metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
RB Art, An animated image of a man sitting on a wooden stool. The man is
wearing a white Nike shirt with a blue stripe down the center of the
shirt. His legs are orange and his feet are black and white. His shoes are
black with white and orange stripes on them. The background is a vibrant
blue color. There are yellow stars on the right and left side of the
image.
output:
url: images/1.png
- text: >-
RB Art, A cartoon drawing of a woman in a blue hooded sweatshirt, blue
jeans, and blue tennis shoes is seen on a pink background. The woman is
holding a blue coffee mug in her right hand, and a spray bottle in her
left hand. Her hair is blowing in the wind, and she is wearing a blue cap.
Her eyes are closed, and her mouth is slightly open. Her sneakers are blue
with white laces, and the womans socks are pink.
output:
url: images/2.png
- text: >-
RB Art, A cartoon drawing of a girl in a blue shirt and pink shorts. The
girl is wearing white roller skates with white laces. There is a blue
lollipop on the left side of the image. There are yellow stars on the
right and left of the girl. The background is a light blue color
output:
url: images/3.png
- text: >-
RB Art, A cartoon drawing of a girl in a white t-shirt with the word
"LOVER" on it in black letters. The girl is wearing a pair of blue jeans
and red tennis shoes. She is standing on her knees with her legs crossed.
Her left leg is crossed over a yellow skateboard. The skateboard has an I
on it. The background is a light pink color. There are yellow stars and a
pink flower on the pink background.
output:
url: images/4.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: RG Art
license: creativeml-openrail-m
Model description for RGART
Image Processing Parameters
Parameter | Value | Parameter | Value |
---|---|---|---|
LR Scheduler | constant | Noise Offset | 0.03 |
Optimizer | AdamW | Multires Noise Discount | 0.1 |
Network Dim | 64 | Multires Noise Iterations | 10 |
Network Alpha | 32 | Repeat & Steps | 24 & 3300 |
Epoch | 30 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 39
Best Dimensions & Inference
Dimensions | Aspect Ratio | Recommendation |
---|---|---|
1280 x 832 | 3:2 | Best |
1024 x 1024 | 1:1 | Default |
Inference Range
- Recommended Inference Steps: 30–35
Setting Up
import torch
from pipelines import DiffusionPipeline
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
lora_repo = "strangerzonehf/RGART"
trigger_word = "RG Art"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Trigger words
You should use RG Art
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.