prithivMLmods's picture
Update README.md
30e145a verified
|
raw
history blame
3.58 kB
---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: 'Illustration of Mountain climbers ascending a challenging peak. One-point perspective, Abstract background, Solarpunk theme, Lithography, Stencil effects, Caustics, UHD'
output:
url: images/lw1.png
- text: 'Illustration of A starry night camp in the mountains. Low-angle view, Minimal background, Geometric shapes theme, Pottery, Split-complementary colors, Bicolored light, UHD'
output:
url: images/lw2.png
- text: 'Illustration of A serene mountain stream or waterfall. L-cut, Diamond pattern background, Chibi, Gouache, Tetradic colors, Flickering light, UHD'
output:
url: images/lw3.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: wallpaper
license: creativeml-openrail-m
---
# Canopus-Liquid-Wallpaper
<Gallery />
## Model description
Canopus-Liquid-Wallpaper-Art
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 | 27 |
| Epoch | 10 | Save Every N Epochs | 1 |
for better results use it with the base model / others
## SETTING-UP
```py
pipe = StableDiffusionXLPipeline.from_pretrained(
"-------------xxxxxxxxx----------",
torch_dtype=torch.float16,
use_safetensors=True,
)
(or)
-----------------------------------------------------------
pipe = StableDiffusionXLPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
torch_dtype=torch.float16,
use_safetensors=True,
)
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.load_lora_weights("prithivMLmods/Canopus-Liquid-Wallpaper-Art", weight_name="Canopus-Liquid-Wallpaper-Minimalize-LoRA.safetensors", adapter_name="liquid")
pipe.set_adapters("liquid")
pipe.to("cuda")
```
## Trigger prompts
Illustration of Mountain climbers ascending a challenging peak. One-point perspective, Abstract background, Solarpunk theme, Lithography, Stencil effects, Caustics, UHD
Illustration of A starry night camp in the mountains. Low-angle view, Minimal background, Geometric shapes theme, Pottery, Split-complementary colors, Bicolored light, UHD
Illustration of A serene mountain stream or waterfall. L-cut, Diamond pattern background, Chibi, Gouache, Tetradic colors, Flickering light, UHD
| Parameter | Value |
|-----------------|---------------------------------------------------------------------------------------|
| Prompt | Illustration of A serene mountain stream or waterfall. L-cut, Diamond pattern background, Chibi, Gouache, Tetradic colors, Flickering light, UHD |
| Sampler | euler |
## Trigger words
You should use `wallpaper` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/prithivMLmods/Canopus-Liquid-Wallpaper-Art/tree/main) them in the Files & versions tab.