strangerzonehf/Flux-3DXL-Partfile-0003

Prompt

3DXLP3, a vibrant red womans face is adorned with a black collar and a black shirt. Her hair is a vibrant shade of red, adding a pop of color to her face. Her eyes are a piercing blue, and her eyebrows are a darker shade of brown. Her lips are a lighter shade of pink, and she is smiling slightly at the moment. The backdrop is a dark gray, creating a stark contrast to her red dress.

Prompt

3DXLP3, a man dressed in a black jacket, white shirt, black tie, and a blue vest with a black belt. He is holding a black gun in his right hand, aiming it towards the right side of the frame. His hair is short and dark brown, and he has a serious expression on his face. The backdrop is a light gray, and the mans shadow is cast on the left side of his chest.

Prompt

3DXLP3, a 3D rendering of a muscular man stands in front of a gray backdrop. He is dressed in a red headband, white wrist bands, and a pair of yellow sunglasses. His left arm is raised in the air, while his right arm is bent at the elbow. His right hand is resting on his hip, and his left hand is positioned in a way that he is pointing to the left. He has a beard, mustache, and dark hair, and is wearing a red and yellow swimsuit with white stars on the bottom. His legs are covered in a light-colored pair of socks, and the socks are a bright yellow color

Prompt

3DXLP3, A close-up shot of a black mans face, positioned in front of a gray backdrop. He is wearing a blue baseball cap with a white number 3 embroidered on the front of the cap. His earrings are adorned with silver earrings. His mouth is slightly open, with a black mustache and beard. His eyebrows are dark and goatee, adding a touch of texture to his face. He is wearing a dark blue t-shirt with a collar.

Model description for 3DXL Partfile 0003

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	20 & 2800
Epoch	20	Save Every N Epochs	1

Labeling: florence2-en(natural language & English)

Total Images Used for Training : 15

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/Flux-3DXL-Partfile-0003"
trigger_word = "3DXLP3"  
pipe.load_lora_weights(lora_repo)

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

Trigger words

You should use 3DXLP3 to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.