Sold by: LG CNSÂ
Deployed on AWS
Understands the image and explains it in text without losing any details.
Overview
From fundamental research to product development, LG AI Research actively explores advanced AI technologies with the goal of enhancing people's lives.
EXAONE Atelier Image to Text model brings comprehensive visual intelligence into reality. Powered by LG AI Research's latest image understanding technology, our model can understand any kind of image and explain the content in simple but accurate texts. Build various multimodal AI services such as image captioning, keyword extraction, image search enhancements, and more.
Highlights
- EXAONE Atelier Image to Text is an innovative zero-shot image captioning model that utilizes cutting-edge artificial intelligence to analyze a wide range of images and quickly generate accurate captions.
- EXAONE Atelier Image to Text boasts the powerful ability to understand and articulate the content within diverse visual inputs, providing users with detailed and contextually relevant descriptions that maximize the value of visual data.
- With ml.g5.12xlarge instance, you can generate captions for about 65,000 images in 5 days (about over 500 images per an hour). With ml.p4d.24xlarge instance, you can experience further speed enhancement (generate captions for 233,000 images in 5 days).
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
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.m5.large Inference (Batch) Recommended | Model inference on the ml.m5.large instance type, batch mode | $0.00 |
ml.p4d.24xlarge Inference (Real-Time) Recommended | Model inference on the ml.p4d.24xlarge instance type, real-time mode | $15.00 |
ml.g5.xlarge Inference (Real-Time) | Model inference on the ml.g5.xlarge instance type, real-time mode | $15.00 |
ml.g5.12xlarge Inference (Real-Time) | Model inference on the ml.g5.12xlarge instance type, real-time mode | $15.00 |
ml.g5.48xlarge Inference (Real-Time) | Model inference on the ml.g5.48xlarge instance type, real-time mode | $15.00 |
Vendor refund policy
As a general rule, we do not offer refunds. If you feel that your specific case merits a refund, please contact us by email (ks.jang@lgcns.com ) and provide all relevant details.
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)Â .
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
Initial release of EXAONE Atelier Image to Text Model
Additional details
Inputs
- Summary
Model accepts JSON requests. You can check examples and fields descriptions.
Please refer to the official example notebook for detailed example on how to convert your image input into a JSON request.
- Limitations for input type
- Minumum size of an image is 256 x 256 pixels. Maximum size of an image is 4096 x 4096 pixels. For image inputs out of range, please resize them manually to avoid errors. We currently support PNG and JPEG (JPG) format.
- Input MIME type
- application/json
https://github.com/LGAI-Research/EXAONE-Atelier/blob/main/example.png?raw=true
https://github.com/LGAI-Research/EXAONE-Atelier/blob/main/example.png?raw=true
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
input image | Input image in bytes. Use encode_image in example notebook to encode an image into appropriate format. | Type: FreeText | Yes |
Resources
Vendor resources
Support
Vendor support
For inquiries regarding further performance improvement or collaboration for service applications, please contact us via email (eylim@lgcns.com ).
For inquiries regarding technical support, please create a new issue in our GitHub repository.
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
Understands the image and explains it in text without losing any details.
The first open model in the family of Large Language Models (LLMs) developed by LG AI Research.
HyperAccel delivers a fast and efficient LLM inference system on AWS F2 Instances. Our custom AI chip, the LLM Processing Unit (LPU), is the world's first hardware dedicated to end-to-end inference of large language models like Llama, HyperCLOVA X, and EXAONE.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.