---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: '2color illustration, A purple and black drawing of a woman laying on a bed. The bed is covered with a green blanket. There is a black lamp hanging from the ceiling above the bed. To the right of the bed is a table with a basket on top of it. There are books and bottles on the table.'
  output:
    url: images/1.png
- text: '2color illustration, An eye-level view of a woman in a red dress is sitting on a bed in front of a TV. The TV is turned on, and the screen has a red and white striped design on it. The woman is looking at the TV, and there is a black and white polka dot chair to the right of the TV. There is a table with a laptop and a plate of food on it, and a black lamp to the left of the laptop.'
  output:
    url: images/2.png
- text: '2color illustration, A medium-angle perspective of a cartoon drawing of a woman sitting on a couch. The woman is wearing a striped shirt, long pants, and a long-sleeved shirt. She is holding a pen in her right hand. Her left hand is resting on the armrest of the couch, while her right arm rests on the couch. Her legs are crossed in front of her legs. The couch is a light yellow color, with a black base. The floor beneath the couch is made up of small square tiles. The ceiling above the room is dark blue, with small white dots dotting the ceiling.'
  output:
    url: images/3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: 2color illustration
license: creativeml-openrail-m
---
![FGazsdfgvaszdfva.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/-exdK6pf_aHWsQmB48oM0.png)

<Gallery />

# Model description for 2Color-Illustration
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 & 2770 |
| Epoch                     | 20   | Save Every N Epochs       | 1    |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 22

## 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/2Color-Illustration"
trigger_word = "2color illustration"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)
```
## Trigger words

You should use `2color illustration` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/strangerzonehf/2Color-Illustration/tree/main) them in the Files & versions tab.