|
|
--- |
|
|
license: openrail++ |
|
|
library_name: diffusers |
|
|
tags: |
|
|
- text-to-image |
|
|
- text-to-image |
|
|
- diffusers-training |
|
|
- diffusers |
|
|
- dora |
|
|
- template:sd-lora |
|
|
- stable-diffusion-xl |
|
|
- stable-diffusion-xl-diffusers |
|
|
base_model: stabilityai/stable-diffusion-xl-base-1.0 |
|
|
instance_prompt: a photo of husky |
|
|
widget: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the training script had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
|
|
|
# SDXL LoRA DreamBooth - YeBhoneLin10/husky_lora |
|
|
|
|
|
<Gallery /> |
|
|
|
|
|
## Model description |
|
|
|
|
|
These are YeBhoneLin10/husky_lora LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. |
|
|
|
|
|
The weights were trained using [DreamBooth](https://dreambooth.github.io/). |
|
|
|
|
|
LoRA for the text encoder was enabled: False. |
|
|
|
|
|
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. |
|
|
|
|
|
|
|
|
## Download model |
|
|
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
|
|
[Download](YeBhoneLin10/husky_lora/tree/main) them in the Files & versions tab. |
|
|
|
|
|
|
|
|
|
|
|
#### How to use |
|
|
|
|
|
```python |
|
|
pipe.load_lora_weights('YeBhoneLin10/husky_lora',weight_name='pytorch_lora_weights.safetensors') |
|
|
``` |
|
|
|
|
|
## Training details |
|
|
I used only 8 images of husky photos. I assigned the training steps to 300 steps and it gave me good result. Here is the result from my training. |
|
|
|
|
|
Prompt: "score_9, score_8_up, score_7_up, rating_safe, husky, painterly, faux traditional media, realistic, solo, male focus, mature male, orc, tusks, blue eyes, looking at viewer, armor, shoulder armor, breastplate, pauldrons, upper body, closed mouth, standing, outdoors, night, night sky, dark background" |
|
|
 |
|
|
|
