---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Ghost
- Pink
widget:
- text: >-
    Dark Creature, Captured in a vibrant pink background, a large hamburger is
    prominently displayed in the center of the frame. The burger is adorned with
    a variety of seeds, including sesame seeds, and a bun with lettuce and a
    slice of cheese. Surrounding the burger, a white wolf can be seen facing
    towards the right. The wolf is facing to the left, with its mouth open,
    while its head turned towards the left. To the right of the hamburger, two
    white foxes are facing the same direction, while the foxes facing the right
    are facing away from the camera. The background is a vibrant shade of pink,
    with a few birds flying in the background.
  output:
    url: images/DT1.png
- text: >-
    Dark Creature, a cartoon depiction of a person dressed in a black mask,
    holding a lit candle in their hands. The persons face is obscured by the
    mask, which is covered by a black fur. The background is a vibrant red,
    adorned with a pattern of leaves and birds, adding a pop of color to the
    scene.
  output:
    url: images/DT2.png
- text: >-
    Dark Creature, Captured in a digital art style, a woman with long dark hair
    and a black jacket is seated on a black chair. She is surrounded by four
    white dogs, each with a black tail and pointy ears. The background is a
    vibrant pink floral pattern, adding a pop of color to the scene. The womans
    hair is styled in a sleek bob, and she wearing a black turtleneck with a red
    pattern on it. Her hair is pulled back in a ponytail, and her lips are
    pursed. Her eyes are painted black, while her hair is a darker shade of
    black. There are two black birds on the top left and right side of the
    image. The birds are facing the woman, while the one on the right is facing
    the left.
  output:
    url: images/DT3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Dark Creature
license: creativeml-openrail-m
---
# Dark-Thing-Flux-LoRA

<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/Dark-Thing-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           | 24 & 2450|
| Epoch                     | 10  | Save Every N Epochs       | 1      |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 15 
    
## Best Dimensions

- 1024 x 1024 (Default)
  
## Setting Up
```
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/Dark-Thing-Flux-LoRA"
trigger_word = "Dark Creature"  
pipe.load_lora_weights(lora_repo)

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

You should use `Dark Creature` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

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