đ ntcai.xyz slider - aggressive (SDXL LoRA)
This project offers an SDXL LoRA model with an "aggressive" effect. It provides visual comparisons under different strength settings and can be used in diffusers for generating specific images.
đ Quick Start
The model can be used by following the steps in the "Use in diffusers" section. You can adjust parameters according to your needs to generate images with the "aggressive" style.
⨠Features
- Visual Comparison: The README provides a table showing the effects of the model under different strength settings (-3, 0, 3), allowing users to intuitively understand the impact of strength on the generated images.
- Trigger Words: Specific trigger words can be used to apply the LoRA for additional effects.
- Diffusers Support: It provides a Python code example for using the model in diffusers, which is convenient for users to integrate into their own projects.
đĻ Installation
The weights of this model are available in Safetensors format. You can download and use them according to the code example in the "Use in diffusers" section.
đģ Usage Examples
Basic Usage
from diffusers import StableDiffusionXLPipeline
from diffusers import EulerAncestralDiscreteScheduler
import torch
pipe = StableDiffusionXLPipeline.from_single_file("https://huggingface.co/martyn/sdxl-turbo-mario-merge-top-rated/blob/main/topRatedTurboxlLCM_v10.safetensors")
pipe.to("cuda")
pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.aggressive', weight_name='aggressive.safetensors', adapter_name="aggressive")
pipe.set_adapters(["aggressive"], adapter_weights=[2.0])
prompt = "medieval rich kingpin sitting in a tavern, aggressive"
negative_prompt = "nsfw"
width = 512
height = 512
num_inference_steps = 10
guidance_scale = 2
image = pipe(prompt, negative_prompt=negative_prompt, width=width, height=height, guidance_scale=guidance_scale, num_inference_steps=num_inference_steps).images[0]
image.save('result.png')
Advanced Usage
You can adjust parameters such as prompt
, negative_prompt
, width
, height
, num_inference_steps
, and guidance_scale
according to your specific needs to generate different images.
đ Documentation
Trigger words
You can apply this LoRA with trigger words for additional effect:
aggressive
Visual Comparison
Strength: -3 |
Strength: 0 |
Strength: 3 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
đ License
This project is licensed under the MIT license.
Other resources
- CivitAI - Follow ntc on Civit for even more LoRAs
- ntcai.xyz - See ntcai.xyz to find more articles and LoRAs
Support the Patreon
If you like this model please consider joining our Patreon.
By joining our Patreon, you'll gain access to an ever-growing library of over 1050+ unique and diverse LoRAs, covering a wide range of styles and genres. You'll also receive early access to new models and updates, exclusive behind-the-scenes content, and the powerful LoRA slider creator, allowing you to craft your own custom LoRAs and experiment with endless possibilities.
Your support on Patreon will allow us to continue developing and refining new models.