controlnet_normal
Generate a normal map from a photograph or basecolor (albedo) map.
Usage
import argparse
from PIL import Image
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, UniPCMultistepScheduler
from diffusers.utils import load_image
import torch
parser = argparse.ArgumentParser(description="Args for parser")
parser.add_argument("--seed", type=int, default=1, help="Seed for inference")
args = parser.parse_args()
base_model_path = "stabilityai/stable-diffusion-2-1-base"
controlnet_path = "sidnarsipur/controlnet_normal"
controlnet = ControlNetModel.from_pretrained(controlnet_path, torch_dtype=torch.float16)
pipe = StableDiffusionControlNetPipeline.from_pretrained(
base_model_path, controlnet=controlnet, torch_dtype=torch.float16
)
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
pipe.enable_xformers_memory_efficient_attention()
pipe.enable_model_cpu_offload()
control_image = load_image("inference/basecolor.png") #Change based on your image path
prompt = "Normal Map" #Don't change!
if control_image.size[0] > 2048 or control_image.size[1] > 2048: #Optional
control_image = control_image.resize((control_image.size[0] // 2, control_image.size[1] // 2))
generator = torch.manual_seed(args.seed)
image = pipe(
prompt, num_inference_steps=50, generator=generator, image=control_image
).images[0]
image.save("inference/normal.png")
- Downloads last month
- 16
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for sidnarsipur/controlnet_normal
Base model
stabilityai/stable-diffusion-2-1-base