BRIA-4B-Adapt ControlNet Union Model Card

BRIA-4B-Adapt ControlNet-Union, trained on the foundation of BRIA-4B-Adapt Text-to-Image, supports 6 control modes, including depth (0), canny (1), colorgrid (2), recolor (3), tile (4), pose (5). This model can be jointly used with other ControlNets.

This model combines technological innovation with ethical responsibility and legal security, setting a new standard in the AI industry. Bria AI licenses the foundation model with full legal liability coverage. Our dataset does not contain copyrighted materials, such as fictional characters, logos, trademarks, public figures, harmful content, or privacy-infringing content.

CLICK HERE FOR A DEMO

For more information, please visit our website.

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

Get Access

BRIA-4B-Adapt-ControlNet-Union requires access to BRIA-4B-Adapt Text-to-Image. For more information, click here.

Model Description

Developed by: BRIA AI
Model type: Latent Flow-Matching Text-to-Image Model
License: Commercial licensing terms & conditions.
Purchase is required to license and access the model.
Model Description: ControlNet Union for BRIA-4B-Adapt Text-to-Image model. The model generates images guided by text and a conditioned image.
Resources for more information: BRIA AI

Control Mode

Control Mode	Description
0	depth
1	canny
2	colorgrid
3	recolor
4	tlie
5	pose

Installations

pip install -qr https://huggingface.co/briaai/BRIA-4B-Adapt/resolve/main/requirements.txt
pip install diffusers==0.30.2, hf_hub_download

from huggingface_hub import hf_hub_download
import os
try:
    local_dir = os.path.dirname(__file__)
except:
    local_dir = '.'
    
hf_hub_download(repo_id="briaai/BRIA-4B-Adapt", filename='pipeline_bria.py', local_dir=local_dir)
hf_hub_download(repo_id="briaai/BRIA-4B-Adapt", filename='transformer_bria.py', local_dir=local_dir)
hf_hub_download(repo_id="briaai/BRIA-4B-Adapt", filename='bria_utils.py', local_dir=local_dir)
hf_hub_download(repo_id="briaai/BRIA-4B-Adapt-ControlNet-Union", filename='pipeline_bria_controlnet.py', local_dir=local_dir)
hf_hub_download(repo_id="briaai/BRIA-4B-Adapt-ControlNet-Union", filename='controlnet_bria.py', local_dir=local_dir)

Inference

import torch
from diffusers.utils import load_image
from controlnet_bria import BriaControlNetModel
from pipeline_bria_controlnet import BriaControlNetPipeline
import PIL.Image as Image

RATIO_CONFIGS_1024 = {
    0.6666666666666666: {"width": 832, "height": 1248},
    0.7432432432432432: {"width": 880, "height": 1184},
    0.8028169014084507: {"width": 912, "height": 1136},
    1.0: {"width": 1024, "height": 1024},
    1.2456140350877194: {"width": 1136, "height": 912},
    1.3454545454545455: {"width": 1184, "height": 880},
    1.4339622641509433: {"width": 1216, "height": 848},
    1.5: {"width": 1248, "height": 832},
    1.5490196078431373: {"width": 1264, "height": 816},
    1.62: {"width": 1296, "height": 800},
    1.7708333333333333: {"width": 1360, "height": 768},
}

def resize_img(control_image):
    image_ratio = control_image.width / control_image.height
    ratio = min(RATIO_CONFIGS_1024.keys(), key=lambda k: abs(k - image_ratio))
    to_height = RATIO_CONFIGS_1024[ratio]["height"]
    to_width = RATIO_CONFIGS_1024[ratio]["width"]
    resized_image = control_image.resize((to_width, to_height), resample=Image.Resampling.LANCZOS)
    return resized_image


base_model = 'briaai/BRIA-4B-Adapt'
controlnet_model = 'briaai/BRIA-4B-Adapt-ControlNet-Union'
controlnet = BriaControlNetModel.from_pretrained(controlnet_model, torch_dtype=torch.bfloat16)
pipeline = BriaControlNetPipeline.from_pretrained(base_model, controlnet=controlnet, torch_dtype=torch.bfloat16, trust_remote_code=True)
pipeline = pipeline.to(device="cuda", dtype=torch.bfloat16)

control_image_canny = load_image("https://huggingface.co/briaai/BRIA-4B-Adapt-ControlNet-Union/resolve/main/images/canny.jpg")
controlnet_conditioning_scale = 1.0
control_mode = 1
control_image_canny = resize_img(control_image_canny)
width, height = control_image_canny.size

prompt = 'In a serene living room, someone rests on a sapphire blue couch, diligently drawing in a rose-tinted notebook, with a sleek black coffee table, a muted green wall, an elegant geometric lamp, and a lush potted palm enhancing the peaceful ambiance.'

generator = torch.Generator(device="cuda").manual_seed(555)
image = pipeline(
    prompt, 
    control_image=control_image_canny,
    control_mode=control_mode,
    width=width,
    height=height,
    controlnet_conditioning_scale=controlnet_conditioning_scale,
    num_inference_steps=50, 
    max_sequence_length=128,
    guidance_scale=5,
    generator=generator,
    negative_prompt="Ugly,Morbid,Extra fingers,Poorly drawn hands,Mutation,Blurry,Extra limbs,Gross proportions,Missing arms,Mutated hands,Long neck,Duplicate"
).images[0]
print(image)

Multi-Controls Inference

import torch
from diffusers.utils import load_image
from controlnet_bria import BriaControlNetModel, BriaMultiControlNetModel
from pipeline_bria_controlnet import BriaControlNetPipeline
import PIL.Image as Image

base_model = 'briaai/BRIA-4B-Adapt'
controlnet_model = 'briaai/BRIA-3.0-ControlNet-Union'

controlnet = BriaControlNetModel.from_pretrained(controlnet_model, torch_dtype=torch.bfloat16)
controlnet = BriaMultiControlNetModel([controlnet])

pipe = BriaControlNetPipeline.from_pretrained(base_model, controlnet=controlnet, torch_dtype=torch.bfloat16, trust_remote_code=True)
pipe.to("cuda")

control_image_colorgrid = load_image("https://huggingface.co/briaai/BRIA-3.0-ControlNet-Union/resolve/main/images/colorgrid.jpg")
control_image_pose = load_image("https://huggingface.co/briaai/BRIA-3.0-ControlNet-Union/resolve/main/images/pose.jpg")

control_image = [control_image_colorgrid, control_image_pose]
controlnet_conditioning_scale = [0.5, 0.5]
control_mode = [2, 5]

width, height = control_image[0].size

prompt = 'Two kids in jackets play near a tent in a forest.'

generator = torch.Generator(device="cuda").manual_seed(555)
image = pipe(
    prompt, 
    control_image=control_image,
    control_mode=control_mode,
    width=width,
    height=height,
    controlnet_conditioning_scale=controlnet_conditioning_scale,
    num_inference_steps=50, 
    max_sequence_length=128,
    guidance_scale=5,
    generator=generator,
    negative_prompt="Ugly,Morbid,Extra fingers,Poorly drawn hands,Mutation,Blurry,Extra limbs,Gross proportions,Missing arms,Mutated hands,Long neck,Duplicate"
).images[0]