StableDiffusionWebUI: Embeddings
Preface
Embeddings and text inversion both refer to textual embeddings.
They can be simply understood as a collection of prompts,
used in both negative and positive prompts.
Using Embeddings
Installation
After downloading embeddings, place them in the stable-diffusion-webui/embeddings directory.
Usage
Under the embeddings tab, select the embedding you want to use and click on it.
It will automatically populate the embedding into the positive or negative prompt field.
If newly added embeddings don’t appear in the list,
click the refresh button on the right side.
Embeddings - Positive Effect
Positive Prompt
(best quality:1), (high quality:1), detailed/(extreme, highly, ultra/), realistic, 1girl/(beautiful, delicate, perfect/)
Sampler
DPM++ 2M
Sampling Steps
20
Seed
1199889759
Checkpoint
anythingv5nijimix
Normal Effect
embeddings-youngv2
Link: https://civitai.com/models/65214?modelVersionId=94703
Description: Generates younger-looking characters
embeddings-youngerv2
Link: https://civitai.com/models/65214?modelVersionId=95275
Description: Generates even younger-looking characters
embeddings-youngeestv2
Link: https://civitai.com/models/65214?modelVersionId=95528
Description: Generates the youngest-looking characters
Embeddings - Negative Effect
The above demonstrates using embeddings as positive prompts.
In practice, using embeddings as positive prompts has become less common,
since other methods can achieve similar or better results.
A more common use of embeddings is as negative prompts.
For example, the hands in the images above have issues. Let’s try some hand-related negative prompt embeddings
and see the results.
embeddings-youngerv2-NegativeHand
Link: https://civitai.com/models/56519/negativehand-negative-embedding
Description: A negative prompt embedding for hands, aimed at generating better hand quality
embeddings-youngeestv2-NegativeHand
Summary
Embeddings are currently mainly used as negative prompts
to avoid undesirable artifacts in generated images.
SDWebUI
|—Link: https://sdwebui.ai/?from=vq
|—Authentic Stable Diffusion WebUI V1.10.1~
|—Top-tier 4090 GPU, premium members get exclusive single 4090 card for image generation~
|—Supports Mac client, Windows client, and Web online usage~
|—Innovative instant model transfer feature, instantly use local models~
|—Supports txt2img, img2img, extras, and PNG info
|—Supports CLIP interrogation and DeepBooru interrogation
|—Supports Hires.fix with 21 built-in upscaling models
|—Supports ADetailer with 11 built-in repair models
|—Supports ControlNet with 44 built-in preprocessors and 68 built-in models
|—Supports super-resolution upscaling (Tiled Diffusion, Demo Fusion, Tiled VAE)
|—Supports old photo restoration with 21 built-in upscaling models, plus GFPGAN and CodeFormer restoration models
|—Built-in 2 common Styles, 11 popular Checkpoint models, 7 popular LoRA models, 14 common embeddings
|—Built-in oldsix prompt plugin
|—Built-in 23-lesson beginner tutorial