Experiments / README.md
Guizmus's picture
Update README.md
36a15f6
|
raw
history blame
1.17 kB
---
license: creativeml-openrail-m
---
# 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.
---
## NikeAir v1.0
![MultiModel](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)
---
## Illusion v1.0
![MultiModel](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)
---
## Hogleg Style v2.4
![MultiModel](https://huggingface.co/Guizmus/Experiments/resolve/main/showcase_HogLegStyle.png)
* 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)