---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Dual-Character
- Male
- Female
- 3D-Character
- Fine-Textured
widget:
- text: >-
    3DXLC1, A close-up portrait of a man in a black tuxedo with a white collared
    shirt and a black bow tie. The mans hair is short and dark, and he has a
    slight smile on his face. His eyes are blue, and his lips are pink. The
    backdrop is a light gray, and the mans shadow is cast on the left side of
    the image.
  output:
    url: images/C1.png
- text: >-
    3DXLC1, a beautiful young woman with long dark brown hair, wearing a black
    bikini, is stunning against a backdrop of blue water and a blurred blurred
    background. The womans gaze is directed towards the left side of the frame,
    her lips pursed with red lipstick. Her left hand is resting on her hip,
    adding a touch of contrast to her body. The sky is a muted blue, with a few
    wispy clouds in the distance.
  output:
    url: images/C2.png
- text: >-
    3DXLC1, a medium-sized man stands against a stark white backdrop. He is
    dressed in a black tuxedo, adorned with a white collared shirt and a black
    bow tie. His hair is styled in a short bob, adding a pop of color to his
    attire. His eyes are a piercing blue, and his lips are a pinkish-pink. His
    eyebrows are a darker shade of brown, and he has a slight smile on his face.
  output:
    url: images/C3.png
- text: >-
    3DXLC1, A close-up shot of a woman with long dark brown hair and blue eyes.
    She is wearing a black halter top with a black collar around her neck. Her
    lips are painted with red lipstick. Her right hand is visible on the right
    side of the image. The background is blurred out of focus. The sky is blue.
  output:
    url: images/C4.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: 3DXLC1
license: creativeml-openrail-m
---
![strangerzonehf/Flux-3DXL-Partfile-C0001](images/cx.png)
<Gallery />

## Model description for 3DXL Partfile 000C1

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           | 15 & 2500 |
| Epoch                     | 18   | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 17

## 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
```python
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-C0001"
trigger_word = "3DXLC1"  
pipe.load_lora_weights(lora_repo)

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

## Trigger words

You should use `3DXLC1` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/strangerzonehf/Flux-3DXL-Partfile-C0001/tree/main) them in the Files & versions tab.