---
license: creativeml-openrail-m
tags:
- stable-diffusion
- text-to-image
---
The embeddings in this repository were trained for the 768px [Stable Diffusion v2.0](https://huggingface.co/stabilityai/stable-diffusion-2) model. The embeddings should work on any model that uses SD v2.0 as a base.
**Knollingcase v1**
The v1 embeddings were trained for 4000 iterations with a batch size of 2, a text dropout of 10%, & 16 vectors using Automatic1111's WebUI. A total of 69 training images with high quality captions were used.
**Knollingcase v2**
The v2 embeddings were trained for 5000 iterations with a batch size of 4 and a text dropout of 10%, & 16 vectors using Automatic1111's WebUI. A total of 78 training images with high quality captions were used.
**Knollingcase v3**
The v3 embeddings were trained for 4000-6250 iterations with a batch size of 4 and a text dropout of 10%, & 16 vectors using Automatic1111's WebUI. A total of 86 training images with high quality captions were used.
* [Full Image](https://huggingface.co/ProGamerGov/knollingcase-embeddings-sd-v2-0/resolve/main/cruise_ship_on_wave_kc16-v3-6250.png)
**Knollingcase v4**
The v4 embeddings were trained for 4000-6250 iterations with a batch size of 4 and a text dropout of 10%, using Automatic1111's WebUI. A total of 116 training images with high quality captions were used.
**Usage**
To use the embeddings, download and then rename the file to whatever trigger word you want to use.
The knollingcase style is considered to be a concept inside a sleek (sometimes scifi) display case with transparent walls, and a minimalistic background.
Suggested prompt words are: "photorealistic", "octane render", & "very detailed".
Suggested negative prompts words are: "blurry" and you can add "toy" to make outputs more realistic looking.
Suggested prompts:
```
, micro-details, photorealism, photorealistic,
# Negative prompts
blurry, toy, cartoon, animated, underwater
```
```
photorealistic , very detailed, scifi case,
, very detailed, scifi transparent case,
```