README.md

---
license: creativeml-openrail-m
inference: false
---

# Guizmus' test models

Those are medium to low quality models, single focus usualy, that can bring some fun but not really do significant things.

I'm not sharing the diffusers, just the ckpt and some examples.

You can also find my models relating to the Picture of the Week on Stable Diffusion discord [here](https://huggingface.co/Guizmus/SD_PoW_Collection)

---
## Rick Roll v1
![rickRoll person](https://huggingface.co/Guizmus/Experiments/resolve/main/showcase_rickroll.jpg)
* training: 20 pictures, 2400 steps on 1e-6 polynomial LR with 8 bit adam
* **Activation token :** `Rick Roll`
* [Model link](https://huggingface.co/Guizmus/Experiments/resolve/main/RickRoll_v1.ckpt)

---
## TMNT v1.0
![TMNT person](https://huggingface.co/Guizmus/Experiments/resolve/main/showcase_TMNT.jpg)
* training: 11 pictures, 1000 steps on 5e-6 polynomial LR with 8 bit adam
* **Activation token :** `TMNT person`
* [Model link](https://huggingface.co/Guizmus/Experiments/resolve/main/TMNT_v1.ckpt)

---
## Sid v1.0
![Simsbooth person](https://huggingface.co/Guizmus/Experiments/resolve/main/showcase_sid.jpg)
* training: 10 pictures, 2500 steps on 1e-6 polynomial LR
* **Activation token :** `Sid`
* [Model link](https://huggingface.co/Guizmus/Experiments/resolve/main/Sid-v1.ckpt)

---
## Kirby v1.0
![Simsbooth person](https://huggingface.co/Guizmus/Experiments/resolve/main/kirby_showcase.png)
* training: 10 pictures, 2500 steps on 1e-6 polynomial LR
* **Activation token :** `Kirby`
* [Model link](https://huggingface.co/Guizmus/Experiments/resolve/main/Kirby-v1.ckpt)

---
## Simsbooth v1.0
![Simsbooth person](https://huggingface.co/Guizmus/Experiments/resolve/main/Simsbooth_v1.jpg)
* training: 122 pictures, 18k steps on 1e-6 polynomial LR
* **Activation token :** `Simsbooth person`
* [Model link](https://huggingface.co/Guizmus/Experiments/resolve/main/Simsbooth-v1.ckpt)

---
## Hogleg Style v2.4
![Hogleg Style](https://huggingface.co/Guizmus/Experiments/resolve/main/showcase_HogLegStyle.jpg)
* training: 5k steps lr 1e-6, 122 samples, then 2k more steps on a lower lr and a rebalanced dataset
* **Activation token :** `HogLeg Style`
* [Model link](https://huggingface.co/Guizmus/Experiments/resolve/main/HogLegStyle-v2.4.ckpt)

---
## Illusion v1.0
![Illusion](https://huggingface.co/Guizmus/Experiments/resolve/main/showcase_illusion.png)
* training: 1k2 steps, 12 samples
* **Activation token :** `Illusion drawing`
* [Model link](https://huggingface.co/Guizmus/Experiments/resolve/main/Illusion-v1.ckpt)

---
## NikeAir v1.0
![NikeAir](https://huggingface.co/Guizmus/Experiments/resolve/main/showcase_nikeair.jpg)
* training: 1k2 steps, 10 samples
* **Activation token :** `NikeAir Shoes`
* [Model link](https://huggingface.co/Guizmus/Experiments/resolve/main/NikeAirShoes-v1.ckpt)