yiff_toolkit / README.md
k4d3's picture
awoo
b05b0bc
|
raw
history blame
44.3 kB
---
license: wtfpl
datasets:
- k4d3/furry
language:
- en
tags:
- not-for-all-audiences
---
<!--markdownlint-disable MD033 MD038 -->
# Hotdogwolf's Yiff Toolkit
The Yiff Toolkit is a comprehensive set of tools designed to enhance your creative process in the realm of furry art. From refining artist styles to generating unique characters, the Yiff Toolkit provides a range of tools to help you cum.
> NOTE: You can click on any image in this README to be instantly teleported next to the original resolution version of it! If you want the metadata for a picture and it isn't there, you need to delete the letter e before the .png in the link! If a metadata containing original image is missing, please let me know!
## Table of Contents
<div style="background-color: lightyellow; padding: 10px;">
<details>
<summary>Click to reveal table of contents</summary>
- [Hotdogwolf's Yiff Toolkit](#hotdogwolfs-yiff-toolkit)
- [Table of Contents](#table-of-contents)
- [Dataset Tools](#dataset-tools)
- [Dataset Preparation](#dataset-preparation)
- [Create the `training_dir` Directory](#create-the-training_dir-directory)
- [Grabber](#grabber)
- [Manual Method](#manual-method)
- [LoRA Training Guide](#lora-training-guide)
- [Installation Tips](#installation-tips)
- [Pony Training](#pony-training)
- [Download Pony in Diffusers Format](#download-pony-in-diffusers-format)
- [Sample Prompt File](#sample-prompt-file)
- [Training Commands](#training-commands)
- [`--lowram`](#--lowram)
- [`--pretrained_model_name_or_path`](#--pretrained_model_name_or_path)
- [`--output_dir`](#--output_dir)
- [`--train_data_dir`](#--train_data_dir)
- [`--resolution`](#--resolution)
- [`--enable_bucket`](#--enable_bucket)
- [`--min_bucket_reso` and `--max_bucket_reso`](#--min_bucket_reso-and---max_bucket_reso)
- [`--network_alpha`](#--network_alpha)
- [`--save_model_as`](#--save_model_as)
- [`--network_module`](#--network_module)
- [`--network_args`](#--network_args)
- [`--network_dropout`](#--network_dropout)
- [`--lr_scheduler`](#--lr_scheduler)
- [`--lr_scheduler_num_cycles`](#--lr_scheduler_num_cycles)
- [`--learning_rate`](#--learning_rate)
- [`--unet_lr`](#--unet_lr)
- [`--text_encoder_lr`](#--text_encoder_lr)
- [`--network_dim`](#--network_dim)
- [`--output_name`](#--output_name)
- [`--scale_weight_norms`](#--scale_weight_norms)
- [`--no_half_vae`](#--no_half_vae)
- [`--save_every_n_epochs`](#--save_every_n_epochs)
- [`--mixed_precision`](#--mixed_precision)
- [`--save_precision`](#--save_precision)
- [`--caption_extension`](#--caption_extension)
- [`--cache_latents` and `--cache_latents_to_disk`](#--cache_latents-and---cache_latents_to_disk)
- [`--optimizer_type`](#--optimizer_type)
- [`--dataset_repeats`](#--dataset_repeats)
- [`--max_train_steps`](#--max_train_steps)
- [`--shuffle_caption`](#--shuffle_caption)
- [`--sdpa` or `--xformers` or `--mem_eff_attn`](#--sdpa-or---xformers-or---mem_eff_attn)
- [`--sample_prompts` and `--sample_sampler` and `--sample_every_n_steps`](#--sample_prompts-and---sample_sampler-and---sample_every_n_steps)
- [CosXL Training](#cosxl-training)
- [Embeddings for 1.5 and SDXL](#embeddings-for-15-and-sdxl)
- [ComfyUI Walkthrough any%](#comfyui-walkthrough-any)
- [AnimateDiff for Masochists](#animatediff-for-masochists)
- [Stable Cascade Furry Bible](#stable-cascade-furry-bible)
- [Resonance Cascade](#resonance-cascade)
- [SDXL Furry Bible](#sdxl-furry-bible)
- [Some Common Knowledge Stuff](#some-common-knowledge-stuff)
- [Pony Diffusion V6](#pony-diffusion-v6)
- [Requirements](#requirements)
- [Positive Prompt Stuff](#positive-prompt-stuff)
- [Negative Prompt Stuff](#negative-prompt-stuff)
- [SeaArt Furry](#seaart-furry)
- [Pony Diffusion V6 LoRAs](#pony-diffusion-v6-loras)
- [Concept Loras](#concept-loras)
- [space-v1e500](#space-v1e500)
- [spacengine-v1e500](#spacengine-v1e500)
- [Artist/Style LoRAs](#artiststyle-loras)
- [blp-v1e400](#blp-v1e400)
- [blue\_frost](#blue_frost)
- [butterchalk-v3e400](#butterchalk-v3e400)
- [cecily\_lin-v1e37](#cecily_lin-v1e37)
- [chunie\_ponyxl\_v1e5](#chunie_ponyxl_v1e5)
- [cooliehigh-v1e45](#cooliehigh-v1e45)
- [dagasi-v1e134](#dagasi-v1e134)
- [darkgem\_ponyxl\_v1e4](#darkgem_ponyxl_v1e4)
- [furry\_sticker-v1e250](#furry_sticker-v1e250)
- [goronic-v1e1](#goronic-v1e1)
- [greg\_rutkowski-v1e400](#greg_rutkowski-v1e400)
- [hamgas-v1e400](#hamgas-v1e400)
- [honovy\_ponyxl\_v1e4](#honovy_ponyxl_v1e4)
- [jinxit-v1e10](#jinxit-v1e10)
- [kame\_3-v1e80](#kame_3-v1e80)
- [louart-v1e10](#louart-v1e10)
- [realistic+scale\_iridescence-v3e500](#realisticscale_iridescence-v3e500)
- [skecchiart-v1e134](#skecchiart-v1e134)
- [spectrumshift-v1e400](#spectrumshift-v1e400)
- [squishy-v1e10](#squishy-v1e10)
- [whisperingfornothing-v1e58](#whisperingfornothing-v1e58)
- [wjs07-v1e200](#wjs07-v1e200)
- [wolfy-nail-v1e400](#wolfy-nail-v1e400)
- [woolrool\_ponyxl\_v1e4](#woolrool_ponyxl_v1e4)
- [Character LoRAs](#character-loras)
- [amalia-v2e400](#amalia-v2e400)
- [amicus-v1e200](#amicus-v1e200)
- [auroth-v1e250](#auroth-v1e250)
- [blaidd-v1e400](#blaidd-v1e400)
- [martlet-v1e200](#martlet-v1e200)
- [ramona-v1e400](#ramona-v1e400)
- [tibetan-v2e500](#tibetan-v2e500)
- [veemon-v1e400](#veemon-v1e400)
- [hoodwink-v1e400](#hoodwink-v1e400)
- [jayjay-v1e400](#jayjay-v1e400)
- [foxparks-v2e134](#foxparks-v2e134)
- [lovander-v3e10](#lovander-v3e10)
- [skiltaire-v1e400](#skiltaire-v1e400)
- [chillet-v3e10](#chillet-v3e10)
- [maliketh-v1e1](#maliketh-v1e1)
- [wickerbeast-v1e500](#wickerbeast-v1e500)
- [Satisfied Customers](#satisfied-customers)
</details>
</div>
## Dataset Tools
I have uploaded all of the little handy Python scripts I use to [/dataset_tools](https://huggingface.co/k4d3/yiff_toolkit/tree/main/dataset_tools). They are pretty self explanatory by just the file name but almost all of them contain an AI generated description. If you want to use them you will need to edit the path to your `training_dir` folder, the variable will be called `path` or `directory` and look something like this:
```py
def main():
path = 'C:\\Users\\kade\\Desktop\\training_dir_staging'
```
Don't be afraid of editing Python scripts, unlike the real snake, these won't bite!
---
## Dataset Preparation
Before you begin collecting your dataset you will need to decide what you want to teach the model, it can be a character, a style or a new concept.
For now let's imagine you want to teach your model *wickerbeasts* so you can generate your VRChat avatar every night.
### Create the `training_dir` Directory
Before starting we need a directory where we'll organize our datasets. Open up a terminal by pressing `Win + R` and typing in `pwsh`. We will also be using [git](https://git-scm.com/download/win) and [huggingface](https://huggingface.co/) to version control our smut. For brevity I'll refrain from giving you a tutorial on both. Once you have your newly created dataset on HF ready lets clone it. Make sure you change `user` in the first line to your HF username!
```pwsh
git clone [email protected]:/datasets/user/training_dir C:\training_dir
cd C:\training_dir
git branch wickerbeast
git checkout wickerbeast
```
Let's continue with downloading some *wickerbeast* data but don't close the terminal window just yet, for this we'll make good use of the furry <abbr title="image board">booru</abbr> [e621.net](https://e621.net/). There are two nice ways to download data from this site with the metadata intact, I'll start with the fastest and then I will explain how you can selectively browse around the site and get the images you like one by one.
### Grabber
[Grabber](https://github.com/Bionus/imgbrd-grabber) makes your life easier when trying to compile datasets quickly from imageboards.
[![A screenshot of Grabber.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/tutorial/grabber1.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/tutorial/grabber1.png)
Clicking on the `Add` button on the Download tab lets you add a `group` which will get downloaded, `Tags` will be the where you can type in the search parameters like you would on e621.net, so for example the string `wickerbeast solo -comic -meme -animated order:score` will search for solo wickerbeast pictures without including comics, memes, and animated posts in descending order of their scores. For training SDXL LoRAs you usually won't need more than 50 images, but you should set the solo group to `40` and add a new group with `-solo` instead of `solo` and set the `Image Limit` to `10` for it to include some images with other characters in it. This will help the model learn a lot better!
You should also enable `Separate log files` for e621, this will download the metadata automatically alongside the pictures.
[![Another screenshot of Grabber.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/tutorial/grabber2.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/tutorial/grabber2.png)
For Pony I've set up the Text file content like so: `rating_%rating%, %all:separator=^, %` for other models you might want to replace `rating_%rating%` with just `%rating%`.
You should also set the `Folder` into which the images will get downloaded. Let's use `C:\training_dir\1_wickerbeast` for both groups.
Now you are ready to right-click on each group and download the images.
---
### Manual Method
This method requires a browser extension like [ViolentMonkey](https://violentmonkey.github.io/) and the following UserScript:
<div style="background-color: lightyellow; padding: 10px;">
<details>
<summary>Click to reveal userscript.</summary>
```js
// ==UserScript==
// @name e621 JSON Button
// @namespace https://cringe.live
// @version 1.0
// @description Adds a JSON button next to the download button on e621.net
// @author _ka_de
// @match https://e621.net/*
// @match https://e6ai.net/*
// @grant none
// ==/UserScript==
(function() {
'use strict';
function constructJSONUrl() {
// Get the current URL
var currentUrl = window.location.href;
// Extract the post ID from the URL
var postId = currentUrl.match(/^https?:\/\/(?:e621\.net|e6ai\.net)\/posts\/(\d+)/)[1];
// Check the hostname
var hostname = window.location.hostname;
// Construct the JSON URL based on the hostname
var jsonUrl = 'https://' + hostname + '/posts/' + postId + '.json';
return jsonUrl;
}
function createJSONButton() {
// Create a new button element
var jsonButton = document.createElement('a');
// Set the attributes for the button
jsonButton.setAttribute('class', 'button btn-info');
var jsonUrl = constructJSONUrl();
// Set the JSON URL as the button's href attribute
jsonButton.setAttribute('href', jsonUrl);
// Set the inner HTML for the button
jsonButton.innerHTML = '<i class="fa-solid fa-angle-double-right"></i><span>JSON</span>';
// Find the container where we want to insert the button
var container = document.getElementById('image-extra-controls');
// Insert the button after the download button
container.insertBefore(jsonButton, container.children[0].nextSibling);
}
// Run the function to create the JSON button
createJSONButton();
})();
```
</details>
</div>
This will put a link to the JSON next to the download button on e621.net and e6ai.net and you can use [this](https://huggingface.co/k4d3/yiff_toolkit/blob/main/dataset_tools/e621%20JSON%20to%20txt.ipynb) Python script to convert them to caption files, it uses the `rating_` prefix before `safe/questionable/explicit` because.. you've guessed it, Pony! It also lets you ignore the tags you add into `ignored_tags` using the `r"\btag\b",` syntax, just replace `tag` with the tag you want it to skip.
---
## LoRA Training Guide
### Installation Tips
---
Firstly, download kohya_ss' [sd-scripts](https://github.com/kohya-ss/sd-scripts), you need to set up your environment either like [this](https://github.com/kohya-ss/sd-scripts?tab=readme-ov-file#windows-installation) tells you for Windows, or if you are using Linux or Miniconda on Windows, you are probably smart enough to figure out the installation for it. I recommend always installing the latest [PyTorch](https://pytorch.org/get-started/locally/) in the virtual environment you are going to use, which at the time of writing is `2.2.2`. I hope future me has faster PyTorch!
---
⚠️ **TODO:** Awoo this section.
### Pony Training
---
I'm not going to lie, it is a bit complicated to explain everything. But here is my best attempt going through some "basic" stuff and almost all lines in order.
#### Download Pony in Diffusers Format
I'm using the diffusers version for training I converted, you can download it using `git`.
```bash
git clone https://huggingface.co/k4d3/ponydiffusers
```
---
#### Sample Prompt File
A sample prompt file is used during training to sample images. A sample prompt for example might look like this for Pony:
```py
# anthro female kindred
score_9, score_8_up, score_7_up, score_6_up, rating_explicit, source_furry, solo, female anthro kindred, mask, presenting, white pillow, bedroom, looking at viewer, detailed background, amazing_background, scenery porn, realistic, photo --n low quality, worst quality, blurred background, blurry, simple background --w 1024 --h 1024 --d 1 --l 6.0 --s 40
# anthro female wolf
score_9, score_8_up, score_7_up, score_6_up, rating_explicit, source_furry, solo, anthro female wolf, sexy pose, standing, gray fur, brown fur, canine pussy, black nose, blue eyes, pink areola, pink nipples, detailed background, amazing_background, realistic, photo --n low quality, worst quality, blurred background, blurry, simple background --w 1024 --h 1024 --d 1 --l 6.0 --s 40
```
Please note that sample prompts should not exceed 77 tokens, you can use [Count Tokens in Sample Prompts](https://huggingface.co/k4d3/yiff_toolkit/blob/main/dataset_tools/Count%20Tokens%20in%20Sample%20Prompts.ipynb) from [/dataset_tools](https://huggingface.co/k4d3/yiff_toolkit/tree/main/dataset_tools) to analyze your prompts.
If you are training with multiple GPUs, ensure that the total number of prompts is divisible by the number of GPUs without any remainder.
---
#### Training Commands
<div style="background-color: lightyellow; padding: 10px;">
<details>
<summary>Click to reveal training commands.</summary>
##### `--lowram`
If you are running running out of system memory like I do with 2 GPUs and a really fat model that gets loaded into it per GPU, this option will help you save a bit of it and might get you out of OOM hell.
---
##### `--pretrained_model_name_or_path`
The directory containing the checkpoint you just downloaded. I recommend closing the path if you are using a local model with a `/`.
```py
--pretrained_model_name_or_path="/ponydiffusers/" \
```
---
##### `--output_dir`
This is where all the saved epochs or steps will be saved, including the last one. If y
```py
--output_dir="/output_dir" \
```
---
##### `--train_data_dir`
The directory containing the dataset. We prepared this earlier together.
```py
--train_data_dir="/training_dir" \
```
---
##### `--resolution`
Always set this to match the model's resolution, which in Pony's case it is 1024x1024. If you can't fit into the VRAM, you can decrease it to `512,512` as a last resort.
```py
--resolution="1024,1024" \
```
---
##### `--enable_bucket`
⚠️
```py
--enable_bucket \
```
---
##### `--min_bucket_reso` and `--max_bucket_reso`
⚠️
```py
--min_bucket_reso=256 \
--max_bucket_reso=1024 \
```
---
##### `--network_alpha`
⚠️
```py
--network_alpha=4 \
```
---
##### `--save_model_as`
⚠️
```py
--save_model_as=safetensors \
```
---
##### `--network_module`
⚠️
```py
--network_module=lycoris.kohya \
```
---
##### `--network_args`
⚠️
```py
--network_args \
"preset=full" \
"conv_dim=256" \
"conv_alpha=4" \
"rank_dropout=0" \
"module_dropout=0" \
"use_tucker=False" \
"use_scalar=False" \
"rank_dropout_scale=False" \
"algo=locon" \
"train_norm=False" \
"block_dims=8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8" \
"block_alphas=0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625,0.0625" \
```
---
##### `--network_dropout`
⚠️
```py
--network_dropout=0 \
```
---
##### `--lr_scheduler`
⚠️
```py
--lr_scheduler="cosine" \
```
---
##### `--lr_scheduler_num_cycles`
⚠️
```py
--lr_scheduler_num_cycles=1 \
```
---
##### `--learning_rate`
⚠️
```py
--learning_rate=0.0001 \
```
---
##### `--unet_lr`
⚠️
```py
--unet_lr=0.0001 \
```
---
##### `--text_encoder_lr`
⚠️
```py
--text_encoder_lr=0.0001 \
```
---
##### `--network_dim`
⚠️
```py
--network_dim=8 \
```
---
##### `--output_name`
⚠️
```py
--output_name="last" \
```
---
##### `--scale_weight_norms`
⚠️
```py
--scale_weight_norms=1 \
```
---
##### `--no_half_vae`
⚠️
```py
--no_half_vae \
```
---
##### `--save_every_n_epochs`
⚠️
```py
--save_every_n_epochs=10 \
```
---
##### `--mixed_precision`
⚠️
```py
--mixed_precision="fp16" \
```
---
##### `--save_precision`
⚠️
```py
--save_precision="fp16" \
```
---
##### `--caption_extension`
⚠️
```py
--caption_extension=".txt" \
```
##### `--cache_latents` and `--cache_latents_to_disk`
⚠️
```py
--cache_latents \
--cache_latents_to_disk \
```
---
##### `--optimizer_type`
The default optimizer is `AdamW` and there are a bunch of them added every month or so, therefore I'm not listing them all, you can find the list if you really want, but `AdamW` is the best as of this writing so we use that!
```py
--optimizer_type="AdamW" \
```
---
##### `--dataset_repeats`
Repeats the dataset when training with captions, by default it is set to `1` so we'll set this to `0` with:
```py
--dataset_repeats=0 \
```
---
##### `--max_train_steps`
Specify the number of steps or epochs to train. If both `--max_train_steps` and `--max_train_epochs` are specified, the number of epochs takes precedence.
```py
--max_train_steps=500 \
```
---
##### `--shuffle_caption`
Shuffles the captions set by `--caption_separator`, it is a comma `,` by default which will work perfectly for our case since our captions look like this:
> rating_questionable, 5 fingers, anthro, bent over, big breasts, blue eyes, blue hair, breasts, butt, claws, curved horn, female, finger claws, fingers, fur, hair, huge breasts, looking at viewer, looking back, looking back at viewer, nipples, nude, pink body, pink hair, pink nipples, rear view, solo, tail, tail tuft, tuft, by lunarii, by x-leon-x, mythology, krystal \(darkmaster781\), dragon, scalie, wickerbeast, The image showcases a pink-scaled wickerbeast a furred dragon creature with blue eyes., She has large breasts and a thick tail., Her blue and pink horns are curved and pointy and she has a slight smiling expression on her face., Her scales are shiny and she has a blue and pink pattern on her body., Her hair is a mix of pink and blue., She is looking back at the viewer with a curious expression., She has a slight blush.,
As you can tell, I have separated the caption part not just the tags with a `,` to make sure everything gets shuffled. I'm at this point pretty certain this is beneficial especially when your caption file contains more than 77 tokens.
NOTE: `--cache_text_encoder_outputs` and `--cache_text_encoder_outputs_to_disk` can't be used together with `--shuffle_caption`. Both of these aim to reduce VRAM usage, you will need to decide between these yourself!
---
##### `--sdpa` or `--xformers` or `--mem_eff_attn`
The choice between `--xformers` or `--mem_eff_attn` and `--spda` will depend on your GPU. You can benchmark it by repeating a training with them!
---
##### `--sample_prompts` and `--sample_sampler` and `--sample_every_n_steps`
You have the option of generating images during training so you can check the progress, the argument let's you pick between different samplers, by default it is on `ddim`, so you better change it!
You can also use `--sample_every_n_epochs` instead which will take precedence over steps. The `k_` prefix means karras and the `_a` suffix means ancestral.
```py
--sample_prompts=/training_dir/sample-prompts.txt
--sample_sampler="euler_a" \
--sample_every_n_steps=100
```
My recommendation for Pony is to use `euler_a` for toony and for realistic `k_dpm_2`.
Your sampler options include the following:
```bash
ddim, pndm, lms, euler, euler_a, heun, dpm_2, dpm_2_a, dpmsolver, dpmsolver++, dpmsingle, k_lms, k_euler, k_euler_a, k_dpm_2, k_dpm_2_a
```
---
</details>
</div>
### CosXL Training
<!--
The only difference between CosXL training is that you need to enable `--v_parameterization`, and you can't sample the images. 😹 I also don't recommend using the `block_dims` and `block_alphas` from Pony.
-->
---
## Embeddings for 1.5 and SDXL
Embeddings in Stable Diffusion are high-dimensional representations of input data, such as images or text, that capture their essential features and relationships. These embeddings are used to guide the diffusion process, enabling the model to generate outputs that closely match the desired characteristics specified in the input.
You can find in the [`/embeddings`](https://huggingface.co/k4d3/yiff_toolkit/tree/main/embeddings) folder a whole bunch of them I collected for SD 1.5 that I later converted with [this](https://huggingface.co/spaces/FoodDesert/Embedding_Converter) tool for SDXL.
## ComfyUI Walkthrough any%
⚠️ Coming next year! ⚠️
## AnimateDiff for Masochists
⚠️ Coming in 2026! ⚠️
## Stable Cascade Furry Bible
### Resonance Cascade
πŸ†
## SDXL Furry Bible
### Some Common Knowledge Stuff
[Resolution Lora](https://huggingface.co/jiaxiangc/res-adapter/resolve/main/sdxl-i/resolution_lora.safetensors?download=true) is a nice thing to have, it will help with consistency. For SDXL it is just a LoRA you can load in and it will do its magic. No need for a custom node or extension in this case.
### Pony Diffusion V6
---
#### Requirements
Download the [model](https://civitai.com/models/257749/pony-diffusion-v6-xl) and load it in to whatever you use to generate models.
#### Positive Prompt Stuff
```sd
score_9, score_8_up, score_7_up, score_6_up, rating_explicit, source_furry,
```
I just assumed you wanted *explicit* and *furry*, you can also set the rating to `rating_safe` or `rating_questionable` and the source to `source_anime`, `source_cartoon`, `source_pony`, `source_rule34` and optionally mix them however you'd like. Its your life! `score_9` is an interesting tag, the model seems to have put all it's "*artsy*" knowledge. You might want to check if it is for your taste. The other interesting tag is `score_5_up` which seems to have learned a little bit of everything regarding quality while `score_4_up` seems to be at the bottom of the autism spectrum regarding art, I do not recommend using it, but you can do whatever you want!
You can talk to Pony in three ways, use tags only, tags are neat, but you can also just type in
`The background is of full white marble towers in greek architecture style and a castle.` and use natural language to the fullest extent, but the best way is to mix it both, its actually recommended since the score tags by definition are tags, and you need to use them!
Other nice words to have in the box depending on your mood:
```sd
detailed background, amazing_background, scenery porn
```
Other types of backgrounds include:
```sd
simple background, abstract background, spiral background, geometric background, heart background, gradient background, monotone background, pattern background, dotted background, stripped background, textured background, blurred background
```
After `simple background` you can also define a color for the background like `white background` to get a simple white background.
For the character portrayal you can set many different types:
```sd
three-quarter view, full-length portrait, headshot portrait, bust portrait, half-length portrait, torso shot
```
Its a good thing to describe your subject or subjects start with `solo` or `duo` or maybe `trio, group` , and then finally start describing your character in an interesting situation.
#### Negative Prompt Stuff
⚠️ **WARNING: Super under construction!** ⚠️
### SeaArt Furry
---
SeaArt's furry model sadly has its cons not just pros, yes it might come with artist knowledge bundled, but it seems to have trouble doing more than one character or everyone is bad at prompting, oh and it uses raw e621 tags, which just means you have to use underscores `_` instead of spaces&nbsp;` `&nbsp; inside the tags.
⚠️ TODO: Prompting tips.
## Pony Diffusion V6 LoRAs
All LoRAs listed here are actually LyCORIS with the exception of `blue_frost` which is just a regular LoRA. This might be important in case the software you use makes you put them in separate folders or if you are generating from a cute Python script.
### Concept Loras
#### space-v1e500
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/space-v1e500.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/space-v1e500.json)
```js
// Keywords:
by hubble
by jwst
// Example Positive Prompts:
by jwst, a galaxy, photo
by jwst, a red and blue galaxy
by hubble, a galaxy, photo
// Negative Prompt:
cropped,
blurry, wtf, old art, where is your god now, abstract background, simple background, cropped
```
#### spacengine-v1e500
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/spaceengine-v1e500.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/spaceengine-v1e500.json)
```js
// Keyword
by spaceengine
// Example Prompt:
by spaceengine, a planet, black background
```
### Artist/Style LoRAs
#### blp-v1e400
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/blp-v1e400.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/blp-v1e400.json)
Replicate [blp](https://e6ai.net/posts?tags=blp)'s unique style of AI art without employing 40 different custom nodes to alter sigmas and noise injection. I recommend you set your CFG to `6` and use `DPM++ 2M Karras` for the sampler and scheduler for a more realistic look or you can use `Euler a` for a more cartoony/dreamy generation with with a low CFG of `6`.
There have been reports that if you use this LoRA with a negative weight of `-0.5` your generations will have a slight sepia tone.
```js
blp,
// Recommended:
detailed background, amazing_background, scenery porn, feral,
```
---
#### blue_frost
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/blue_frost.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/blue_frost.json)
A bit of an experiment trying to make generating kitsch winter scenes easier. Originally trained for base SDXL, but it seems to work with PonyXL just fine. If you can call kitsch fine, anyway..
---
#### butterchalk-v3e400
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/butterchalk-v3e400.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/butterchalk-v3e400.json)
I'm not into `young anthro` I only trained this one for you, you hentai baka! ^_^
---
#### cecily_lin-v1e37
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/cecily_lin-v1e37.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/cecily_lin-v1e37.json)
I'm honestly not familiar with this artist, I just scraped their art and let sd-scripts go wild.
---
#### chunie_ponyxl_v1e5
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/chunie_ponyxl_v1e5.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/chunie_ponyxl_v1e5.json)
Everyone loves Chunie, except for that loud dumbass on Discord. 😹
---
#### cooliehigh-v1e45
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/cooliehigh-v1e45.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/cooliehigh-v1e45.json)
Again, I'm really uncultured when it comes to furry artists.
---
#### dagasi-v1e134
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/dagasi-v1e134.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/dagasi-v1e134.json)
Even I heard about this one!
---
#### darkgem_ponyxl_v1e4
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/darkgem_ponyxl_v1e4.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/darkgem_ponyxl_v1e4.json)
Quality digital painting style. Some people don't like it.
I recommend first an `Euler a` with `40` steps, CFG set to `11` at 1024x1024 resolution and then a hi-res pass at 1536x1536 with `DPM++ 2M Karras` at 60 steps with denoise set at 0.69 for the highest darkgem. Please only use `darkgem` if you want gems to appear in the scene or maybe your character will end up `holding a dark red gem`.
<div style="background-color: lightyellow; padding: 10px;">
<details>
<summary>Click to reveal images.</summary>
[![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/darkgem/00000859-04070924e-512.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/darkgem/00000859-04070924e.png)
</details>
</div>
---
#### furry_sticker-v1e250
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/furry_sticker-v1e250.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/furry_sticker-v1e250.json)
Generate an infinite amount of furry stickers for your infinite amount of telegram accounts!
```js
// Positive prompt:
furry sticker, simple background, black background, white outline,
// Negative prompt:
abstract background, detailed background, amazing_background, scenery porn,
```
<div style="background-color: lightyellow; padding: 10px;">
<details>
<summary>Click to reveal images.</summary>
[![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/furry_sticker/it-wasnt-me-512.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/furry_sticker/it-wasnt-me.png) [![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/furry_sticker/kade-rice-512.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/furry_sticker/kade-rice.png) [![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/furry_sticker/kade-this-point-up-sticker-your-stupid-512.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/furry_sticker/kade-this-point-up-sticker-your-stupid.png) [![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/furry_sticker/tibetan-unimpressede-512.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/furry_sticker/tibetan-unimpressede.png)
</details>
</div>
---
#### goronic-v1e1
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/goronic-v1e1.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/goronic-v1e1.json)
---
#### greg_rutkowski-v1e400
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/greg_rutkowski-v1e400.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/greg_rutkowski-v1e400.json)
---
#### hamgas-v1e400
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/hamgas-v1e400.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/hamgas-v1e400.json)
---
#### honovy_ponyxl_v1e4
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/honovy_ponyxl_v1e4.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/honovy_ponyxl_v1e4.json)
---
#### jinxit-v1e10
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/jinxit-v1e10.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/jinxit-v1e10.json)
---
#### kame_3-v1e80
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/kame_3-v1e80.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/kame_3-v1e80.json)
---
#### louart-v1e10
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/louart-v1e10.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/louart-v1e10.json)
---
#### realistic+scale_iridescence-v3e500
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/realistic%2Bscale_iridescence-v3e500.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/realistic%2Bscale_iridescence-v3e500.json)
```js
// Positive prompt:
realistic, photo, detailed background, amazing_background, scenery porn,
// Negative prompt:
abstract background, simple background
```
My take on photorealistic furries. Highly experimental and extremely fun!
I recommend you don't try anything but a CFG of `6` and `DPM++ 2M Karras`.
You can combo this with the [RetouchPhoto LoRA](https://civitai.com/models/343602/retouchphoto-for-ponyv6) for even more research. πŸ“ˆ
<div style="background-color: lightyellow; padding: 10px;">
<details>
<summary>Click to view images</summary>
[![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/realistic/00001231-04070113-512.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/realistic/00001231-04070113.png) [![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/realistic/00000685-04021915-512.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/realistic/00000685-04021915.png) [![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/realistic/00000703-04021946-512.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/realistic/00000703-04021946.png) [![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/realistic/00000706-04021959-512.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/realistic/00000706-04021959.png) [![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/realistic/00000754-04030229-512.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/realistic/00000754-04030229.png) [![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/realistic/00000233-03232306-512.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/realistic/00000233-03232306.png)
</details>
</div>
---
#### skecchiart-v1e134
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/skecchiart-v1e134.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/skecchiart-v1e134.json)
---
#### spectrumshift-v1e400
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/spectrumshift-v1e400.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/spectrumshift-v1e400.json)
---
#### squishy-v1e10
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/squishy-v1e10.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/squishy-v1e10.json)
---
#### whisperingfornothing-v1e58
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/whisperingfornothing-v1e58.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/whisperingfornothing-v1e58.json)
---
#### wjs07-v1e200
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/wjs07-v1e200.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/wjs07-v1e200.json)
---
#### wolfy-nail-v1e400
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/wolfy-nail-v1e400.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/wolfy-nail-v1e400.json)
---
#### woolrool_ponyxl_v1e4
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/woolrool_ponyxl_v1e4.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/woolrool_ponyxl_v1e4.json)
---
### Character LoRAs
#### amalia-v2e400
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/amalia-v2e400.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/amalia-v2e400.json)
Some loli cat girl. Enjoy yourself!
---
#### amicus-v1e200
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/amicus-v1e200.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/amicus-v1e200.json)
Gay space wolf from a visual novel everyone wants me to play.
---
#### auroth-v1e250
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/auroth-v1e250.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/auroth-v1e250.json)
A dragon or wyvern thing from DOTA2
---
#### blaidd-v1e400
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/blaidd-v1e400.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/blaidd-v1e400.json)
**Half-wolf Blaidd!** Bestest boy of Elden Ring! He's a very good boy! Can be a naughty boy though as well, if you like..
---
#### martlet-v1e200
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/martlet-v1e200.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/martlet-v1e200.json)
---
#### ramona-v1e400
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/ramona-v1e400.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/ramona-v1e400.json)
---
#### tibetan-v2e500
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/tibetan-v2e500.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/tibetan-v2e500.json)
---
#### veemon-v1e400
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/veemon-v1e400.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/veemon-v1e400.json)
---
#### hoodwink-v1e400
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/hoodwink-v1e400.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/hoodwink-v1e400.json)
---
#### jayjay-v1e400
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/jayjay-v1e400.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/jayjay-v1e400.json)
---
#### foxparks-v2e134
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/foxparks-v2e134.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/foxparks-v2e134.json)
---
#### lovander-v3e10
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/lovander-v3e10.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/lovander-v3e10.json)
---
#### skiltaire-v1e400
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/skiltaire-v1e400.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/skiltaire-v1e400.json)
---
#### chillet-v3e10
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/chillet-v3e10.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/chillet-v3e10.json)
---
#### maliketh-v1e1
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/maliketh-v1e1.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/maliketh-v1e1.json)
Second best boy of Elden Ring, it took me 7 tries the first time, so this is my form of payback!
```js
// Positive prompt:
male, anthro, maliketh \(elden ring\), white fur, white hair, head armor, red canine genitalia, knot,
// NLP version:
anthro male maliketh \(elden ring\) with white fur and white hair wearing head armor, He has a red canine genitalia with a knotty base and fluffy tail, He has claws and monotone fur with a monotone body,
```
<div style="background-color: lightyellow; padding: 10px;">
<details>
<summary>Click to reveal images</summary>
[![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/maliketh/00000844-04070802e-512.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/maliketh/00000844-04070802e.png) [![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/maliketh/00000850-04070838-512.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/maliketh/00000850-04070838.png) [![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/maliketh/00000842-04070728e-512.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/maliketh/00000842-04070728e.png)
</details>
</div>
---
#### wickerbeast-v1e500
- [⬇️ Download](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/ponyxl_loras/wickerbeast-v1e500.safetensors?download=true)
- [πŸ“Š Metadata](https://huggingface.co/k4d3/yiff_toolkit/raw/main/ponyxl_loras/wickerbeast-v1e500.json)
---
## Satisfied Customers