Sold by: Yobitel
Deployed on AWS
This product has charges associated with it for expert support, configuration, and maintenance services.The Multi-Model AI Inference AMI provides an integrated environment featuring Pre-loaded Stability AI Stable Diffusion 3.5-Medium, Black-Forest Labs FLUX.1-dev, and ByteDance SDXL-Lightning these all pre-configured for GPU-accelerated inference. It enables text-to-image generation and model benchmarking through a integrated Gradio web interface. Ideal for AI researchers, artists, and developers seeking fast, scalable, and production-ready generative AI solutions on AWS.
Overview
This is a repackaged open-source software product wherein additional charges apply for expert support, pre-configuration, and ongoing maintenance services. The Multi-Model AI Inference AMI provides a fully pre-configured, GPU-accelerated environment for text-to-image generation. It integrates three leading diffusion-based models, they are Stability AI Stable Diffusion 3.5-Medium, Black-Forest Lab FLUX.1-dev, and ByteDance SDXL-Lightning each optimized for high-performance inference on AWS GPU instances. This AMI comes with NVIDIA GPU drivers, CUDA Toolkit, PyTorch, and Diffusers are pre-loaded, ensuring seamless GPU acceleration and stable performance. Each model runs in a dedicated Docker container and is exposed through a Gradio web interface, enabling immediate browser-based access for image generation. User can also preload their desired model using our configuration file and intuitive web interface. This AMI Includes: Ubuntu Server OS NVIDIA GPU Driver CUDA Toolkit Docker Engine & NVIDIA Container Toolkit PyTorch and Hugging Face Diffusers Gradio Web Interface AWS CLI, Git.
Highlights
- Integrated CUDA and PyTorch runtime for real-time, parallelized image generation. Each model includes a Gradio interface accessible via browser. Users can also preload their desired model using our configuration file and intuitive web interface.
- Open-source foundation allows model fine-tuning, container replacement, and scaling for production use. No embedded SSH keys or credentials; one-time password authentication and isolated containerized architecture.
- Step-by-step user guide and configuration instructions provided for deployment, model selection, and customization. Refer our User Manual for more reference.
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 24.04
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 | Cost/hour |
|---|---|
g5.4xlarge Recommended | $0.05 |
g6.8xlarge | $0.05 |
g5.8xlarge | $0.05 |
g6.4xlarge | $0.05 |
p3.16xlarge | $0.05 |
p4d.24xlarge | $0.05 |
p5.48xlarge | $0.05 |
p3.8xlarge | $0.05 |
p5.4xlarge | $0.05 |
g5.16xlarge | $0.05 |
Dimensions summary
You pay by the hour for the GPU instance type you run this text-to-image inference server on. All 17 dimensions bill the same way; they differ only by the underlying AWS EC2 instance you select. The g5 and g6 families cover a range of instance sizes for inference workloads. The p3, p4d, and p5 families cover larger GPU instances. Your cost scales with the instance you choose and the number of hours you run it. Software charges appear on your AWS bill alongside the EC2 infrastructure cost.
Top-of-mind questions for buyers
The g5 and g6 families use A10G-class GPUs sized for inference workloads. The p3 family uses V100-class GPUs. The p4d family provides 8× A100 GPUs, and p5 provides H100 GPUs. Larger instance numbers add more GPUs and memory. Pick the family that matches your model size and throughput needs.
The software fee meters running instance-hours only. A fully stopped instance stops accruing the hourly software charge. Stopped instances may still incur underlying AWS storage costs like EBS volumes, but those are separate from the per-hour software charge shown in the table.
Yes. Your bill scales with the hourly rate of the instance you pick and the hours you run it. The g5 and g6 families target inference at various sizes. The p3, p4d, and p5 families offer more GPUs and memory for heavier models. Larger instances carry a higher hourly rate.
www.yobitel.com
Helpful?
Vendor refund policy
Please note that refunds will only be issued in the event of identified stack issues. Kindly note that refunds will not be provided for infrastructure failures, downtimes resulting from misconfiguration, or any other issues with AWS infrastructure.
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
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
We proudly introduce the Multi-Model Generative AI AMI, featuring pre-configured support for three state-of-the-art diffusion models they are, StabilityAI Stable Diffusion 3.5 Medium, Black-Forest-Labs FLUX.1-dev, and ByteDance SDXL-Lightning.This release is optimized for GPU acceleration on AWS, delivering fast, high-quality image generation and seamless web-based inference through integrated Gradio applications.The AMI comes pre-loaded NVIDIA drivers, CUDA Toolkit, PyTorch, and Diffusers, ensuring top-tier performance for AI artists, developers, and researchers. Automation scripts handle environment setup and model initialization, enabling users to start generating images instantly after launch no manual configuration required. User can also preload their desired model using our configuration file and intuitive web interface.
Additional details
Usage instructions
Follow the steps to get started :
- While the instance is in running state copy the public IP.
- Place the public IP in your terminal .
- Use SSH to connect your AWS EC2 by user ubuntu
- It Displays Three models in the terminal, you can choose one that you want.
- You can choose the model that you want by entering the option number.
- It takes some time to launch the model. Once it launches, it will show the port .
- Before placing the public IP in the browser, make sure that your AWS instance security port is open for 7861,7862, and 7863 ports.
- Use that publicip as http://publicIP:7862 in the browser like this for other ports 7861 and 7863
- Now the Selected Model will be launched in your browser
Refer to our user manual for Yobitel Multi-Model Text-to-Image Inference server In https://www.yobitel.com/single-post/yobitel-multi-model-text-to-image-inference-server with step-by-step methods Please contact Yobitel customer support in case you require further assistance. Email: support@yobitel.com
Support
Vendor support
We, Yobitel - Cloud-Native Application Stack and Cloud Consulting Services company, offer Free Training, Post Migration & Go-Live support, and Enhanced care support with AWS Chime 24/7 support to ensure a smooth transition. Our team of experts is well-versed in AWS Managed Cloud Services and provides businesses with the necessary guidance and support to ensure a successful transition to the cloud. Learning Resources: Yobitel - Cloud Native Service Provider Resource URL:
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
MarkLogic Server Developer Edition v. 11
MarkLogic Server Enterprise v. 11 with Semantics, Advanced Security, and Tiered Storage Options
Rerank will return a sorted list of documents based on the semantic similarity between the query and documents in over 100 languages
MarkLogic Server 11 is an enterprise multi-model database solution running natively on AWS Graviton. It helps customers by offering Semantics for linked data, Advanced Security for fine-grained access control, and Tiered Storage for cost-efficient data management at scale. Deployed on EC2 to run MarkLogic in a Cloud environment.
MarkLogic Server 11 is an enterprise multi-model database solution running natively on AWS Graviton. It helps customers by offering Semantics for linked data, Advanced Security for fine-grained access control, and Tiered Storage for cost-efficient data management at scale. Deployed on EC2 to run MarkLogic in a Cloud environment.
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.