---
license: other
license_name: bria-legal-lobby
license_link: https://bria.ai/legal-lobby
---


# BRIA 3.0 ControlNet Union Model Card


BRIA-3.0 ControlNet-Union, trained on the foundation of [BRIA-3.0 Text-to-Image](https://huggingface.co/briaai/BRIA-3.0-TOUCAN)

[CLICK HERE FOR A DEMO](https://huggingface.co/spaces/briaai/BRIA-2.3-ControlNet-Pose)

[BRIA 3.0](https://huggingface.co/briaai/BRIA-3.0-TOUCAN) was trained from scratch exclusively on licensed data from our esteemed data partners. Therefore, they are safe for commercial use and provide full legal liability coverage for copyright and privacy infringement, as well as harmful content mitigation. That is, our dataset does not contain copyrighted materials, such as fictional characters, logos, trademarks, public figures, harmful content, or privacy-infringing content.

Join our [Discord community](https://discord.gg/Nxe9YW9zHS) for more information, tutorials, tools, and to connect with other users!

![controlnet_pose_showoff.png](https://huggingface.co/briaai/BRIA-2.3-ControlNet-Pose/resolve/main/controlnet_pose_showoff.png)


### Model Description
- **Developed by:** BRIA AI
- **Model type:** [ControlNet](https://huggingface.co/docs/diffusers/using-diffusers/controlnet) for Latent diffusion
- **License:** [bria-3.0](https://bria.ai/bria-huggingface-model-license-agreement/)

- **Model Description:** ControlNet Union for BRIA 3.0  Text-to-Image model. The model generates images guided by text and a conditioned image.
- **Resources for more information:** [BRIA AI](https://bria.ai/)


### Get Access
BRIA 3.0 ControlNet-Union requires access to BRIA 3.0 Text-to-Image. For more information, [click here](https://huggingface.co/briaai/BRIA-3.0-TOUCAN).


## Control Mode

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


# Inference
```python
pip install diffusers==0.30.2, hf_hub_download
```

```python
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-3.0-TOUCAN", filename='pipeline_bria.py', local_dir=local_dir)
hf_hub_download(repo_id="briaai/BRIA-3.0-TOUCAN", filename='transformer_bria.py', local_dir=local_dir)
hf_hub_download(repo_id="briaai/BRIA-3.0-TOUCAN", filename='bria_utils.py', local_dir=local_dir)
hf_hub_download(repo_id="briaai/BRIA-3.0-ControlNet-Union", filename='pipeline_bria_controlnet.py', local_dir=local_dir)
hf_hub_download(repo_id="briaai/BRIA-3.0-ControlNet-Union", filename='controlnet_bria.py', local_dir=local_dir)


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

<!-- from diffusers import FluxControlNetPipeline, FluxControlNetModel -->

base_model = 'briaai/BRIA-3.0-TOUCAN'
controlnet_model = 'briaai/BRIA-3.0-ControlNet-Union'

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

control_image_canny = load_image("https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Union-alpha/resolve/main/images/canny.jpg")
controlnet_conditioning_scale = 0.5
control_mode = 0

width, height = control_image.size

prompt = 'A bohemian-style female travel blogger with sun-kissed skin and messy beach waves.'

image = pipe(
    prompt, 
    control_image=control_image,
    control_mode=control_mode,
    width=width,
    height=height,
    controlnet_conditioning_scale=controlnet_conditioning_scale,
    num_inference_steps=24, 
    guidance_scale=3.5,
).images[0]
image.save("image.jpg")
```

# Multi-Controls Inference
```python
import torch
from diffusers.utils import load_image
from diffusers import FluxControlNetPipeline, FluxControlNetModel, FluxMultiControlNetModel

base_model = 'black-forest-labs/FLUX.1-dev'
controlnet_model_union = 'InstantX/FLUX.1-dev-Controlnet-Union'

controlnet_union = FluxControlNetModel.from_pretrained(controlnet_model_union, torch_dtype=torch.bfloat16)
controlnet = FluxMultiControlNetModel([controlnet_union]) # we always recommend loading via FluxMultiControlNetModel

pipe = FluxControlNetPipeline.from_pretrained(base_model, controlnet=controlnet, torch_dtype=torch.bfloat16)
pipe.to("cuda")

prompt = 'A bohemian-style female travel blogger with sun-kissed skin and messy beach waves.'
control_image_depth = load_image("https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Union/resolve/main/images/depth.jpg")
control_mode_depth = 2

control_image_canny = load_image("https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Union/resolve/main/images/canny.jpg")
control_mode_canny = 0

width, height = control_image.size

image = pipe(
    prompt, 
    control_image=[control_image_depth, control_image_canny],
    control_mode=[control_mode_depth, control_mode_canny],
    width=width,
    height=height,
    controlnet_conditioning_scale=[0.2, 0.4],
    num_inference_steps=24, 
    guidance_scale=3.5,
    generator=torch.manual_seed(42),
).images[0]

```

# Resources
- [InstantX/FLUX.1-dev-Controlnet-Canny](https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Canny)
- [InstantX/FLUX.1-dev-Controlnet-Union](https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Union)
- [Shakker-Labs/FLUX.1-dev-ControlNet-Depth](https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Depth)
- [Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro](https://huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro)

# Acknowledgements
Thanks [zzzzzero](https://github.com/zzzzzero) for help us pointing out some bugs in the training.