---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'ylw realism, Captured at eye-level, a close-up shot of a young man with curly blonde hair stands against a backdrop of a light blue sky. The mans face is angled slightly to the left, with a slight smile on his face. His eyes are slightly open, as if he is looking to the right. His hair is a mix of brown and white, and his sweater is draped over his shoulders. The sweaters sweater is a blend of red and white stripes, and the sweaters collar is a darker shade of red.'
  output:
    url: >-
      images/R1.png
- text: 'ylw realism, a close-up shot captures a young woman with long brown hair, wearing a mustard colored turtleneck and a yellow hat. Her left hand is resting on her head, adding a pop of color to the scene. The backdrop is a light blue, creating a stark contrast to the womans face.'
  output:
    url: >-
      images/R2.png
- text: 'ylw realism, a young woman stands with her left hand on her hip. She is wearing a short-sleeved navy blue t-shirt with a white collar. The word "Welby" is embroidered in white on the front of the shirt. Her hair is long and wavy, and her lips are pursed. Her jeans are a light blue denim with a zipper on the side. The backdrop is a stark white wall.'
  output:
    url: >-
      images/R3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: ylw realism
license: creativeml-openrail-m
---
![strangerzonehf/Flux-YWL-Realism-LoRA](images/ywl.png)

<Gallery />

**The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.**

## Model description 

**strangerzonehf/Flux-YWL-Realism-LoRA**

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           | 26 & 3100 |
| Epoch                     | 23   | Save Every N Epochs       | 1     |

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

## Best Dimensions

- 768 x 1024 (Best)
- 1024 x 1024 (Default)
    
## 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-YWL-Realism-LoRA"
trigger_word = "ylw realism"  
pipe.load_lora_weights(lora_repo)

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

You should use `ylw realism` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/strangerzonehf/Flux-YWL-Realism-LoRA/tree/main) them in the Files & versions tab.