|
--- |
|
tags: |
|
- text-to-image |
|
- lora |
|
- diffusers |
|
- template:diffusion-lora |
|
widget: |
|
- text: 'cardboard# art, a medium-sized sculpture of a womans head is positioned against a beige wall. The womans face is adorned with a white face, adorned with black braids, and her lips are painted a vibrant red. Her hair is styled in a bun, adding a touch of texture to her face. She is wearing a red collared button-down shirt with a yellow button-up collar. Her earring is tucked into her right ear. Her left ear is encased in a small yellow barrette. The wall behind her is a light brown, with a few small red dots scattered across it.' |
|
output: |
|
url: images/1.png |
|
- text: 'cardboard# art, a medium-angle view of a paper cutout of a mans face is displayed against a dark gray backdrop. The mans head is adorned with a brown hat, a white beard, and a white mustache. His eyes are open, and his lips are slightly parted, as if he is looking to the left. His hair is cut in a bob, adding a pop of color to the scene. His earrings, a cross, are visible in the bottom right corner of the frame.' |
|
output: |
|
url: images/2.png |
|
- text: 'cardboard# art, a cartoon depiction of a man with a beard and mustache is seen eating a hamburger. The mans face is white, with brown hair, and his eyes are closed. His hands are positioned on either side of the hamburger, and he is wearing a light blue long-sleeved shirt. The hamburger is adorned with a variety of toppings, including hamburgers, cheese, and tomatoes. The background is a pale yellow, and the mans arms are positioned in front of him, adding a pop of color to the composition.' |
|
output: |
|
url: images/3.png |
|
- text: 'cardboard# art, a cardboard cutout of a mans face is displayed against a vibrant green backdrop. The mans head is adorned with a black mustache, a black beard, and a gray short-sleeved t-shirt. His arms are positioned at the bottom of the frame, adding a pop of color to the scene. He is wearing a pair of orange-colored glasses, with a thick rimmed frame.' |
|
output: |
|
url: images/4.png |
|
- text: 'Cardboard# Art: A bust-style cardboard cutout of a man with round glasses and a beanie, displayed in front of a vibrant red backdrop. His face is painted light tan, with a neatly trimmed mustache and beard. He is dressed in a green collared shirt with the top button open. A cardboard notebook and pen are tucked under his left arm.' |
|
output: |
|
url: images/5.png |
|
- text: 'Cardboard# Art: A cardboard cutout of an elderly woman sitting on a park bench, displayed in front of a pale green background. Her hair is styled in a neat bun, painted silver-gray. She is dressed in a purple coat with a red scarf wrapped around her neck. A small cardboard pigeon is perched on her left shoulder, adding a playful touch to the scene.' |
|
output: |
|
url: images/6.png |
|
base_model: black-forest-labs/FLUX.1-dev |
|
instance_prompt: cardboard# art |
|
license: apache-2.0 |
|
--- |
|
 |
|
|
|
<Gallery /> |
|
|
|
# **Model description for Flux-Cardboard-Art-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 | 26 & 3500 | |
|
| Epoch | 22 | Save Every N Epochs | 1 | |
|
|
|
Labeling: florence2-en(natural language & English) |
|
|
|
Total Images Used for Training : 37 |
|
|
|
## Best Dimensions & Inference |
|
|
|
| **Dimensions** | **Aspect Ratio** | **Recommendation** | |
|
|-----------------|------------------|---------------------------| |
|
| 1280 x 832 | 3:1 | Compatible | |
|
| 1024 x 1024 | 1:1 | 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 = "strangerzonehf/Flux-Cardboard-Art-LoRA" |
|
trigger_word = "cardboard# art" |
|
pipe.load_lora_weights(lora_repo) |
|
|
|
device = torch.device("cuda") |
|
pipe.to(device) |
|
``` |
|
## Trigger words |
|
|
|
You should use `cardboard# art` to trigger the image generation. |
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
[Download](/strangerzonehf/Flux-Cardboard-Art-LoRA/tree/main) them in the Files & versions tab. |
|
|
