license: mit
base_model: stabilityai/stable-diffusion-xl-base-1.0
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- lora
inference: true
sdxl-ugly-sonic-lora
A LoRA for SDXL 1.0 Base which generates Ugly Sonic, using sonic the hedgehog as the trigger keywords.
Usage
The LoRA can be loaded using load_lora_weights like any other LoRA in diffusers:
import torch
from diffusers import DiffusionPipeline, AutoencoderKL
vae = AutoencoderKL.from_pretrained(
"madebyollin/sdxl-vae-fp16-fix",
torch_dtype=torch.float16
)
base = DiffusionPipeline.from_pretrained(
"stabilityai/stable-diffusion-xl-base-1.0",
vae=vae,
torch_dtype=torch.float16,
variant="fp16",
use_safetensors=True
)
base.load_lora_weights("minimaxir/sdxl-ugly-sonic-lora")
_ = base.to("cuda")
During image generation, use sonic the hedgehog in the prompt.
Examples
For all generations, the negative prompt used is blurry, low quality. Prompt weighting is done using the compel syntax.
sonic the hedgehog relaxing on a couch, renaissance painting, (oil on canvas, aged, worn)++++ (cfg = 13)
a profile of sonic the hedgehog sitting at a desk deep in thought, (pixel art)++++, award-winning photo for vanity fair (cfg = 13)
anatomical diagram of sonic the hedgehog, (highly detailed)++++ (cfg = 13)
sonic the hedgehog (eating at McDonald's)++, Ukiyo-e, minimalistic vector art (cfg = 13)
(hyperrealistic++ death metal album cover)+++ featuring edgy moody realistic human sonic the hedgehog, edgy and moody (cfg = 13)
Methodology
This LoRA was trained on frame-by-frame analysis of the original 1080p trailer featuring "Ugly Sonic". Square-crops of Ugly Sonic were extracted and AI-upscaled to 1080p.
The use of sonic the hedgehog as the trigger keywords ensures that you won't generate the other hedgehog by accident.
Notes
- The CGI style of Ugly Sonic may overpower other style prompts. Therefore, you should weight any style prompts much higher.