From 2e9c15711b6423381af8de2bf71fbb15ae0b9949 Mon Sep 17 00:00:00 2001 From: psychedelicious <4822129+psychedelicious@users.noreply.github.com> Date: Sun, 19 Feb 2023 09:34:28 +1100 Subject: [PATCH] docs(ti): add using & troubleshooting sections --- docs/features/TEXTUAL_INVERSION.md | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/docs/features/TEXTUAL_INVERSION.md b/docs/features/TEXTUAL_INVERSION.md index d472d04efa..c0b34e3f7c 100644 --- a/docs/features/TEXTUAL_INVERSION.md +++ b/docs/features/TEXTUAL_INVERSION.md @@ -250,6 +250,24 @@ invokeai-ti \ --only_save_embeds ``` +## Using Embeddings + +After training completes, the resultant embeddings will be saved into your `$INVOKEAI_ROOT/embeddings//learned_embeds.bin`. + +These will be automatically loaded when you start InvokeAI. + +Add the trigger word, surrounded by angle brackets, to use that embedding. For example, if your trigger word was `terence`, use `` in prompts. This is the same syntax used by the HuggingFace concepts library. + +**Note:** `.pt` embeddings do not require the angle brackets. + +## Troubleshooting + +### `Cannot load embedding for . It was trained on a model with token dimension 1024, but the current model has token dimension 768` + +Messages like this indicate you trained the embedding on a different base model than the currently selected one. + +For example, in the error above, the training was done on SD2.1 (768x768) but it was used on SD1.5 (512x512). + ## Reading For more information on textual inversion, please see the following