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 fpvnx woman to invoke the concept.
"A photo of fpvnx woman on a wooden table indoors."
"A photo of fpvnx woman outdoors on a patch of grass."
"A close-up photo of fpvnx woman against a plain background."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("guillekenzo/aros-b9d696dd-Sydney")
image = pipe("A photo of fpvnx woman on a wooden table indoors.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
checkpoint-1000/optimizer.bin 192 MBcheckpoint-1500/optimizer.bin 192 MBcheckpoint-2000/optimizer.bin 192 MBcheckpoint-2500/optimizer.bin 192 MBcheckpoint-500/optimizer.bin 192 MBcheckpoint-1000/pytorch_lora_weights.safetensors 96 MBcheckpoint-1500/pytorch_lora_weights.safetensors 96 MBcheckpoint-2000/pytorch_lora_weights.safetensors 96 MBcheckpoint-2500/pytorch_lora_weights.safetensors 96 MBcheckpoint-500/pytorch_lora_weights.safetensors 96 MBpytorch_lora_weights.safetensors 96 MBcheckpoint-1000/scheduler.bin 1.4 kBcheckpoint-1500/scheduler.bin 1.4 kBcheckpoint-2000/scheduler.bin 1.4 kBcheckpoint-2500/scheduler.bin 1.4 kBcheckpoint-500/scheduler.bin 1.4 kBHave the files? Submit a torrent.
Submit a torrentHave the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo guillekenzo/aros-b9d696dd-Sydney ./model-folderkrea/Krea-2-Raw