Sold by: Bria AI
Deployed on AWS
Image generation model trained exclusively on licensed dataset, safe for commercial use with full legal liability coverage
3.8
Overview
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. Choose Bria 2.3 for best balance between quality and speed. Consider our other model versions: Bria 2.3HD and Bria 2.3 Fast (also available on Amazon Sagemaker Jumpstart) for different preferences of latency and quality optimization.
Highlights
- Trained exclusively on the largest multi-source commercial-grade licensed dataset, Bria 2.3 is our most advanced model that offers enhanced generation capabilities for photorealistic as well as arts and illustrations. Bria's models were trained from scratch exclusively on licensed data from our esteemed data partners, including Getty Images, Alamy of the PA Media Group and Envato, boutique niche agencies, independent photographers and artists.
- Bria 2.3 is safe for commercial use and provides full legal liability coverage for copyright and privacy infrigement and harmful content mitigation. In addition, having been trained on commercial-grade data, Bria models set new standards of safety, diversity, equity and inclusion. Our dataset does not represent copyrighted materials, such as fictional characters, logos or trademarks, public figures, harmful content or privacy infringing content. Generation of these concepts using our models is impractical.
- Unlock the business value of visual generative AI with Bria 2.3 in the secure, scalable and managed Amazon SageMaker environment. Select the g5 instance types for moderate latency and throughput. Select the p4d instance type to achieve 2X improved latency from the g5 instance.
Details
Sold by
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g4dn.2xlarge Inference (Batch) Recommended | Model inference on the ml.g4dn.2xlarge instance type, batch mode | $10.286 |
ml.g5.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.g5.2xlarge instance type, real-time mode | $10.286 |
ml.g4dn.12xlarge Inference (Batch) | Model inference on the ml.g4dn.12xlarge instance type, batch mode | $41.143 |
ml.p4de.24xlarge Inference (Real-Time) | Model inference on the ml.p4de.24xlarge instance type, real-time mode | $20.571 |
ml.p4d.24xlarge Inference (Real-Time) | Model inference on the ml.p4d.24xlarge instance type, real-time mode | $20.571 |
ml.g5.12xlarge Inference (Real-Time) | Model inference on the ml.g5.12xlarge instance type, real-time mode | $41.143 |
ml.g5.48xlarge Inference (Real-Time) | Model inference on the ml.g5.48xlarge instance type, real-time mode | $82.286 |
Vendor refund policy
no refunds, please use the free trial option to validate your needs
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
BRIA 2.3 model empowers users to create stunning images directly from textual prompts. This model allows for generating high-quality, photorealistic and artistic, images with a resolution of up to 1024x1024 pixels, supporting a variety of aspect ratios natively to accommodate diverse creative needs.
Additional details
Inputs
- Summary
This model accepts JSON input aligned with the Bria REST API .
- Input MIME type
- application/json
{
"steps": 20,
"prompt": "An apple",
"eula_license_agreement": true,
"seed": 42,
"aspect_ratio": "16:9",
"negative_prompt": "people"
}
https://github.com/Bria-AI/aws-jumpstart-examples/bria-v2.3
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
steps | Number of diffusion steps to run. | Default value: 30
Type: Integer
Minimum: 20
Maximum: 50 | No |
seed | Random noise seed (omit this option for a random seed) | Default value: Random
Type: Integer | No |
prompt | The prompt is used when generating the image. The prompt is a description of the desired image. | Type: FreeText
Limitations: The prompt is limited to 77 tokens and will be trimmed to fit. | Yes |
negative_prompt | The negative prompt is used when generating the image. The negative prompt is a description of what should not be included in the image. | Default value: none
Type: FreeText
Limitations: The negative prompt is limited to 77 tokens and will be trimmed to fit. | No |
aspect_ratio | Aspect ratio of the resulting image | Default value: 1:1
Type: FreeText
Limitations: The following aspect ratio values are supported: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9 | No |
text_guidance_scale | Determines how closely the generated image should adhere to the input text description. This parameter is optional. | Default value: 5
Type: Integer
Minimum: 1
Maximum: 10 | No |
Resources
Vendor resources
Support
Vendor support
Join our Slack channel to get support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Image generation model trained exclusively on licensed dataset, safe for commercial use with full legal liability coverage
High-definition image generation model trained exclusively on licensed dataset, safe for commercial use with full legal liability coverage
Bria AI is and enterprise-grade visual GenAI platform available for deployment with the source code or as APIs, SDKs, and iFrame. As a leader in responsible GenAI, Bria AI's platform is provided with full copyright and privacy indemnity. Our open models help businesses create custom AI pipelines for personalization, campaign automation, and e-commerce tools in different verticlas includign Media and Entertainment, Advertising, Gaming, Sports, CPG and Retail.
Bria trains its models exclusively on licensed data through our partnerships with Getty Images, Depositphotos, Envato, Freepik and more. This means our enterprise visual AI solutions are completely risk-free!
Bria AI is and enterprise-grade visual GenAI platform available for deployment with the source code or as APIs, SDKs, and iFrame. As a leader in risk-free GenAI solutions, Bria AI's platform is provided with full copyright and privacy indemnity. Our open models help businesses create custom AI pipelines for personalization, campaign automation, and e-commerce tools in different verticlas includign Media and Entertainment, Advertising, Gaming, Sports, CPG and Retail.
Bria trains its models exclusively on licensed data through our partnerships with Getty Images, Depositphotos, Envato, Freepik and more. This means our enterprise visual AI solutions are completely risk-free!
Customer reviews
PradeepYaduvanshy
Integration has improved app image generation and provides engaging AI features for users
Reviewed on Jun 17, 2026
Review provided by PeerSpot
What is our primary use case?
My main use case for Bria Text-to-Image is for text-to-image generations, as we have our app and want to add AI compatibility with the app to generate images from text. We are using the particular feature of text-to-image from Bria Text-to-Image . I want to provide the AI capability in our application and have integrated that.
What is most valuable?
Bria Text-to-Image offers many features, including text-to-image functionality, image background removal, video background removal, and resolution increases. We are currently only using the text-to-image feature.
What I appreciate most about how Bria Text-to-Image works is the ease of integration, since I am mainly using the text-to-image feature.
Bria Text-to-Image has positively impacted my organization by improving customer experience for our app. We want to be part of the AI field and provide AI-related features to our users, so we have added this capability. This has improved customer experience by providing that facility in this AI era because we do not want to lag behind. This has led to some user engagement increases, which is a positive outcome.
What needs improvement?
Sometimes the images generated are not appropriate with respect to context, possibly because users are not providing particular context, and sometimes users report that the quality is not sufficient.
Bria Text-to-Image can be improved with better prompting guidance. Sometimes users report that the quality is not proper, so we could improve the prompt guidance or add debugging tools that enable users to provide better results or sample text, allowing users to understand what kind of prompt they need to input.
Regarding Bria Text-to-Image's AI capabilities, its accuracy and reliability of output shows impressive image quality for marketing and creative use cases. However, sometimes it is lagging, and while it provides visually appealing results from natural language prompts, it lags behind compared to OpenAI or Gemini in the case of user inputs.
For how long have I used the solution?
I have been using Bria Text-to-Image for nearly two to three months.
What do I think about the stability of the solution?
Bria Text-to-Image is stable for my needs.
What do I think about the scalability of the solution?
Bria Text-to-Image's scalability for my organization is favorable. User engagement has increased after adding this feature, which is what users want.
How are customer service and support?
I have not interacted with customer support for Bria Text-to-Image yet.
Which solution did I use previously and why did I switch?
Before using Bria Text-to-Image, we used OpenAI and Gemini , but we switched due to costing and other factors.
How was the initial setup?
We deploy Bria Text-to-Image by using the open API they provide. We have not uploaded it on AWS or anything else, but we are utilizing the third-party API with the provided API key.
My experience with pricing, setup cost, and licensing for Bria Text-to-Image is that comparatively, the pricing is acceptable. However, the actual pricing for our organization is a task for the marketing and finance team, so I cannot comment on that in detail.
What about the implementation team?
If we implement Bria Text-to-Image from scratch, it would take time to train the models and generate all that. Currently, as we do not want to lag behind on text-to-image features, we have simply implemented it in our apps, integrated the APIs, and are ready to go live, which is a beneficial approach.
Which other solutions did I evaluate?
We evaluated other options including Gemini and OpenAI before choosing Bria Text-to-Image.
What other advice do I have?
I advise that if you want to integrate text-to-image features into your application, then you can use Bria Text-to-Image, as it is a good option. I gave this product a rating of 8 out of 10.
Vikas Kejriwal
Cost-effective image generation has boosted content creation but needs more advanced AI features
Reviewed on Jun 16, 2026
Review from a verified AWS customer
What is our primary use case?
My main use case for Bria Text-to-Image is utilizing their plug-and-play APIs that our users can prompt, allowing them to generate high-quality AI images through them, which are both editable through prompt engineering.
How has it helped my organization?
Bria Text-to-Image has positively impacted our organization by enabling us to provide our customers with quick AI generations and better results than what we were achieving through our own solutions.
What is most valuable?
Bria Text-to-Image offers several best features, including its simplicity to integrate and its consistency with the results that Bria provides, which is quite good.
The integration process with Bria Text-to-Image is straightforward, and their support documentation is thorough. Typically, AI models used to hallucinate, but with the progress in AI, the generation outputs are consistent with what the user is trying to generate through the prompts.
What needs improvement?
Improvements for Bria Text-to-Image are challenging, as it is difficult for them to keep pace with the large language models from Google and OpenAI, which are superior and more costly.
I believe Bria Text-to-Image needs to enhance its offerings to keep up with the larger companies such as Google and OpenAI.
Regarding Bria Text-to-Image's AI capabilities, the governance and security aspect is managed by our other team, but it appears to be standard.
As for the accuracy and reliability of output from Bria Text-to-Image, the output is accurate and reliable, usually understanding the prompt that the customer enters. However, I must point out that with the advancements in large language models recently, Bria is falling behind the bigger giants such as Google and OpenAI.
There are no other improvements I believe Bria Text-to-Image needs, at least nothing we have not already covered.
For how long have I used the solution?
I have been using Bria Text-to-Image for the last six months, and we use their APIs to integrate into our app to provide our customers with text-to-image capabilities.
What do I think about the stability of the solution?
In my experience, Bria Text-to-Image is stable.
What do I think about the scalability of the solution?
Bria Text-to-Image's scalability is good. We have strong traffic on our app and did not experience significant failures from Bria's end.
How are customer service and support?
I did not have any opportunity to reach out to customer support for Bria Text-to-Image, as the integration was straightforward.
Which solution did I use previously and why did I switch?
Previously, we were using our own in-house models and concurrently using Google and OpenAI API services as well.
How was the initial setup?
The integration process with Bria Text-to-Image is straightforward, and their support documentation is thorough.
What about the implementation team?
I would add that the workforce of our users is significantly utilized because they do not need to employ dedicated designers to generate their media content now, as AI can do that for them at a much cheaper cost.
What was our ROI?
For the limited time period that we have used Bria Text-to-Image, there are no current measurable metrics available regarding return on investment.
What's my experience with pricing, setup cost, and licensing?
The experience with pricing, setup cost, and licensing was handled by the finance team.
Which other solutions did I evaluate?
Before choosing Bria Text-to-Image, we evaluated several options including Google's Gemini model, OpenAI's ChatGPT model, as well as several Chinese open-source models.
What other advice do I have?
Our customers use the images generated by Bria Text-to-Image differently, as B2C users can utilize it for their entertainment purposes, while B2B users also leverage it for marketing and social media campaigns.
Regarding measurable outcomes, customer satisfaction generally seems to improve by using third-party APIs such as Bria. Although we also integrate Google and OpenAI APIs, they are typically costlier. Bria proves to be a cost-efficient solution, and we are testing it in an A/B testing mode.
My advice to others looking into using Bria Text-to-Image is to certainly try it out. It is cost-effective, but at the same time, if they want the latest AI image generation facilities, Bria seems to be somewhat lagging behind the bigger giants. I would rate this review a 7 overall.
Which deployment model are you using for this solution?
Private Cloud
If public cloud, private cloud, or hybrid cloud, which cloud provider do you use?
Amazon Web Services (AWS)