đ PoW : Elemental Flowers
This model is related to the "Picture of the Week" contest on Stable Diffusion discord, allowing users to create images of elemental flowers.
đ Quick Start
This model can be used just like any other Stable Diffusion model. You can generate images using the following code example:
from diffusers import StableDiffusionPipeline
import torch
model_id = "Guizmus/SDArt_elementalflowers"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "SDArt ibc"
image = pipe(prompt).images[0]
image.save("./SDArt.png")
You can also export the model to ONNX, MPS and/or FLAX/JAX. The model present in the diffusers is the user tokens version.
⨠Features
- Thematic Creation: Create images of flowers representing the four elements: fire, water, earth, and air. Use colors and shapes to capture the essence of the elements and incorporate their symbolism into the designs.
- Model Diversity: There are two versions of the model, the user tokens version and the classic tokens version, providing different ways to generate images.
đĻ Installation
No specific installation steps are provided in the original document.
đģ Usage Examples
Basic Usage
from diffusers import StableDiffusionPipeline
import torch
model_id = "Guizmus/SDArt_elementalflowers"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "SDArt ibc"
image = pipe(prompt).images[0]
image.save("./SDArt.png")
đ Documentation
Theme
Emerald leaves, crimson petals, and a fragrance so sweet â Nature's art, a canvas so neat. Is it the fiery passion of a red rose, or the tranquil bliss of a bluebell that grows?
Love is like a garden of these elemental treasures, each with its own charm, each with its own measures.
Create images of flowers representing the four elements: fire, water, earth, and air. Use colors and shapes that capture the essence of one or each element, and consider the symbolism and associations associated with them to create unique designs.
Consider the symbolism and associations of each element as you create your images. What emotions or concepts do they evoke, and how can you incorporate that into your designs?
What will your elemental flower bloom into? Where does it grow? What is it surrounded by? Even better-- what's your flower called? Name it! Today's example flowers were made by me ^^ enjoy!
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 "SDArt" and I balance the learning on the low side, so that it doesn't just replicate creations.
The total dataset is made of 49 pictures. It was trained on Stable diffusion 1.5. I used EveryDream to do the training, 100 total repeat per picture. The pictures were tagged using the token "SDArt", and an arbitrary token I choose. The dataset is provided below, as well as a list of usernames and their corresponding token.
A second version, titled "Classic version", has been trained by spliting all the 4-shot pictures into individual pictures, and using more usual tokens, like the 4 elements. This dataset is a little larger (61 pictures) and got trained for longer but on the same repeats/params.
The recommended sampling is k_Euler_a or DPM++ 2M Karras on 20 steps, CFGS 7.5 .
Trained tokens
User tokens version
- SDArt
- dyce
- ohwx
- bnp
- juli
- aten
- hep
- fcu
- hiko
- ufos
- nwsl
- cous
- aved
- mth
- gani
- kprc
- kuro
- asot
- jap
- weho
- hmv
- psst
- sqm
- irgc
- buka
- buon
- nmwx
- byes
- utm
- dany
- avel
- vaw
- zaki
- guin
- urd
- nasi
- vini
- hta
- crit
- inem
- mlas
- isch
- phol
- vedi
- dds
- acu
- httr
- pte
- oxi
- ibc
Classic tokens version
- elem flowers
- air
- water
- fire
- earth
- multielem
Download links
User tokens version
SafeTensors
CKPT
Dataset
Classic tokens version
SafeTensors
CKPT
Dataset
đ§ Technical Details
- Training Base: The model was trained on Stable diffusion 1.5.
- Training Tool: EveryDream was used for training, with 100 total repeats per picture.
- Dataset: The total dataset of the first version is made of 49 pictures, and the second "Classic version" dataset is a little larger, consisting of 61 pictures.
- Sampling Recommendation: The recommended sampling is k_Euler_a or DPM++ 2M Karras on 20 steps, CFGS 7.5 .
đ License
This model is under the creativeml-openrail-m license.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)