---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- 3D
- Coin
- Design
widget:
- text: >-
    Golden Coin, Captured from a low-angle perspective on a vibrant purple
    backdrop, a glowing yellow circle with a white dollar sign in the center of
    the circle. The dollar sign is adorned with a bright yellow hue, adding a
    pop of color to the scene. The shadow of the dollar sign casts a shadow on
    the purple background, adding depth to the image.
  output:
    url: images/1.png
- text: >-
    Golden Coin, a vibrant orange letter "HF" is prominently displayed in the
    center of the frame. The letter is encircled by a bright yellow light,
    creating a stark contrast against the background. The word "hf.co" is
    written in the lower right corner of the image, adding a touch of contrast
    to the overall composition.
  output:
    url: images/2.png
- text: >-
    Golden Coin, Captured from a high-angle perspective on a gray surface, the
    top of a yellow bottle cap is visible. The cap is adorned with a white
    skull-like design in the center of the cap, adding a pop of color to the
    scene. The background is a solid black, creating a stark contrast to the
    yellow cap.
  output:
    url: images/3.png
- text: >-
    Golden Coin, A close-up view of a yellow plastic cap with a round opening in
    the center. The cap has a white line going around the top of the cap. Inside
    the cap is a brown liquid with a white arrow coming out of it. The
    background is a bright white.
  output:
    url: images/4.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Golden Coin
license: creativeml-openrail-m
---
# Flux-Golden-Coin-Design

<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-Golden-Coin-Design**

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           | 15 & 2200 |
| Epoch                     | 10   | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 13

## Best Dimensions & Inference

| **Dimensions** | **Aspect Ratio** | **Recommendation**       |
|-----------------|------------------|---------------------------|
| 1280 x 832      | 3:2              | Best                     |
| 1024 x 1024     | 1:1              | Default                  |

### Inference Range

- **Recommended Inference Steps:** 30–35
    
## 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-Golden-Coin-Design"
trigger_word = "Golden Coin"  
pipe.load_lora_weights(lora_repo)

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

You should use `Golden Coin` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/prithivMLmods/Flux-Golden-Coin-Design/tree/main) them in the Files & versions tab.