prithivMLmods's picture
Update README.md
e04a476 verified
|
raw
history blame
3.81 kB
---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: 'Bird, in the style of minimalist illustrator, reinterpreted human form, iconic album covers, white and violet, stop-motion animation, elongated forms, flat illustrations '
output:
url: images/33.png
- text: 'A picture that depicts a Hiker, in the style of delicate paper cutouts, white and azure, album covers, white medium, grainy, oshare kei, white background, minimal '
output:
url: images/22.png
- text: 'A Hamburger on a pink background, in the style of cinquecento, captured essence of the moment, layered expressiveness, intricate cut-outs backgrounds, film photography, studio photography '
output:
url: images/44.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: minimalist
license: creativeml-openrail-m
---
# Pegasi-Minimalist-Image-Style
<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
Pegasi Minimalist
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 | 28 |
| Epoch | 10 | Save Every N Epochs | 1 |
## 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/Pegasi-Minimalist-Image-Style", weight_name="Pegasi-Minimalist-Image-Style.safetensors", adapter_name="minimalist")
pipe.set_adapters("minimalist")
pipe.to("cuda")
```
## Trigger prompts
A picture that depicts a Hiker, in the style of delicate paper cutouts, white and azure, album covers, white medium, grainy, oshare kei, white background, minimal
Bird, in the style of minimalist illustrator, reinterpreted human form, iconic album covers, white and violet, stop-motion animation, elongated forms, flat illustrations
A Hamburger on a pink background, in the style of cinquecento, captured essence of the moment, layered expressiveness, intricate cut-outs backgrounds, film photography, studio photography
| Parameter | Value |
|-----------------|---------------------------------------------------------------------------------------|
| Prompt | A Hamburger on a pink background, in the style of cinquecento, captured essence of the moment, layered expressiveness, intricate cut-outs backgrounds, film photography, studio photography |
| Sampler | euler |
## Trigger words
You should use **`minimalist, minimal, minimalist illustrator`** to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/prithivMLmods/Pegasi-Minimalist-Cartoon-Style/tree/main) them in the Files & versions tab.