---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'sketch card, a close-up of a hand holding a card with a cartoon image of Mario on it. The card has a yellow background with a red cap and a red M on it, and the character is wearing blue overalls with a yellow button on the left side of his chest. The character is waving his left hand and has a big smile on his face. To the right of the card is a small cartoon character with a blue outfit and red hat. They are standing on a table with a white tablecloth. The table is adorned with small lights, adding a pop of color to the scene.'
  output:
    url: images/SC1.png
- text: 'sketch card, a hand is holding a small card with a drawing of three bears on it. The first bear is a panda, the second is a brown bear, and the third is a white bear. The bear on the left is wearing a gray and white striped shirt, while the third bear is in the middle of the three bears. The bears are facing each other, with their mouth open. The third bear has its head tilted to the left. The background is a gray wall with a row of windows in the upper left corner of the frame.'
  output:
    url: images/SC2.png
- text: 'sketch card, a hand is holding a small, square, white paper with a cartoon image of a yellow minion on it. The minion faces are drawn in a cartoon-like fashion, with big, round eyes, a wide smile, and a pair of eye-level glasses. The background of the image is a light blue, with Asian characters in a foreign language. To the right of the minions face, there is a white wall with multi-colored squares on it, adding a pop of color to the scene.'
  output:
    url: images/SC3.png
- text: 'sketch card, a hand is holding a white card with a cartoon drawing of a man in a gray jacket and a green shirt. The man has long black hair and a white face mask. His right hand is raised in the air, while his left hand is resting on his hip. The drawing is done in a simple, cartoon style. The background of the card is a collage of other cartoon drawings. To the right of the cards is a row of colored paints.'
  output:
    url: images/SC4.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: sketch card
license: creativeml-openrail-m
---
# Flux.1-Dev-Sketch-Card-LoRA

<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.1-Dev-Sketch-Card-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           | 14 & 1990 |
| Epoch                     | 16    | Save Every N Epochs       | 1     |

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

## 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.1-Dev-Sketch-Card-LoRA"
trigger_word = "sketch card"  
pipe.load_lora_weights(lora_repo)

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

You should use `sketch card` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/prithivMLmods/Flux.1-Dev-Sketch-Card-LoRA/tree/main) them in the Files & versions tab.