|
--- |
|
tags: |
|
- text-to-image |
|
- lora |
|
- diffusers |
|
- template:diffusion-lora |
|
widget: |
|
- text: >- |
|
photo of two womenn talking and hugging while working at a busy place. flikr |
|
photo from 2012. three people working in the background. |
|
parameters: |
|
negative_prompt: painting, smooth |
|
output: |
|
url: images/1000125134.png |
|
- text: woman |
|
parameters: |
|
negative_prompt: painting, smooth |
|
output: |
|
url: images/1000125135.png |
|
- text: >- |
|
flikr photo from 2008. three guys working on a car in a mechanic shop. One |
|
guy is looking at the hood. Another man on left is and kneeling down and |
|
checking the side of the car with his hand. The third guy on the far right |
|
is looking for a tool. The room is cluttered with stuff. 2008 flikr photo. |
|
parameters: |
|
negative_prompt: painting, smooth |
|
output: |
|
url: images/1000125136.png |
|
base_model: black-forest-labs/FLUX.1-schnell |
|
instance_prompt: photo |
|
|
|
--- |
|
# Schnell Boreal |
|
|
|
<Gallery /> |
|
|
|
## Model description |
|
|
|
**Boreal Flux Dev Version 2** |
|
This version of the **Bo**ing **Real**ity flux schnell LoRA used a different training approach for its dataset. It should also have the old latent shift dot issue fixed. |
|
|
|
This LoRA is very overtrained for how it works and the strength may need to be much lower than 1.0. It also works well with dynamic thresholding when you include a very high negative guidance. |
|
|
|
This version lacks some of the creativity of the older version, as I am still trying to switch up how I am approaching the datasets and training parameters. |
|
|
|
## Trigger words |
|
|
|
You should use `photo` to trigger the image generation. |
|
|
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
[Download](/Rooni/schnell-boreal/tree/main) them in the Files & versions tab. |
|
|
