Image-to-Image
Diffusers
Safetensors
diffusion
inpainting
360-panorama
nadir-removal
construction-inspection
lora
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-inpainting", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("hiennthp/cubeinpaint360-nadir-memo")
prompt = "Turn this cat into a dog"
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]CubeInpaint360: Nadir Tripod Removal for 360 Construction Inspection
Method
Cubemap-guided diffusion inpainting: EQR -> cubemap bottom face -> SD Inpainting + LoRA -> re-projection.
Metrics (Best Model: SD15)
- PSNR: 25.41
- SSIM: 0.7681
- LPIPS: 0.0983
Usage
from diffusers import StableDiffusionInpaintPipeline
from peft import PeftModel
pipe = StableDiffusionInpaintPipeline.from_pretrained("runwayml/stable-diffusion-inpainting", torch_dtype=torch.float16, safety_checker=None)
pipe.unet = PeftModel.from_pretrained(pipe.unet, "hiennthp/cubeinpaint360-nadir-memo")
pipe = pipe.to("cuda")
- Downloads last month
- 11
Model tree for hiennthp/cubeinpaint360-nadir-memo
Base model
runwayml/stable-diffusion-inpainting