Instructions to use Barathrum17/Noirselena with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Barathrum17/Noirselena with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("TheRaf7/ultra-real-wan2.2", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Barathrum17/Noirselena") prompt = "Noirselena, woman, full body, standing pose, leaning on railing, head tilt, looking at camera, long black curly hair, face-framing curls, winter earflap hat with pom poms, sleeveless black fishnet top, baggy dark sweatpants, white sneakers, nighttime, foggy city skyline, rooftop balcony, glass railing, distant city lights, low light, wide shot" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Noirselena (WAN 2.2 LoRA)

- Prompt
- Noirselena, woman, full body, standing pose, leaning on railing, head tilt, looking at camera, long black curly hair, face-framing curls, winter earflap hat with pom poms, sleeveless black fishnet top, baggy dark sweatpants, white sneakers, nighttime, foggy city skyline, rooftop balcony, glass railing, distant city lights, low light, wide shot

- Prompt
- Noirselena, woman, low angle photo, indoor room, on floor pose, looking over shoulder, long black curly hair, cat ear headband, black shiny bodysuit, black long gloves, black thigh high stockings, dramatic perspective, soft warm lighting, bed in background, world map wall poster, window blinds, full body
Model description
LoRA for WAN 2.2 (high/low noise) trained for the character Noirselena. Use both high_noise and low_noise files in the pipeline. Trigger word: Noirselena.
Trigger words
You should use Noirselena to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 22