README.md

---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Street Bokeh
- Backgroung-Blur
widget:
- text: >-
    Street Bokeh, a young woman with long dark hair, wearing a black hooded
    jacket, stands in front of a backdrop of colorful lights. The backdrop is
    blurred, creating a stark contrast with the vibrant colors of the lights.
  output:
    url: images/SB1.png
- text: >-
    Street Bokeh, A close-up shot of a mans face, the mans eyes are slightly
    open, and he is wearing a pair of dark sunglasses with tinted lenses. His
    hair is dark brown, and his eyebrows are a light brown. His mouth is
    slightly closed, as if he is looking to the left. The background is blurred,
    and there are a bunch of colorful lights in the background, adding a pop of
    color to the scene.
  output:
    url: images/SB2.png
- text: >-
    Street Bokeh, Captured at eye-level, a close-up shot of a womans face,
    adorned with a pair of tinted sunglasses. The womans eyes are tinted a deep
    pink, and her hair is cascading over her shoulders. She is dressed in a
    leopard print jacket, a silver necklace, and earrings. The background is
    blurred, creating a vibrant and colorful backdrop.
  output:
    url: images/SB3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Street Bokeh
license: creativeml-openrail-m
---
# Street-Bokeh-Flux-LoRA

<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/Street-Bokeh-Flux-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           | 23 & 2550|
| Epoch                     | 12  | Save Every N Epochs       | 1      |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 13 [ Hi-RES ]
    
## 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/Street-Bokeh-Flux-LoRA"
trigger_word = "Street Bokeh"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)
```
## Data source
    
    - https://freeflo.ai/

## Trigger words

You should use `Street Bokeh` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/prithivMLmods/Street-Bokeh-Flux-LoRA/tree/main) them in the Files & versions tab.