---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Realism
- Fine-Detailed
- Flux.1-dev
widget:
- text: >-
    Fine Detailed, A half Body Photo of a beautiful brunette Scottish girl,
    green eyes, messy beehive hair style, natural skin complexion, slim with
    curves, tartan shirt, outdoor background, soft lighting, captured by
    {randomly selected} photographer. This image looks glamorous and elegant in
    style and outdoor  background that was recognized as a contest winner. It
    has been featured on CG Society. Cinematic
  output:
    url: images/FD1.png
- text: >-
    Fine Detailed, A close-up shot of a medium-sized man with medium-length
    brown hair and a goatee. His eyes are a piercing blue, and his eyebrows are
    a darker shade of brown. He is wearing a brown jacket over a white t-shirt,
    and a gray sweater with a zipper on the right side of the jacket. The
    background is blurred, and the lighting is soft, creating a soft focus on
    the mans face.
  output:
    url: images/FD2.png
- text: >-
    Fine Detailed, A woman with long red hair, wearing a fur coat, standing
    outdoors in snowy Red Square, Moscow, with iconic colorful domes in the
    background. She faces slightly sideways, looking directly at the camera with
    a calm expression.
  output:
    url: images/FD3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Fine Detailed
license: creativeml-openrail-m
---
## Flux-Realism-FineDetailed  - B+ 20

<Gallery />

- Hosted Here🧨: https://huggingface.co/spaces/prithivMLmods/FLUX-LoRA-DLC

**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 

**prithivMLmods/Flux-Realism-FineDetailed**

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           | 28 & 3400|
| Epoch                     | 15  | Save Every N Epochs       | 1      |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 27 

## Realism LoRA In-Image
![prithivMLmods/Flux-Realism-FineDetailed](images/FD.png)
![prithivMLmods/Flux-Realism-FineDetailed](images/flux1.png)
## Best Dimensions

- 1024 x 1024 (Default)
  
## 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 = "prithivMLmods/Flux-Realism-FineDetailed"
trigger_word = "Fine Detailed"  
pipe.load_lora_weights(lora_repo)

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

> [!WARNING]
> **Trigger words:**  You should use `Fine Detailed` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/prithivMLmods/Flux-Realism-FineDetailed/tree/main) them in the Files & versions tab.