README.md

---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Polaroid
widget:
- text: >-
    Polaroid Collage, a collage of photographs of the New York City is displayed
    on a white surface. The photographs are arranged in a grid-like pattern,
    with a variety of buildings and skyscrapers visible. The buildings are lit
    up, creating a stark contrast against the blue sky. The photograph is taken
    from a low angle, adding a touch of depth to the composition.
  output:
    url: images/P1.png
- text: >-
    Polaroid Collage, a collage of black and white photographs is displayed on a
    white surface. The photographs are arranged in a grid-like pattern, with a
    variety of shapes and sizes. Some of the photographs feature mountains,
    trees, and a body of water. The mountains are covered in snow, and the sky
    is filled with clouds, adding a touch of warmth to the scene.
  output:
    url: images/P3.png
- text: >-
    Polaroid Collage, Captured in a black and white collage, a cats face is
    featured prominently in the center of the frame. The cats eyes are a
    piercing blue, and its whiskers are long and white, adding a pop of color to
    the otherwise monochromatic image. The background is a stark white, creating
    a stark contrast to the cats fur.
  output:
    url: images/P4.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Polaroid Collage
license: creativeml-openrail-m
---
# Flux-Polaroid-Plus

<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-Polaroid-Plus**

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 & 3300 |
| Epoch                     | 17    | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 24

## 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-Polaroid-Plus"
trigger_word = "Polaroid Collage"  
pipe.load_lora_weights(lora_repo)

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

You should use `Polaroid Collage` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

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