---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- Art
widget:
- text: >-
    nm99, a vibrant orange moon is seen in the center of the frame. The moon is
    surrounded by three black circles, each with a different size and shape.
    Below the moon, there is a mountain range that is composed of gray and white
    crisscrossed mountains. The mountains are outlined in black, while the
    mountains range range in a lighter shade of gray. The sun is in the upper
    left corner, and the moon is partially obscured in the lower right corner.
    The background is a light gray wood paneling, adding a pop of color to the
    scene.
  output:
    url: images/NM1.png
- text: >-
    nm99, Captured in a sepia toned photograph, a silhouette of a seated buddha
    is depicted in a seated position. The statue is set against a backdrop of a
    brown wooden wall, adorned with a white moon. The silhouette of the seated
    Buddha is encircled by a circular pedestal, with a candle burning in the
    center. The pedestal is surrounded by a wavy, black swirl pattern. The sun
    is shining down on the statue, adding a touch of warmth to the scene. The
    shadow of the statue is cast on the wall, adding depth to the composition.
  output:
    url: images/NM3.png
- text: >-
    nm99, a black silhouette of a man stands in the middle of a tree. The mans
    body is covered in a black shirt and pants, and his arms are stretched out
    in front of him. The trees roots are visible on the left and right side of
    the frame, and their roots are on the right and left side. The background is
    a light brown, with a rough texture.
  output:
    url: images/NM4.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: nm99
license: creativeml-openrail-m
---
# Flux-Art-Nightmare-99

<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-Art-Nightmare-99**

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           | 18 & 2000 |
| Epoch                     | 10    | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 14

## 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-Art-Nightmare-99"
trigger_word = "nm99"  
pipe.load_lora_weights(lora_repo)

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

You should use `nm99` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/prithivMLmods/Flux-Art-Nightmare-99/tree/main) them in the Files & versions tab.