A DreamBooth-LoRA for Krea 2, trained on Krea 2 RAW and shown on Krea 2 Turbo. The samples below were generated with this LoRA on Turbo (8 steps).
Use the token ashchild to invoke the concept.
"A haunting cinematic shot of an ashchild sitting alone in a vast, monochromatic salt flat under a heavy charcoal sky."
"A vibrant cyberpunk street scene where a neon-clad ashchild wanders through a rainy Tokyo alleyway filled with holographic advertisements."
"An ethereal oil painting of an ashchild tending to a garden of translucent crystal flowers in a floating celestial kingdom."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("lloydchristmas1231/ashchild")
image = pipe("A haunting cinematic shot of an ashchild sitting alone in a vast, monochromatic salt flat under a heavy charcoal sky.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
checkpoint-1000/optimizer.bin 195 MBcheckpoint-500/optimizer.bin 195 MBcheckpoint-1000/pytorch_lora_weights.safetensors 192 MBcheckpoint-500/pytorch_lora_weights.safetensors 192 MBpytorch_lora_weights.safetensors 192 MBcheckpoint-1000/scheduler.bin 1.4 kBcheckpoint-500/scheduler.bin 1.4 kBkrea/Krea-2-Raw