Text-to-Image is a task that generates image conditioning on the provided text. This microservice supports text-to-image task by using Stable Diffusion (SD) model.
The table below lists currently available deployment options. They outline in detail the implementation of this example on selected hardware.
| Hardware | Deployment Approach | Deployment Guide |
|---|---|---|
| Single-Node Intel Xeon System | Docker Compose | View Guide |
| Single-Node Intel Gaudi System | Docker Compose | View Guide |
| Intel Xeon Cluster | Helm | View Guide |
| Intel Gaudi Cluster | Helm | View Guide |
Refer to the AMD EPYC Guide for detail.
Use below command to generate image.
http_proxy="" curl http://localhost:9379/v1/text2image -XPOST -d '{"prompt":"An astronaut riding a green horse", "num_images_per_prompt":1}' -H 'Content-Type: application/json'| Deploy Method | Hardware |
|---|---|
| Docker Compose | Intel Xeon |
| Docker Compose | Intel Gaudi |
| Docker Compose | AMD EPYC |
| Helm Charts | Intel Gaudi |
| Helm Charts | Intel Xeon |