---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'Multi-perspective Art , A cartoon drawing of a man in a red shirt, black pants, and brown shoes is standing on a yellow surface. The man is holding a brown object in his right hand. He is reaching out towards the sky towards the right side of the image. The sky is a light blue with two white clouds in the distance. There are two white sail boats in the water in the background.'
  output:
    url: images/1.png
- text: 'Multi-perspective Art, a man in a gray suit is running on a white crosswalk. The mans suit is adorned with a gray stripe down the side of his jacket. His shoes are black with a red stripe on the side. His arms are outstretched, as if he is crossing the crosswalk, while his legs are bent at the knees. The background is a teal-green color, and there is a white sign on the left side of the image.'
  output:
    url: images/2.png
- text: 'Multi-perspective Art , Captured from a low-angle perspective on a vibrant orange-brown surface, a silhouette of a man in a white shirt, black pants, and black shoes, is throwing a ball into the air. The mans arm is bent at the top of the hill, and the ball is suspended in mid-air. The background, a vibrant shade of pink, is the focal point of the image.'
  output:
    url: images/3.png
- text: 'Multi-perspective Art , a man in a red jacket and black pants is seen climbing a ramp, holding a black rope. The ramp is elevated, creating a stark contrast with the vibrant orange background. The mans shadow is cast on the ramp, adding a touch of depth to the scene.'
  output:
    url: images/4.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Multi-perspective Art
license: creativeml-openrail-m
---
![gggggggggggg.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/Vf3_S4fIcNwdLhenux_cl.png)

<Gallery />

# Model description for Multi-perspective-Art-Flux

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           | 19 & 2500 |
| Epoch                     | 23   | Save Every N Epochs       | 1    |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 36

## Best Dimensions & Inference

| **Dimensions** | **Aspect Ratio** | **Recommendation**       |
|-----------------|------------------|---------------------------|
| 1280 x 832      | 3:2              | Best                     |
| 1024 x 1024     | 1:1              | Default                  |

### Inference Range

- **Recommended Inference Steps:** 30–35

## 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 = "strangerzonehf/Multi-perspective-Art-Flux"
trigger_word = "Multi-perspective Art"  
pipe.load_lora_weights(lora_repo)

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

You should use `Multi-perspective Art` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/strangerzonehf/Multi-perspective-Art-Flux/tree/main) them in the Files & versions tab.