---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'jason character, a man is seated in a car, his left arm resting on the seat of the car. He is wearing a sleeveless tank top with the word "FONDA" printed on it in black letters. His right arm is draped over his right shoulder. His left hand is resting on a black steering wheel, his right hand is positioned in front of him. The sun is shining on the right side of the image, casting a shadow onto the mans chest. The mans face is slightly turned to the left, he has a serious expression on his face. His hair is dark brown, his hair is short and neatly combed. He is wearing a black baseball cap on his head, adding a pop of color to the scene. In the background, a backdrop of palm trees can be seen.'
  output:
    url: images/image.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: jason character
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
---

![zdzdfzdfgzdfcbv.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/YWYstnaRXvTT1X0Coy_ny.png)

# Jason_Gta6-Flux-LoRA

<Gallery />

# Model description for Jason_Gta6-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           | 13 & 1680 |
| 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 = "strangerzonehf/Jason_Gta6-Flux-LoRA "
trigger_word = "jason character"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)
```

## Trigger words

You should use `jason character` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/strangerzonehf/Jason_Gta6-Flux-LoRA/tree/main) them in the Files & versions tab.