README.md

---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'toon mix, a medium-haired woman, dressed in a white shirt and dark-colored bikini, is adorned with a white scarf tied around her waist. She is holding a gray bottle, her right hand resting on her hip. Her left hand is wrapped around the bottle, adding a pop of color to her body. Shes wearing a pink sun visor, and her brown hair cascades over her shoulders. The backdrop, a rocky cliff, is a stark contrast to the blue sky, dotted with white stars.'
  output:
    url: images/T1.png
- text: 'toon mix, a vibrant orange hat stands atop a womans head. The womans long, brown hair cascades over her shoulders, framing her face. She is wearing a black jacket, adorned with a bright orange scarf, and a yellow backpack. The background is blurred, with a few cars parked on the street, adding a touch of color to the scene.'
  output:
    url: images/T2.png
- text: 'toon mix, a woman with long brown hair, wearing a gray knitted cap and a black jacket, is seen in a close-up view. She is wearing a pair of white earphones in her mouth, adding a pop of color to her face. The womans face is obscured by the cap, which is adorned with a black and white speckled cap. The cap is held up by a hand, with the word "FRIORY" written in blue letters above it. The hand is held in the air, while the other hand reaches out towards the camera. In the background, a reflection of a woman can be seen on the glass of a building, adding depth to the scene.'
  output:
    url: images/T3.png
- text: 'toon mix, captured at eye-level, a medium-angle shot captures a young Asian woman with long dark brown hair, wearing a white tank top and a gray and black plaid shirt. The womans face is adorned with a black and white abstract painting, adding a pop of color to the otherwise monochromatic scene. She is standing in a field of grass, with a backdrop of trees and a clear blue sky.'
  output:
    url: images/T4.png
- text: 'Toon Mix: A young woman with shoulder-length blonde hair is wearing a pastel blue dress with a white belt. She holds a straw sun hat in her right hand while the other hand rests lightly on her hip. She’s adorned with a gold bracelet and a delicate necklace. The backdrop features a serene beach with gentle waves and a golden sunset that adds a warm glow to the scene.'
  output:
    url: images/T5.png
- text: 'Toon mix, a tall, slender man with short blonde hair wears a loose, white shirt with rolled-up sleeves and light blue denim jeans. He is holding a skateboard under his right arm, with a splash of red graffiti on its deck. He stands on a concrete sidewalk, a graffiti-covered brick wall in the background. The setting sun casts long shadows across the scene, while a pigeon perched on the wall adds a whimsical touch.'
  output:
    url: images/T6.png
- text: 'Toon mix, a boy with a mischievous grin and spiky black hair wears a red baseball cap tilted to the side, a bright yellow hoodie, and ripped black jeans. He is riding a vibrant green bicycle on a cobblestone path, with colorful autumn leaves scattered around. The background includes a bustling park, complete with families, dogs, and children playing on swings.'
  output:
    url: images/T7.png
- text: 'Toon mix, a tall man with sharp features and salt-and-pepper hair wears a tailored navy suit with a burgundy tie. He stands under a glowing streetlamp on a cobblestone street, holding a black umbrella against a light drizzle. Behind him, a Parisian-style café with outdoor seating creates an air of sophistication, while faint jazz music seems to float through the scene.'
  output:
    url: images/T8.png
- text: 'Toon Mix: A young man with short black hair, dressed in a blue denim jacket over a white t-shirt, is seated on a wooden bench. He is holding a steaming cup of coffee in his hands, with a vibrant red scarf draped around his neck. His relaxed pose contrasts with the bustling city backdrop, where towering skyscrapers meet the orange hues of the sunset.'
  output:
    url: images/T9.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: toon mix
license: creativeml-openrail-m
---
# Flux.1-Dev-Realtime-Toon-Mix

<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-Realtime-Toon-Mix**

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           | 17 & 2900 |
| Epoch                     | 15    | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 29

## 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-Realtime-Toon-Mix"
trigger_word = "toon mix"  
pipe.load_lora_weights(lora_repo)

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

You should use `toon mix` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/prithivMLmods/Flux.1-Dev-Realtime-Toon-Mix/tree/main) them in the Files & versions tab.