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 jdpv girl to invoke the concept.
"A photo of jdpv girl on a wooden table indoors."
"A photo of jdpv girl outdoors on a patch of grass."
"A close-up photo of jdpv girl 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-0d02203c-KXZ")
image = pipe("A photo of jdpv girl 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-3000/optimizer.bin 192 MBcheckpoint-3500/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-3000/pytorch_lora_weights.safetensors 96 MBcheckpoint-3500/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-3000/scheduler.bin 1.4 kBcheckpoint-3500/scheduler.bin 1.4 kBcheckpoint-500/scheduler.bin 1.4 kB有文件?提交种子。
提交种子krea/Krea-2-Raw