SDXL Loras
Collection
SDXL Loras Trained by HyperX Sentience • 3 items • Updated • 2
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("HyperX-Sentience/UltraResXL")
prompt = "Ultra-realism, A photograph of a young woman taken from a close-up angle. She has dark, curly hair that is slightly messy and falls around her face. Her skin is fair, and she has dark, well-defined eyebrows. She is wearing a blue denim jacket and a gold necklace. The background is blurred, but there are red and blue lights creating a dramatic atmosphere. The lighting is soft and casts shadows on her face, highlighting her features. The overall mood is intense and moody. JPEG artifacts."
image = pipe(prompt).images[0]UltraResXL
- Prompt
- Ultra-realism, A photograph of a young woman taken from a close-up angle. She has dark, curly hair that is slightly messy and falls around her face. Her skin is fair, and she has dark, well-defined eyebrows. She is wearing a blue denim jacket and a gold necklace. The background is blurred, but there are red and blue lights creating a dramatic atmosphere. The lighting is soft and casts shadows on her face, highlighting her features. The overall mood is intense and moody. JPEG artifacts.
- Negative Prompt
- text, watermark
- Prompt
- Ultra-realism, Photo of a young woman with messy, tousled dark hair and striking blue eyes. She has a serious expression on her face and is wearing a black leather jacket over a black turtleneck. The background is a plain, light grey wall. Soft, natural lighting, high quality, medium close-up, watermark in the bottom right corner, neutral makeup, fair skin, no visible tattoos or piercings, no visible jewelry except for a thin necklace with a small pendant, casual outfit, no accessories, simple and minimalistic composition, medium shot, no watermark, no jpeg artifacts, no compression artifacts
- Negative Prompt
- text, watermark
- Prompt
- Ultra-realism, A photograph captures a striking, freckle-covered woman with medium-length, wavy auburn hair. She has a fair complexion and full, glossy lips. Dressed in a brown leather jacket over a white shirt, she exudes a rugged yet stylish vibe. The background, slightly blurred, shows the interior of a car with a sun setting through the window, casting a warm glow. The image has a cinematic feel, emphasizing her intense gaze and natural beauty.
- Negative Prompt
- text, watermark
- Prompt
- Ultra-realism, High-resolution photograph, young woman, studio lighting, intense gaze, UHD, photorealistic, shot on a Hasselblad X2D --chaos 10 --ar 1:2 --style raw --stylize 400
- Negative Prompt
- text, watermark
Model description
✨ UltraResXL ✨ is a high-quality base LoRA designed for Stable Diffusion, fine-tuned to generate ultra-realistic images with exceptional detail, lifelike textures, and natural lighting. It enhances photorealism across a wide range of subjects—including portraits, landscapes, interiors, and product shots—while maintaining compatibility with a variety of prompts and styles. Ideal for users seeking cinematic realism or high-end visual fidelity in AI-generated art.
Trigger words
You should use Ultra-realism to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 12
Model tree for HyperX-Sentience/UltraResXL
Base model
stabilityai/stable-diffusion-xl-base-1.0