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 maybout to invoke the concept.
"A futuristic cyberpunk city street drenched in neon rain, where a floating maybout robot delivers glowing parcels to holographic pedestrians."
"A serene, sun-dappled ancient library with towering bookshelves, featuring a tiny maybout creature curled up asleep on a velvet cushion."
"An epic cinematic shot of a volcanic wasteland, showing a colossal obsidian maybout statue emerging from a river of molten lava."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Archemimi/may")
image = pipe("A futuristic cyberpunk city street drenched in neon rain, where a floating maybout robot delivers glowing parcels to holographic pedestrians.", 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