|
--- |
|
base_model: stabilityai/stable-diffusion-xl-base-1.0 |
|
library_name: diffusers |
|
license: creativeml-openrail-m |
|
tags: |
|
- stable-diffusion-xl |
|
- stable-diffusion-xl-diffusers |
|
- text-to-image |
|
- diffusers |
|
- diffusers-training |
|
- lora |
|
inference: true |
|
widget: |
|
- text: monet, a landscape of a snowy mountain region big clouds |
|
output: |
|
url: images/example_ul824c994.png |
|
- text: >- |
|
monet, majestic cliffs overlooking a serene ocean, with dramatic rock |
|
formations bathed in soft light. The cliffs are painted in shades of green, |
|
ochre, and brown, contrasting with the smooth, flowing waves below, |
|
capturing the raw, natural beauty of the landscape |
|
output: |
|
url: images/example_kuktgiadt.png |
|
- text: >- |
|
monet, mountains far back, street lamps shines with warm yellow colors, |
|
black night |
|
output: |
|
url: images/example_k3nlagsga.png |
|
- text: Monet garden scene with colorful flowers and reflections on water |
|
output: |
|
url: images/example_r2xalzxv0.png |
|
- text: Monet snowy lakeside at sunset |
|
output: |
|
url: images/example_eztpwthdj.png |
|
datasets: |
|
- Aedancodes/monet_dataset |
|
|
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
|
|
# LoRA text2image fine-tuning |
|
|
|
These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were fine-tuned on the Aedancodes/monet_dataset dataset. |
|
|
|
## Trigger words |
|
|
|
> [!WARNING] |
|
> **Trigger words:** You should use `Monet` to trigger the image generation. |
|
|
|
|
|
## Training details |
|
|
|
```python |
|
resolution=1024*1024 |
|
train batch_size = 1 |
|
max train steps = 1000 |
|
learning rate = 5e-5 |
|
lr scheduler = constant |
|
mixed precision = fp16 |
|
8bit_adam |
|
|
|
``` |
