README.md

---
tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
widget:
- text: '3d station toon, Captured at eye-level, a close-up shot of a black mans face, adorned with a cream-colored sweater and a plaid jacket. The mans upper torso is encased in a gold ring, adding a touch of color to his attire. His hair is a mix of black and brown, and his eyes are a piercing blue. His eyebrows are a darker shade of brown, while his lips are a lighter shade of pink. The backdrop is a stark grey, and the mans attire is a blend of greens, red, and brown.'
  output:
    url: images/1111.png
- text: '3d station toon, Captured in a low-angle perspective, a close-up shot of a black mans face is adorned with a dark brown baseball cap, adorned with the letters "LA" in capital letters. The mans eyebrows are furrowed, adding a touch of texture to his face. His eyes are a piercing blue, and his eyebrows are a darker shade of brown, while his lips are a lighter shade of pink. He is wearing a maroon collared button-down shirt with a black collar and a silver chain hanging from the collar. The backdrop is a light gray, creating a stark contrast to the mans head and the cap.'
  output:
    url: images/2222.png
- text: '3d station toon, Captured at eye-level, a medium-sized black man with a black beard and mustache, stands in front of a stark white backdrop. He is dressed in a brown tweed jacket, a black t-shirt, and a gold chain draped around his neck. The mans hair is styled in a short bob, adding a touch of texture to his face. His eyes are a piercing blue, and his eyebrows are a darker shade of brown. His lips are a lighter shade of pink, and he has a serious look on his face, as if he is looking at the camera.'
  output:
    url: images/3333.png
- text: '3d station toon, a close-up shot of a black mans face is adorned with a blue and white bandana tied around his head. He is wearing a blue collared button-down shirt, a beige vest, and a gold necklace around his neck. His eyebrows, mustache, and earrings are visible, adding a pop of color to his face. The backdrop is a stark grey, and the mans expression is neutral.'
  output:
    url: images/4444.png
- text: '3D station toon – Captured at eye-level, a close-up shot of a black womans face, adorned with a beige knitted sweater and a dark brown leather jacket. Her voluminous curly hair cascades past her shoulders, a mix of deep brown and auburn highlights. Her eyes are a piercing green, framed by thick, dark brown eyebrows. She wears gold hoop earrings, and her full lips are painted in a subtle shade of plum. A thin gold necklace rests against her collarbone, adding a refined touch. The backdrop is a soft grey, complementing the earthy tones of her attire.'
  output:
    url: images/5555.png
- text: '3D station toon, Captured at eye-level, a close-up shot of a white womans face, adorned with a cream-colored turtleneck sweater and a brown plaid blazer. A delicate silver ring rests on her finger, adding elegance to her look. Her blonde hair is styled in loose waves, framing her piercing green eyes. Her eyebrows are a light brown shade, and her lips are a soft pink. The backdrop is a stark grey, creating a neutral contrast to her warm-toned outfit.'
  output:
    url: images/6666.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: 3d station toon
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
---

![zdgdfxgxdf.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/L-5jmp-aNZMCIgYQ0M6RC.png)

# 3d station toon

<Gallery />

# Model description for 3d-Station-Toon

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           | 25 & 3790 |
| Epoch                     | 29   | Save Every N Epochs       | 1    |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 36

## 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/3d-Station-Toon"
trigger_word = "3d station toon"  
pipe.load_lora_weights(lora_repo)

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

## Trigger words

You should use `3d station toon` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/strangerzonehf/3d-Station-Toon/tree/main) them in the Files & versions tab.