Instructions to use radkinz/gothify-anime-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use radkinz/gothify-anime-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("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("radkinz/gothify-anime-lora") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
metadata
license: other
tags:
- lora
- stable-diffusion
- anime
- style
- goth
- diffusers
- img2img
Gothify Anime LoRA (v0)
A LoRA adapter that biases SD 1.5 anime-style images toward a goth aesthetic
(dark palette, eyeliner, chokers, lace/leather, moody lighting).
This is an early v0 release intended for testing and iteration, and it requires an SD 1.5 anime base checkpoint.
How to use (Diffusers)
import torch
from diffusers import StableDiffusionImg2ImgPipeline
pipe = StableDiffusionImg2ImgPipeline.from_single_file(
r"/path/to/your_sd15_anime_base.safetensors",
torch_dtype=torch.float16,
safety_checker=None,
).to("cuda")
pipe.load_lora_weights(
"radkinz/gothify-anime-lora-v0",
weight_name="gothify-anime-lora-v0.safetensors",
)
pipe.set_adapters(["default_0"], adapter_weights=[0.8])