|
--- |
|
tags: |
|
- text-to-image |
|
- lora |
|
- diffusers |
|
- template:diffusion-lora |
|
widget: |
|
- text: 'This is a vibrant digital illustration featuring a seamless pattern of four Chihuahua heads, each adorned with large, bright pink sunglasses. The dogs have tan fur with white chests and expressive, wide eyes. The background is a solid, vivid blue, interspersed with scattered pink heart shapes, adding a playful and whimsical touch. The illustration style is cartoonish, with smooth shading and exaggerated features, creating a cheerful and eye-catching design.' |
|
output: |
|
url: images/SP1.png |
|
- text: 'Seamless Pattern Design, a light blue background features a pattern of red berries and white snowflakes. The berries are arranged in a way that creates a striking contrast to the blue background. The leaves, stems, and branches are outlined in a muted gold color, adding a touch of nature to the image. The red berries are centered in the middle of the image, while the branches on the right side are outlined with a darker shade of gold. The branches, leaves, and stems are also outlined in white, creating a stark contrast against the background.' |
|
output: |
|
url: images/SP2.png |
|
- text: 'Seamless Pattern Design, A white background with red bows and Christmas decorations. The bows are tied in a bow shape. The decorations are in small pots with green leaves and red flowers. The background is a light pink color.' |
|
output: |
|
url: images/SP3.png |
|
base_model: black-forest-labs/FLUX.1-dev |
|
instance_prompt: Seamless Pattern Design |
|
license: creativeml-openrail-m |
|
--- |
|
# Seamless-Pattern-Design-Flux-LoRA |
|
|
|
<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/Seamless-Pattern-Design-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 | 25 & 3K| |
|
| Epoch | 15 | Save Every N Epochs | 1 | |
|
|
|
Labeling: florence2-en(natural language & English) |
|
|
|
Total Images Used for Training : 17 [ Hi-RES ] |
|
|
|
## 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/Seamless-Pattern-Design-Flux-LoRA" |
|
trigger_word = "Seamless Pattern Design" |
|
pipe.load_lora_weights(lora_repo) |
|
|
|
device = torch.device("cuda") |
|
pipe.to(device) |
|
``` |
|
|
|
## Data source |
|
|
|
- https://playground.com/ |
|
|
|
## Trigger words |
|
|
|
You should use `Seamless Pattern Design` to trigger the image generation. |
|
|
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
[Download](/prithivMLmods/Seamless-Pattern-Design-Flux-LoRA/tree/main) them in the Files & versions tab. |
|
|