1. Basic concept
embedding, also known as textual inversion, Chinese name "embedding or text inversion"
In computer science, embedding is the process of mapping high-dimensional data to low-dimensional space. In image processing, embedding is often used to convert images into vector representations for machine learning and deep learning tasks. When using stable diffusion for painting, embedding can be used to convert the input image into a vector representation, so that the algorithm can process it and generate a new image. This technique could allow algorithms to process image data more efficiently and improve the quality and accuracy of the resulting images.
2. Function
In layman's terms, it is to package the prompt words
. For example:
generate a picture of Emma Watson
There will be a lot of descriptors, or even no description.
Use embddings to enter "masterpiece, high-quality, EmWat69" in the prompt box for writing descriptors to generate the picture above.
3. Open embedding in the WebUI
and click " on the WebUI page Show extra networks"
and then select the required embedding in the Textual Inversion tab, click,
It will appear in the Prompt box for writing descriptors that appear above, together with other descriptors, such as "masterpiece, high quality"
Click generate, and the desired style of picture will be generated quickly without writing a lot of descriptors.
4. Embedding file storage location
Take D disk as an example
D:\stable-diffusion-webui\embeddings
5. Download the embedding file
Open
the filter button on the right of https://civitai.com/ - Textural Inversion
Then you can select the corresponding screen and click, and then click Download Latest on the corresponding page
