---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- dalle
- flux
- realism
- photo-realistic
- realistic
- face-realism
widget:
- text: 'dalle-mix, photography, portrait of contrast, profile silhouette of a woman, vibrant hot pink backdrop, visualize using a camera setup that mimics a large aperture, focusing solely on the silhouettes edge, while a low ISO maintains the richness of color without grain, photorealistic, UHD --ar 9:16 --chaos 1.7 --style raw'
  output:
    url: images/D1.png
- text: 'dalle-mix, Ultra-detailed close-up of a pandas face, styled like a Pixar or DreamWorks character, highlight intricately textured fur for depth, the panda sports a pirate eyepatch, adding a roguish charm, he has a furrowed brow and a smirking mouth, showcasing a cunning and playful demeanor, emphasize crisp details in the facial features, particularly around the expressive eyes and smirking mouth, to bring out the character’s personality, 3D render, --v 6 --style raw --stylize 250 --ar 4:5'
  output:
    url: images/D3.png
- text: 'dalle-mix, photography, portrait of contrast, profile silhouette of a black man, vibrant orange backdrop, visualize using a camera setup that mimics a large aperture, focusing solely on the silhouettes edge, while a low ISO maintains the richness of color without grain, photorealistic, UHD --ar 9:16 --chaos 1. 7 --style raw'
  output:
    url: images/D2.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: dalle-mix
license: creativeml-openrail-m
---
# Flux-Dalle-Mix-LoRA [ Experimental Version ]

<Gallery />

- Hosted Here🧨: https://huggingface.co/spaces/prithivMLmods/FLUX-LoRA-DLC

**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-Dalle-Mix-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           | 25 & 3700|
| Epoch                     | 15  | Save Every N Epochs       | 1      |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 44 [ Hi -Res ]
    
## Samples form Flux.1 Dev Base & Mixer

![prithivMLmods/Flux-Dalle-Mix-LoRA](images/D5.png)
   
## Best Dimensions

- 768 x 1024 (Best)
- 1024 x 1024 (Default)

![prithivMLmods/Flux-Dalle-Mix-LoRA](images/D4.png)

| Description |
|--------------------|
| dalle-mix, Caricatures pencil drawing, cute woman, mid-20's, color pencils, in the style of Pixar, hilariously funny, exaggerated features, white background --chaos 50 --ar 1:2 --stylize 750  |

## 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-Dalle-Mix-LoRA"
trigger_word = "dalle-mix"  
pipe.load_lora_weights(lora_repo)

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

## Trigger words

> [!WARNING]
> **Trigger words:**  You should use `dalle-mix` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/prithivMLmods/Flux-Dalle-Mix-LoRA/tree/main) them in the Files & versions tab.