ### Escaping parantheses () and speech marks ""
If the model you are using has parentheses () or speech marks "" as part of its If the model you are using has parentheses () or speech marks "" as part of its
@ -374,6 +301,5 @@ summoning up the concept of some sort of scifi creature? Let's find out.
Indeed, removing the word "hybrid" produces an image that is more like what we'd Indeed, removing the word "hybrid" produces an image that is more like what we'd
expect. expect.
In conclusion, prompt blending is great for exploring creative space, but can be In conclusion, prompt blending is great for exploring creative space,
difficult to direct. A forthcoming release of InvokeAI will feature more but takes some trial and error to achieve the desired effect.
deterministic prompt weighting.

10
docs/features/WEB.md
View File

@ -299,14 +299,6 @@ initial image" icons are located.
See the [Unified Canvas Guide](UNIFIED_CANVAS.md) See the [Unified Canvas Guide](UNIFIED_CANVAS.md)
## Parting remarks
This concludes the walkthrough, but there are several more features that you can
explore. Please check out the [Command Line Interface](CLI.md) documentation for
further explanation of the advanced features that were not covered here.
The WebUI is only rapid development. Check back regularly for updates!
## Reference ## Reference
### Additional Options ### Additional Options
@ -349,11 +341,9 @@ the settings configured in the toolbar.
See below for additional documentation related to each feature: See below for additional documentation related to each feature:
- [Core Prompt Settings](./CLI.md)
- [Variations](./VARIATIONS.md) - [Variations](./VARIATIONS.md)
- [Upscaling](./POSTPROCESS.md#upscaling) - [Upscaling](./POSTPROCESS.md#upscaling)
- [Image to Image](./IMG2IMG.md) - [Image to Image](./IMG2IMG.md)
- [Inpainting](./INPAINTING.md)
- [Other](./OTHER.md) - [Other](./OTHER.md)
#### Invocation Gallery #### Invocation Gallery

11
docs/features/index.md
View File

@ -17,21 +17,12 @@ a single convenient digital artist-optimized user interface.
### * [Prompt Engineering](PROMPTS.md) ### * [Prompt Engineering](PROMPTS.md)
Get the images you want with the InvokeAI prompt engineering language. Get the images you want with the InvokeAI prompt engineering language.
## * [Post-Processing](POSTPROCESS.md)
Restore mangled faces and make images larger with upscaling. Also see the [Embiggen Upscaling Guide](EMBIGGEN.md).
## * The [Concepts Library](CONCEPTS.md) ## * The [Concepts Library](CONCEPTS.md)
Add custom subjects and styles using HuggingFace's repository of embeddings. Add custom subjects and styles using HuggingFace's repository of embeddings.
### * [Image-to-Image Guide for the CLI](IMG2IMG.md) ### * [Image-to-Image Guide](IMG2IMG.md)
Use a seed image to build new creations in the CLI. Use a seed image to build new creations in the CLI.
### * [Inpainting Guide for the CLI](INPAINTING.md)
Selectively erase and replace portions of an existing image in the CLI.
### * [Outpainting Guide for the CLI](OUTPAINTING.md)
Extend the borders of the image with an "outcrop" function within the CLI.
### * [Generating Variations](VARIATIONS.md) ### * [Generating Variations](VARIATIONS.md)
Have an image you like and want to generate many more like it? Variations Have an image you like and want to generate many more like it? Variations
are the ticket. are the ticket.

3
docs/index.md
View File

@ -137,11 +137,8 @@ This method is recommended for those familiar with running Docker containers
### Image Management ### Image Management
- [Image2Image](features/IMG2IMG.md) - [Image2Image](features/IMG2IMG.md)
- [Inpainting](features/INPAINTING.md)
- [Outpainting](features/OUTPAINTING.md)
- [Adding custom styles and subjects](features/CONCEPTS.md) - [Adding custom styles and subjects](features/CONCEPTS.md)
- [Upscaling and Face Reconstruction](features/POSTPROCESS.md) - [Upscaling and Face Reconstruction](features/POSTPROCESS.md)
- [Embiggen upscaling](features/EMBIGGEN.md)
- [Other Features](features/OTHER.md) - [Other Features](features/OTHER.md)
<!-- separator --> <!-- separator -->