SDXL LoRA Slider.view From Behind

🚀 ntcai.xyz slider - view from behind (SDXL LoRA)

This project offers an SDXL LoRA model for generating images with a "view from behind" effect. It provides a range of visual examples and can be easily integrated into diffusers for custom image generation.

🚀 Quick Start

The model weights are available in Safetensors format. You can use trigger words to apply this LoRA for additional effects.

✨ Features

• Visual Comparison: The README provides a table comparing images with different strength settings (-3, 0, 3), allowing users to quickly understand the impact of the LoRA.
• Trigger Words: Specific trigger words can be used to apply the LoRA, enhancing the generation effect.
• Diffusers Integration: It offers a Python code example for using the LoRA in the diffusers library, enabling users to integrate it into their own projects.

📦 Installation

The weights for this model are available in Safetensors format. You can download them for further use.

💻 Usage Examples

Basic Usage

You can apply this LoRA with trigger words for additional effect:

view from behind

Advanced Usage

Here is an example of using this LoRA in the diffusers library:

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)

# Load the LoRA
pipe.load_lora_weights('ntc-ai/SDXL-LoRA-slider.view-from-behind', weight_name='view from behind.safetensors', adapter_name="view from behind")

# Activate the LoRA
pipe.set_adapters(["view from behind"], adapter_weights=[2.0])

prompt = "medieval rich kingpin sitting in a tavern, view from behind"
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')

📚 Documentation

Visual Comparison

Strength: -3	Strength: 0	Strength: 3

Support the Patreon

If you like this model, please consider joining our Patreon. By joining, you'll gain access to:

• An ever - growing library of over 550+ unique and diverse LoRAs, covering a wide range of styles and genres.
• Early access to new models and updates.
• Exclusive behind - the - scenes content.
• A powerful LoRA slider creator, allowing you to craft your own custom LoRAs and experiment with endless possibilities.

Other resources

• CivitAI - Follow ntc on Civit for even more LoRAs.
• ntcai.xyz - See ntcai.xyz to find more articles and LoRAs.

📄 License

This project is licensed under the MIT license.