You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This guide will show you how to train a [`runwayml/stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) model with Textual Inversion. All the training scripts for Textual Inversion used in this guide can be found [here](https://github.com/huggingface/diffusers/tree/main/examples/textual_inversion) if you're interested in taking a closer look at how things work under the hood.
25
25
@@ -157,7 +157,7 @@ If you're interested in following along with your model training progress, you c
157
157
158
158
## Inference
159
159
160
-
Once you have trained a model, you can use it for inference with the [`StableDiffusionPipeline]. Make sure you include the `placeholder_token` in your prompt, in this case, it is `<cat-toy>`.
160
+
Once you have trained a model, you can use it for inference with the [`StableDiffusionPipeline`]. Make sure you include the `placeholder_token` in your prompt, in this case, it is `<cat-toy>`.
Usually, text prompts are tokenized into an embedding before being passed to a model, which is often a transformer. Textual Inversion does something similar, but it learns a new token embedding, `v*`, from a special token `S*` in the diagram above. The model output is used to condition the diffusion model, which helps the diffusion model understand the prompt and new concepts from just a few example images.
214
214
215
-
To do this, Textual Inversion uses a generator model and noisy versions of the training images. The generator tries to predict less noisy versions of the images, and the token embedding `v*` is optimized based on how well the generator does. If the token embedding successfully captures the new concept, it gives more useful information to the diffusion model and helps create clearer images with less noise. This optimization process typically occurs after several thousand steps of exposure to a variety of prompt and image variants.
215
+
To do this, Textual Inversion uses a generator model and noisy versions of the training images. The generator tries to predict less noisy versions of the images, and the token embedding `v*` is optimized based on how well the generator does. If the token embedding successfully captures the new concept, it gives more useful information to the diffusion model and helps create clearer images with less noise. This optimization process typically occurs after several thousand steps of exposure to a variety of prompt and image variants.
0 commit comments