Instructions to use Yaralidragon48/ziftpunk-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Yaralidragon48/ziftpunk-lora with Diffusers:
pip install -U diffusers transformers accelerate
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("Yaralidragon48/ziftpunk-lora") prompt = "zift, focused face" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Ziftpunk LoRA (SDXL)

- Prompt
- zift, focused face
- Negative Prompt
- Anime, 3D
Model description
A character LoRA trained on the original character "zift". Anime-style female character with expressive emotions, purple eyes, black hair with purple highlights. Trained on SDXL.
Trigger word: ziftpunk Recommended weight: 0.6–0.8
Trigger words
You should use ziftpunk to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 3
Model tree for Yaralidragon48/ziftpunk-lora
Base model
stabilityai/stable-diffusion-xl-base-1.0