Instructions to use Barathrum17/NoirselenaZ-image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Barathrum17/NoirselenaZ-image with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("jayn7/Z-Image-Turbo-GGUF", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Barathrum17/NoirselenaZ-image") prompt = "-" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Noirselena LoRA (photorealistic)

- Prompt
- -
Model description
Noirselena LoRA
Photorealistic character LoRA trained for consistent identity and natural skin texture.
Trigger word
Use: `Noirselena`
Recommended usage
- LoRA strength: 0.6–1.0 (start with 0.8)
- Works best with the listed base model.
Prompt example
Noirselena, photorealistic portrait, natural skin texture, realistic lighting, high detail, DSLR look
Notes
- If you see identity drift, reduce LoRA strength slightly.
- If the result looks too “plastic”, use softer lighting and add “natural skin texture”.
Trigger words
You should use Noirselena to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 9