|
--- |
|
tags: |
|
- text-to-image |
|
- lora |
|
- diffusers |
|
- template:diffusion-lora |
|
widget: |
|
- text: 'quoter, A white background with a brown cross-shaped sticker that reads "Shes an old soul with young eyes, a vintage heart, and a beautiful mind."' |
|
output: |
|
url: images/QQ1.png |
|
- text: 'quoter, Captured from a low-angle perspective on a white backdrop, a square-shaped sticker is adorned with text that reads "Books, not guns. Culture, not violence." The text is written in a bold, black font. The stickers border is a light brown color, adding a pop of color to the image. The background is a stark white, creating a stark contrast to the text.' |
|
output: |
|
url: images/QQ2.png |
|
- text: 'quoter, a light brown rectangular sticker with black text reads "Music is medicine for the soul." The sticker is set against a stark white backdrop. The text is written in a bold, black font, adding a pop of color to the image.' |
|
output: |
|
url: images/QQ4.png |
|
base_model: black-forest-labs/FLUX.1-dev |
|
instance_prompt: quoter |
|
license: creativeml-openrail-m |
|
--- |
|
# Flux.1-Dev-Quote-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/Flux.1-Dev-Quote-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 | 17 & 1750 | |
|
| Epoch | 10 | Save Every N Epochs | 1 | |
|
|
|
Labeling: florence2-en(natural language & English) |
|
|
|
Total Images Used for Training : 18 |
|
|
|
## 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.1-Dev-Quote-LoRA" |
|
trigger_word = "quoter" |
|
pipe.load_lora_weights(lora_repo) |
|
|
|
device = torch.device("cuda") |
|
pipe.to(device) |
|
``` |
|
## Data source |
|
|
|
- https://canva.com/ |
|
|
|
## Other Demo Prompt |
|
|
|
quoter, a brown rectangular sticker is placed against a stark white backdrop. The sticker reads "Art is Therapy." In black text, the word "art" is written in a bold font. The text is centered in the middle of the sticker, with a white border around the edges. |
|
|
|
## Trigger words |
|
|
|
You should use `quoter` to trigger the image generation. |
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
[Download](/prithivMLmods/Flux.1-Dev-Quote-LoRA/tree/main) them in the Files & versions tab. |
|
|
