|
--- |
|
language: |
|
- en |
|
license: creativeml-openrail-m |
|
thumbnail: "https://huggingface.co/Guizmus/PoW_Something/resolve/main/showcase.jpg" |
|
tags: |
|
- stable-diffusion |
|
- text-to-image |
|
- image-to-image |
|
--- |
|
# PoW : Something |
|
|
|
![Showcase](https://huggingface.co/Guizmus/PoW_Something/resolve/main/showcase.jpg) |
|
|
|
## Theme |
|
|
|
## Model description |
|
|
|
This is a model related to the "Picture of the Week" contest on Stable Diffusion discord. |
|
|
|
I try to make a model out of all the submission for people to continue enjoy the theme after the even, and see a little of their designs in other people's creations. The token stays "PoW Style" and I balance the learning on the low side, so that it doesn't just replicate creations. |
|
|
|
The total dataset is made of 50 pictures. It was trained on [Stable diffusion 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5). I used [EveryDream](https://github.com/victorchall/EveryDream2trainer) to do the training, 100 total repeat per picture. The pictures were tagged using the token "PoW Style", and an arbitrary token I choose. The dataset is provided below, as well as a list of usernames and their corresponding token. |
|
|
|
The recommended sampling is k_Euler_a or DPM++ 2M Karras on 20 steps, CFGS 7.5 . |
|
|
|
## Trained tokens |
|
|
|
* PoW Style |
|
* Token "ofi" corresponds to the user "dunkeroni" |
|
* Token "mohd" corresponds to the user "DrSen" |
|
* Token "rmb" corresponds to the user "FoodOfTheGods" |
|
* Token "dca" corresponds to the user "owleye" |
|
* Token "muc" corresponds to the user "LeafsPa" |
|
* Token "onex" corresponds to the user "Lew39" |
|
* Token "toid" corresponds to the user "Ainvas" |
|
* Token "sura" corresponds to the user "tazi" |
|
* Token "juli" corresponds to the user "Only-story" |
|
* Token "veli" corresponds to the user "Horvallis" |
|
* Token "gsp" corresponds to the user "Akumetsu971" |
|
* Token "tux" corresponds to the user "katmoget" |
|
* Token "tvc" corresponds to the user "dony" |
|
* Token "pbc" corresponds to the user "scottie" |
|
* Token "pgs" corresponds to the user "piscabo" |
|
* Token "rps" corresponds to the user "Junglerally" |
|
* Token "dbz" corresponds to the user "Overduet" |
|
* Token "soca" corresponds to the user "DylanWalker" |
|
* Token "suru" corresponds to the user "IkariDev" |
|
* Token "nips" corresponds to the user "espasmo" |
|
* Token "rune" corresponds to the user "Onusai" |
|
* Token "pafc" corresponds to the user "vcm07" |
|
* Token "nlwx" corresponds to the user "sometimes" |
|
* Token "fck" corresponds to the user "bWm_nubby" |
|
* Token "cae" corresponds to the user "Kazzear" |
|
* Token "sohn" corresponds to the user "Brainlasher" |
|
* Token "dori" corresponds to the user "Tdg8uU" |
|
* Token "zawa" corresponds to the user "Nerfgun3" |
|
* Token "revs" corresponds to the user "ResidentChiefNZ" |
|
* Token "hmv" corresponds to the user "ミカ" |
|
* Token "whoo" corresponds to the user "Libra " |
|
* Token "asar" corresponds to the user "millennium_gun" |
|
* Token "blob" corresponds to the user "crazykazoo " |
|
* Token "xiao" corresponds to the user "Deez Games" |
|
* Token "kilt" corresponds to the user "Eface" |
|
* Token "ulf" corresponds to the user "Havok" |
|
* Token "loeb" corresponds to the user "Cryonicus" |
|
* Token "bnha" corresponds to the user "NorTroll" |
|
* Token "gote" corresponds to the user "Vil" |
|
* Token "omd" corresponds to the user "wpatzz" |
|
* Token "adl" corresponds to the user "Eppinette-Chi" |
|
* Token "shld" corresponds to the user "xxab" |
|
* Token "waj" corresponds to the user "Phaff" |
|
* Token "sown" corresponds to the user "King Pendragon" |
|
* Token "rcn" corresponds to the user "Guizmus" |
|
* Token "httr" corresponds to the user "Jordan~~" |
|
* Token "dits" corresponds to the user "bitspirit3" |
|
* Token "hta" corresponds to the user "SirVeggie" |
|
* Token "lun" corresponds to the user "xThIsIsBoToXx" |
|
* Token "olis" corresponds to the user "CesarAI" |
|
|
|
## Download links |
|
|
|
[SafeTensors](https://huggingface.co/Guizmus/PoW_Something/resolve/main/PoWStyle-Something.safetensors) |
|
|
|
[CKPT](https://huggingface.co/Guizmus/PoW_Something/resolve/main/PoWStyle-Something.ckpt) |
|
|
|
[Dataset](https://huggingface.co/Guizmus/PoW_Something/resolve/main/PoWStyle-Something.zip) |
|
|
|
## 🧨 Diffusers |
|
|
|
This model can be used just like any other Stable Diffusion model. For more information, |
|
please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion). |
|
|
|
You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX](). |
|
|
|
```python |
|
from diffusers import StableDiffusionPipeline |
|
import torch |
|
|
|
model_id = "Guizmus/PoW_Something" |
|
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16) |
|
pipe = pipe.to("cuda") |
|
|
|
prompt = "PoW Style sown" |
|
image = pipe(prompt).images[0] |
|
|
|
image.save("./PoWStyle.png") |
|
``` |