Prompt

NewG Art, An abstract painting of a womans face with the words Tienes Cade written in black on the face. The womans eyes are covered in brown, black, and pink dots. Her lips are painted red, and her nose is painted pink. Her hair is dark brown and curly. Her ear is to the left of her face, and there is a lime green background behind her.

Prompt

NewG Art, A medium-sized painting of a womans face, painted in a vibrant shade of red. Her hair is cascading down her shoulders, framing her face. Her eyes are a piercing green, and her lips are a darker shade of brown. She is wearing a star necklace, adding a pop of color to her outfit. The background is a stark white, with a pink line running down the left side of the image. The womans hair is a vibrant red, and she is adorned with a few black stars. The star necklace has a blue bead at the bottom, and a silver chain hangs from it.

Prompt

NewG Art, A medium-sized painting of a mans face is depicted in the center of the frame. The mans eyes are a piercing blue, and he has dark brown hair. His eyebrows are a darker shade of brown, and his lips are a lighter shade of pink. His head is adorned with a pink headband, and the mans hair is a dark brown color. To the left of the painting, the words TOT BE CMO HELUB are written in black. The background is a light blue, with white splashes.

Prompt

NewG Art, A medium-sized painting of a womans face, painted in a vibrant shade of blue. Her eyes are a piercing blue, and her eyelashes are a darker shade of brown. Her nose is painted a light pink color, and she is wearing a ring on her right ear. Her hair is a dark brown, with a few wispy bangs on the left side of her head. Her eyebrows are black, while her lips are a lighter pink. Her mouth is slightly open, as if she is screaming. The background is a light green, and the wall is a pale white. The painting is done in a cartoonish style.

Model description for NewG-Art

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 & 3900
Epoch	30	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 47

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/NewG-Art"
trigger_word = "NewG Art"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)

Trigger words

You should use NewG Art to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.