Skip to content

Textual Inversions

Using Textual Inversion Files#

Textual inversion (TI) files are small models that customize the output of Stable Diffusion image generation. They can augment SD with specialized subjects and artistic styles. They are also known as "embeds" in the machine learning world.

Each TI file introduces one or more vocabulary terms to the SD model. These are known in InvokeAI as "triggers." Triggers are denoted using angle brackets as in "<trigger-phrase>". The two most common type of TI files that you'll encounter are .pt and .bin files, which are produced by different TI training packages. InvokeAI supports both formats, but its built-in TI training system produces .pt.

Hugging Face has amassed a large library of >800 community-contributed TI files covering a broad range of subjects and styles. You can also install your own or others' TI files by placing them in the designated directory for the compatible model type

An Example#

Here are a few examples to illustrate how it works. All these images were generated using the legacy command-line client and the Stable Diffusion 1.5 model:

Japanese gardener Japanese gardener <ghibli-face> Japanese gardener <hoi4-leaders> Japanese gardener <cartoona-animals>

You can also combine styles and concepts:

A portrait of <alf> in <cartoona-animal> style

Installing your Own TI Files#

You may install any number of .pt and .bin files simply by copying them into the embedding directory of the corresponding InvokeAI models directory (usually invokeai in your home directory). For example, you can simply move a Stable Diffusion 1.5 embedding file to the sd-1/embedding folder. Be careful not to overwrite one file with another. For example, TI files generated by the Hugging Face toolkit share the named learned_embedding.bin. You can rename these, or use subdirectories to keep them distinct.

At startup time, InvokeAI will scan the various embedding directories and load any TI files it finds there for compatible models. At startup you will see a message similar to this one:

>> Current embedding manager terms: <HOI4-Leader>, <princess-knight>
To use these when generating, simply type the < key in your prompt to open the Textual Inversion WebUI and select the embedding you'd like to use. This UI has type-ahead support, so you can easily find supported embeddings.