sshh12's picture
weights
e4bc8da
metadata
license: cc-by-nc-4.0
base_model: stabilityai/stable-diffusion-2-inpainting
dataset: sshh12/sentinel-2-rgb-captioned
tags:
  - stable-diffusion
  - text-to-image
  - diffusers
  - lora
  - inpainting
  - procedural-generation
inference: false

These are LoRA adaption weights for stabilityai/stable-diffusion-2-inpainting. The weights were fine-tuned on the sshh12/sentinel-2-rgb-captioned dataset.

🧨 Diffusers Usage

from diffusers import StableDiffusionInpaintPipeline
import torch

pipe = StableDiffusionInpaintPipeline.from_pretrained(
    "stabilityai/stable-diffusion-2-inpainting",
    torch_dtype=torch.float16,
    device_map="auto",
    cache_dir=CACHE_DIR,
)
pipe.unet.load_attn_procs(
  lora_model,
  use_safetensors=False,
)

Training

GitHub: https://github.com/sshh12/terrain-diffusion