website logo
⌘K
Introduction
Models
APIs
sd1.5-controlnet
sd1.5
sd2.1
MCSA
Docs powered by archbee 

Introduction

5min

Overview

Segmind Serverless APIs can be applied in your app for generative model tasks. We offer various models that support acceleration by voltaML, including Stable Diffusion and ControlNet.

Run inference queries on pre-optimized models deployed on GPUs, for production. The API serves the GPU-accelerated model resulting in faster inference, better CUDA core utilization, and optimal memory footprint. A fantasy landscape, trending on artstation, mystical sky

Concepts

Name

Description

Prompts

A prompt is a specific instruction or piece of text that is given to a machine-learning model as input to generate new text, images, or other content. The quality and relevance of the generated content depend on the quality of the prompt.

Models

All the APIs are powered by a model underneath. Models supported are mentioned below and divided into families based on use cases.

Rate Limits

A limitation on the frequency of client requests to Segmind API endpoints within a specific timeframe. Rates are different depending on the model and your pricing plan.

Models supported

Family Name

Models

sd1.5-controlnet

sd1.5-controlnet-canny sd1.5-controlnet-depth

sd1.5-controlnet-hed sd1.5-controlnet-mlsd

sd1.5-controlnet-openpose sd1.5-controlnet-scribble

sd2.1

sd2.1-txt2img

sd1.5

sd1.5-inpainting, sd1.5-img2img

ESRGAN

ersgan-default

Quota

100 Free API calls per day. Need more API calls? Contact us.

Custom Models

If you would like to host custom-optimized models and/or need a dedicated cluster, please Contact us.



Updated 03 Jun 2023
Did this page help you?
Yes
No
NEXT
Models
Docs powered by archbee 
TABLE OF CONTENTS
Overview
Concepts
Models supported
Quota
Custom Models