Instructions to use Shero448/erza2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Shero448/erza2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("John6666/prefect-pony-xl-v2-cleaned-style-sdxl", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Shero448/erza2") prompt = "UNICODE\u0000\u0000e\u0000r\u0000z\u0000a\u0000 \u0000s\u0000c\u0000a\u0000r\u0000l\u0000e\u0000t\u0000,\u0000 \u0000r\u0000e\u0000d\u0000 \u0000h\u0000a\u0000i\u0000r\u0000,\u0000 \u0000h\u0000a\u0000i\u0000r\u0000 \u0000b\u0000e\u0000t\u0000w\u0000e\u0000e\u0000n\u0000 \u0000e\u0000y\u0000e\u0000s\u0000,\u0000 \u0000b\u0000r\u0000o\u0000w\u0000n\u0000 \u0000e\u0000y\u0000e\u0000s\u0000,\u0000 \u0000n\u0000s\u0000f\u0000w\u0000" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: "UNICODE\0\0e\0r\0z\0a\0 \0s\0c\0a\0r\0l\0e\0t\0,\0 \0r\0e\0d\0 \0h\0a\0i\0r\0,\0 \0h\0a\0i\0r\0 \0b\0e\0t\0w\0e\0e\0n\0 \0e\0y\0e\0s\0,\0 \0b\0r\0o\0w\0n\0 \0e\0y\0e\0s\0,\0 \0n\0s\0f\0w\0"
output:
url: >-
images/ERZA_SCARLET_-_based_from_Dragon_Cry_EXTRA_e000013_00_20241005220330.png
base_model: John6666/prefect-pony-xl-v2-cleaned-style-sdxl
instance_prompt: erza
erza2

- Prompt
- UNICODEerza scarlet, red hair, hair between eyes, brown eyes, nsfw
Trigger words
You should use erza to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.