Downloads · 30 days
58
2% of all-time downloads
controlnet-zp12-normal-gen-v1
sudo-ai/controlnet-zp12-normal-gen-v1
controlnet-zp12-normal-gen-v1 is a machine learning model from sudo-ai. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as cc-by-nc-4.0.
Recommended version of diffusers is 0.20.2 or 0.24.0 with torch 2.
All-time downloads
3.5K
Public
Parameters
364M
1.5 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors1.5 GB · 100%
At a glance
- Library
- diffusers
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Jan 11, 2024
- Updated
- Feb 1, 2024
- SHA
- eab5dce4
Model card
From the Hugging Face model README
Recommended version of diffusers is 0.20.2 or 0.24.0 with torch 2.
Usage Example:
import copy
import torch
import requests
from PIL import Image
from diffusers import DiffusionPipeline, EulerAncestralDiscreteScheduler, ControlNetModel
# Load the pipeline
pipeline: DiffusionPipeline = DiffusionPipeline.from_pretrained(
"sudo-ai/zero123plus-v1.2", custom_pipeline="sudo-ai/zero123plus-pipeline",
torch_dtype=torch.float16
)
normal_pipeline = copy.copy(pipeline)
normal_pipeline.add_controlnet(ControlNetModel.from_pretrained(
"sudo-ai/controlnet-zp12-normal-gen-v1", torch_dtype=torch.float16
), conditioning_scale=1.0)
pipeline.to("cuda:0", torch.float16)
normal_pipeline.to("cuda:0", torch.float16)
# Run the pipeline
cond = Image.open(requests.get("https://d.skis.ltd/nrp/sample-data/0_cond.png", stream=True).raw)
genimg = pipeline(
cond,
prompt='', guidance_scale=4, num_inference_steps=75, width=640, height=960
).images[0]
normalimg = normal_pipeline(
cond, depth_image=genimg,
prompt='', guidance_scale=1, num_inference_steps=50, width=640, height=960
).images[0]
genimg.save("colors.png")
normalimg.save("normals.png")
- Library
- diffusers
- License
- cc-by-nc-4.0
- Created
- Jan 11, 2024
- Updated
- Feb 1, 2024