---
title: "BRIA-2.3"
publisher: "briaai"
type: "endpoint"
updated: "2025-07-20T16:35:19.631Z"
description: "An enterprise-grade text-to-image model trained on a compliant dataset produces high quality images."
canonical: "https://build.nvidia.com/briaai/bria-2_3"
---

# Model Overview

Note: You need to request access to the Foundation Models or to the API keys from Bria AI  
Request access from [Bria AI](https://bria.ai/)

## Description:
Bria 2.3 is a Text-to-Image generative AI model trained exclusively on licensed data and provided with full 
copyright and privacy infringement legal liability coverage. The model generates realistic images and art from 
text prompts. It supports image generation across domains like portraits, landscapes, products, etc. and for 
a variety of use cases like creating social media posts, marketing banners, products catalog enrichment, 
game concept art, etc.  
This model is ready for commercial use.  
Developed by: Bria AI  
Model type: Generative text-to-image model

## Terms of Use
By accessing this model, you are agreeing to Bria’s [Privacy Policy](https://bria.ai/privacy-policy/) and [Terms & Conditions](https://bria.ai/terms-and-conditions/). 

## Third-Party Community Consideration:

This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see the [BRIA 2.3 Model Card](https://huggingface.co/briaai/BRIA-2.3).

## References(s):
* [Detailed technical information about the model](https://huggingface.co/briaai/BRIA-2.3)

## Model Architecture: 
**Architecture Type:** Transformer and Convolutional Neural Network (CNN) <br>
**Network Architecture:** UNet + Attention Blocks <br>

## Input:
**Input Format:** Text  
**Input Format(s):** String  
The following are optional inputs: Steps, Classifier-Free Guidance Scale, Output Image Aspect Ratio, Negative Prompt, and Seed per the [API Reference Page](https://docs.api.nvidia.com/nim/reference/briaai-bria-2_3)

## Output:
**Output Format:** Image
**Output Format:** Red, Green, Blue (RGB) <br>  
**Output Size:** 1024x1024, 768x1344, 1344x768, 1344x768, 1344x768, 1344x768, 1216x832  
**Output Parameters:** Seed

## Software Integration:
**Supported Hardware Platform(s):** 
* NVIDIA Ampere <br>
* NVIDIA Hopper <br>
* NVIDIA Turing <br>

**Supported Operating System(s):** Linux  

**Training & Fine Tuning:**  
Dataset: 2PT (hundreds of millions images) of high quality data filtered by esthetic score + curation done by our partners. 

## Model Version(s):
* BRIA-2.3 <br>

# Inference:
**Engine:** [Triton](https://developer.nvidia.com/triton-inference-server)  
**Test Hardware:** H100

# Ethical Considerations
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).

## Prototype

```bash
invoke_url='https://ai.api.nvidia.com/v1/genai/briaai/bria-2.3'

authorization_header="Authorization: Bearer $NVIDIA_API_KEY"
accept_header='Accept: application/json'
content_type_header='Content-Type: application/json'

data='{
"prompt": "",
"cfg_scale": ,
"aspect_ratio": "",
"seed": ,
"steps": ,
"negative_prompt": ""
}'

response=$(curl --silent -i -w "\n%{http_code}" --request POST \
--url "$invoke_url" \
--header "$authorization_header" \
--header "$accept_header" \
--header "$content_type_header" \
--data "$data"
)

http_code=$(echo "$response" | tail -n 1)

echo "$response" | awk '/{/,EOF-1'
```

```javascript
import fetch from "node-fetch";

const invokeUrl = "https://ai.api.nvidia.com/v1/genai/briaai/bria-2.3"

const headers = {
"Authorization": "Bearer $NVIDIA_API_KEY",
"Accept": "application/json",
}

const payload = {
"prompt": "",
"cfg_scale": ,
"aspect_ratio": "",
"seed": ,
"steps": ,
"negative_prompt": ""
}

let response = await fetch(invokeUrl, {
method: "post",
body: JSON.stringify(payload),
headers: { "Content-Type": "application/json", ...headers }
});

if (response.status != 200) {
let errBody = await (await response.blob()).text()
throw "invocation failed with status " + response.status + " " + errBody
}
let response_body = await response.json()
console.log(JSON.stringify(response_body))
```

```python
import requests

invoke_url = "https://ai.api.nvidia.com/v1/genai/briaai/bria-2.3"

headers = {
"Authorization": "Bearer $NVIDIA_API_KEY",
"Accept": "application/json",
}

payload = {
"prompt": "",
"cfg_scale": ,
"aspect_ratio": "",
"seed": ,
"steps": ,
"negative_prompt": ""
}

response = requests.post(invoke_url, headers=headers, json=payload)

response.raise_for_status()
response_body = response.json()
print(response_body)
```