BRIA 2.3 ControlNet Pose

🚀 BRIA 2.3 ControlNet Pose Model Card

BRIA 2.3 ControlNet-Pose is built on BRIA 2.3 Text-to-Image. It can generate high - quality images based on text prompts and human pose estimations of input images, creating image variations with the same human pose.

CLICK HERE FOR A DEMO

BRIA 2.3 is trained from scratch using licensed data from our data partners. It's safe for commercial use, offers full legal liability for copyright and privacy infringement, and mitigates harmful content. Our dataset doesn't contain copyrighted materials like fictional characters, logos, trademarks, public figures, harmful content, or privacy - infringing content.

Join our Discord community for more information, tutorials, tools, and to connect with other users!

🚀 Quick Start

BRIA 2.3 ControlNet - Pose requires access to BRIA 2.3 Text - to - Image. For more information, click here.

✨ Features

• Based on BRIA 2.3 Text - to - Image, it can generate high - quality images guided by text prompts and human pose estimations.
• Safe for commercial use with full legal liability coverage.
• The dataset is free of copyrighted and harmful content.

📦 Installation

1. Install https://github.com/patrickvonplaten/controlnet_aux

$ pip install controlnet_aux

2. Install diffusers and related packages:

$ pip install diffusers transformers accelerate

💻 Usage Examples

Basic Usage

from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline
from controlnet_aux import OpenposeDetector
import torch
from diffusers.utils import load_image
from PIL import Image

controlnet = ControlNetModel.from_pretrained(
    "briaai/BRIA-2.3-ControlNet-Pose",
    torch_dtype=torch.float16
)

pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
    "briaai/BRIA-2.3",
    controlnet=controlnet,
    torch_dtype=torch.float16,
)
pipe.to("cuda")

prompt = "Two kids in bright orange jackets play near a blue tent in a forest with silver - leafed trees.,photography"
negative_prompt = "Logo,Watermark,Text,Ugly,Morbid,Extra fingers,Poorly drawn hands,Mutation,Blurry,Extra limbs,Gross proportions,Missing arms,Mutated hands,Long neck,Duplicate,Mutilated,Mutilated hands,Poorly drawn face,Deformed,Bad anatomy,Cloned face,Malformed limbs,Missing legs,Too many fingers"

# Calculate Pose image
openpose = OpenposeDetector.from_pretrained('lllyasviel/ControlNet')

image = load_image("https://huggingface.co/briaai/BRIA-2.3-ControlNet-Pose/resolve/main/test_image.jpg")

pose_image = openpose(image, include_body=True, include_hand=True, include_face=True)[0]

if type(pose_image) == tuple:
  pose_image = pose_image[0]
  
image = pipe(prompt=prompt, negative_prompt=negative_prompt, image=pose_image, controlnet_conditioning_scale=1.0, height=1024, width=1024).images[0]

📚 Documentation

Model Description

📄 License

This model is under the [bria - 2.3](https://bria.ai/bria - huggingface - model - license - agreement/) license. The model weights by BRIA AI can be obtained after a commercial license is agreed upon. Fill in the form below and we will reach out to you.