---
license: creativeml-openrail-m
---

# Ross Draws stable diffusion model set

Original artist: Ross Draws\
Patreon: https://www.patreon.com/Rossdraws

## Basic explanation

Token and Class words are what guide the AI to produce images similar to the trained style/object/character.
Include any mix of these words in the prompt to produce verying results, or exclude them to have a less pronounced effect.
There is usually at least a slight stylistic effect even without the words, but it is recommended to include at least one.
Adding token word/phrase class word/phrase at the start of the prompt in that order produces results most similar to the trained concept, but they can be included elsewhere as well. Some models produce better results when not including all token/class words.

## Usage

When using this model by itself, it is not necessary to use any keywords, but they will strengthen the style effect.

Rossmix produces the best results, while ross-any also works quite well. Ross based on wd has a more of an illustration feel, but works best when mixed with other models.

Rossmix and ross-any may work better with clip-skip 2, while ross most likely works better with clip skip 1.

## Model: ross.ckpt

token: m_ross\
class: illustration style\
base: waifu diffusion 1.3-full\
images: 120\
steps: 12000

## Model: ross-any.ckpt

token: m_ross\
class: illustration style\
base: anything v3\
images: 120\
steps: 12000

## Model: rossmix.ckpt

token: m_ross\
info: custom berrymix using ross-any

## Example images

Example images also include 3 extra mixes that include ross or ross-any.

Positive: `m_ross, (illustration), (masterpiece), ((best quality)), (ultra-detailed), (official art), ((portrait of a beautiful girl)), upper body`\
Negative: `lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name`

Ground truth
![base](base.png)

Examples
![grid1](img1.png)
![grid2](img2.png)

768x1024 without highres fix
![grid3](img3.png)