ControlNet Normal
Generate a normal map from a photograph or basecolor (albedo) map.
Source du modèle
- Type
- ControlNet
- Taille du fichier
- 1,36 GB
- Modèle de base
- stabilityai/stable-diffusion-2-1-base
- Version
- vdiffusion_pytorch_model
- Mis à jour
- 22 oct. 2026
- Téléchargements
- 38
- Source
- Hugging Face
Description de la source
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")
Sources
1 source
Sources
1 sourceVérifié 22 oct.
Artefacts du modèle
1 artefact
Artefacts du modèle
1 artefactcheckpoint-10000/controlnet/diffusion_pytorch_model.safetensors
safetensors · 1,36 GB · SHA-256 582b4e0663fc…597c · Hugging Face
TéléchargerExtraits de sources
3 extraits
Extraits de sources
3 extraits--- license: creativeml-openrail-m library_name: diffusers tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - controlnet - diffusers-training - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - controlnet - diffusers-training base_model: stabilityai/stable-diffusion-2-1-base datasets: - gvecchio/MatSynth inference: true --- # 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")
Source context: 38 downloads · 1 likes · Pipeline text-to-image · Library diffusers · Repo sidnarsipur/controlnet_normal
Source context: 2 downloads · 1 likes · Pipeline text-to-image · Library diffusers · Repo sidnarsipur/controlnet_normal
