README.md

---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Product-Ad
widget:
- text: >-
    Product Ad, Captured at eye-level, a close-up shot captures a pile of fried
    chicken wings in a white paper cup. The chicken wings are a vibrant brown
    color, adding a pop of color to the scene. The cup is placed on a light
    brown wooden table, creating a stark contrast with the vibrant blue sky in
    the background. To the right of the chicken wings, a slice of lemon, a red
    onion, and a red radish are placed on the table. The radish, and red onions
    are arranged in a circular pattern, adding depth to the composition. The
    backdrop is blurred, suggesting a fair day.
  output:
    url: images/PA1.png
- text: >-
    Product Ad, a blue and silver electric razor is soaring through the air. The
    razor is positioned in the middle of a grassy field, with a backdrop of a
    mountain range that is covered in snow. The sky is a deep blue, dotted with
    white clouds, adding a pop of color to the scene. The blades of the razor
    are splashing in the air, adding texture to the image.
  output:
    url: images/PA3.png
- text: >-
    Product Ad,Vegan Snacks, in the style of an outdoors product hero shot in
    motion, dynamic magazine ad image, photorealism, 4k Raw, --v6
  output:
    url: images/PA4.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Product Ad
license: creativeml-openrail-m
---
# Flux-Product-Ad-Backdrop

<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 

**prithivMLmods/Flux-Product-Ad-Backdrop**

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           | 19 & 2970 |
| Epoch                     | 15    | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 19

## 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 = "prithivMLmods/Flux-Product-Ad-Backdrop"
trigger_word = "Product Ad"  
pipe.load_lora_weights(lora_repo)

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

You should use `Product Ad` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/prithivMLmods/Flux-Product-Ad-Backdrop/tree/main) them in the Files & versions tab.