---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'capybara hf, A cartoon drawing of a brown bear sitting in front of a laptop. The bear is facing to the right and has a smiley face on the screen of the laptop. Above the bear is a white bear with a black nose and a black mouth. The background is a light beige color.'
  output:
    url: images/C1.png
- text: 'capybara hf, A cartoon drawing of a brown bear wearing sunglasses with a yellow circle at the top of the eyes. The bears eyes are tinted black, and the bears body is a light brown color. He is holding a pink money in his right hand. The money has a black border around it, and there are two yellow smiley faces on the eyes of the bear. The background is a solid white color.'
  output:
    url: images/C2.png
- text: 'capybara hf, A cartoon drawing of a brown bear with a black hat on its head. The bear is wearing a black shirt with a pink collar. The bears face is brown and the bears mouth is black. There is a smiley face in the bottom right corner of the image. There are white clouds in the background.'
  output:
    url: images/C3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: capybara hf
license: apache-2.0
---
![strangerzonehf/Flux-Super-Capybara-HF](images/CC.png)

# Flux-Super-Capybara-HF

<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-Super-Capybara-HF**

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           | 22 & 2900 |
| Epoch                     | 15    | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 20

## 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 = "strangerzonehf/Flux-Super-Capybara-HF"
trigger_word = "capybara hf"  
pipe.load_lora_weights(lora_repo)

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

You should use `capybara hf` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/strangerzonehf/Flux-Super-Capybara-HF/tree/main) them in the Files & versions tab.