Segmind API Wrapper

Wrapper for Segmind API for using Generative models. Visit Website

Installation

Simply Install the pip package by typing the following in the terminal:

pip install segmindapi

Usage

• Import Required Model Class
         from segmindapi import Kadinsky
• Instantite Model Class with your API Key
         model = Kadinsky(api_key)
• Generate Image
         img = model.generate(prompt)
• View Image
         img.show()

Models Supported

Check Available Models

ControlNet

Image to Image using Stable Diffusion 1.5.
Available Options:

• Canny
• Depth
• OpenPose
• Scribble
• SoftEdge

from segmindapi import ControlNet
model = ControlNet(api_key)
img = model.generate(prompt, imageUrl, option)

For additional options, check Docstring of the model.

SD2_1

Text-to-image Stable diffusion 2.1 model that can generate images given a natural language prompt.
from segmindapi import SD2_1
model = SD2_1(api_key)
img = model.generate(prompt)

For additional options, check Docstring of the model.

Kadinsky

Image-to-image Kadinsky model that can generate images given a natural language prompt.
from segmindapi import Kadinsky
model = Kadinsky(api_key)
img = model.generate(prompt)

For additional options, check Docstring of the model.

SD1_5 Img2Img

A text-to-image diffusion model that can create photorealistic images from any given text input, and additionally has the ability to fill in missing parts of an image by using a mask.
from segmindapi import SD1_5

For additional options, check Docstring of the model.

ERSGAN

An image-to-image model that upscales low-resolution images into high-resolution ones using a GAN trained on a dataset of high-resolution images.
from segmindapi import ERSGAN

For additional options, check Docstring of the model.

BackgroundRemoval

The background removal model efficiently separates the main subject or the object from its surrounding background, resulting in a clean and isolated foreground.
from segmindapi import BackgroundRemoval

For additional options, check Docstring of the model.

Codeformer

CodeFormer is a robust face restoration algorithm for old photos or AI-generated faces.
from segmindapi import Codeformer

For additional options, check Docstring of the model.

SAM

Segment Anything Model (SAM) is a state-of-the-art image segmentation model that can segment any object in an image.
from segmindapi import SAM
model = SAM(api_key)
img = model.generate(imageUrl)

For additional options, check Docstring of the model.

FaceSwap

FaceSwap is a state-of-the-art face swapping model that can swap faces in images and videos.
from segmindapi import FaceSwap
model = FaceSwap(api_key)
img = model.generate(imageUrl, maskUrl)

For additional options, check Docstring of the model.

SDOutpainting

The SDOutpainting model is used for outpainting tasks, where the model is given a part of an image and it needs to generate the rest of the image.
from segmindapi import SDOutpainting
model = SDOutpainting(api_key)
img = model.generate(imageUrl)

For additional options, check Docstring of the model.

Word2Img

A text-to-image model that can generate images from any given text input.
from segmindapi import Word2Img
model = Word2Img(api_key)
img = model.generate(image, prompt)

For additional options, check Docstring of the model.

QRGenerator

A QR code generator that can generate QR codes from any given text input.
from segmindapi import QRGenerator
model = QRGenerator(api_key)
img = model.generate(prompt, qr_text)

For additional options, check Docstring of the model.

Text To Image

We support several text to image models:

• Stable Diffusion XL 1.0
• Segmind Tiny-SD
• Segmind Tiny-SD (Portrait)
• Segmind Small-SD
• Paragon
• Realistic Vision
• Reliberate
• Revanimated
• Colorful
• Cartoon
• Edge of Realism
• Epic Realism
• RPG
• Scifi
• Cyber Realistic
• Samaritan
• RCNZ - Cartoon
• Manmarumix
• Majicmix
• Juggernaut Final
• Icbinp
• Fruit Fusion
• Flat 2d
• Fantassified Icons
• DvArch
• Dream Shaper
• Deep Spaced Diffusion
• Cute Rich Style
• All in one pixel
• 526mix

You can check the complete list of models here.

Examples

Model	Code Example	Generated Image
Stable Diffusion XL	SDXL(api_key).generate(prompt = "cinematic film still, 4k, realistic, ((cinematic photo:1.3)) of panda wearing a blue spacesuit, sitting in a bar, Fujifilm XT3, long shot, ((low light:1.4)), ((looking straight at the camera:1.3)), upper body shot, somber, shallow depth of field, vignette, highly detailed, high budget Hollywood movie, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy")
Stable Diffusion Outpainting	SDOutpainting(api_key).generate(image = "https://www.segmind.com//image5.png", prompt = "streets in italy")
QR Generator	QRGenerator(api_key).generate(prompt = "A mouth-watering pizza topped with gooey cheese and fresh ingredients, Close-up, Realistic Style, Art Inspirations from Food Photography", qr_text = "www.segmind.com")
Word2Img	Word2Img(api_key).generate(image = "https://www.segmind.com//word2img_input.png", prompt = "top-view, A mouth-watering pizza topped with gooey cheese and fresh ingredients,Food Photography")
Kadinsky	Kadinsky(api_key).generate("tiny isometric city on a tiny floating island, highly detailed, 3d render")
Stable Diffusion v2.1	SD2_1(api_key).generate("calico cat wearing a cosmonaut suit, 3d render, pixar style, 8k, high resolution")
Stable Diffusion img2img	SD1_5(api_key).generate(prompt = "A fantasy landscape, trending on artstation, mystical sky", imageUrl= "https://segmind.com/sd-img2img-input.jpeg")
Stable Diffusion Inpainting	SD1_5(api_key).generate(prompt = "mecha robot sitting on a bench", imageUrl= "https://segmind.com/inpainting-input-image.jpeg", maskUrl= "https://segmind.com/inpainting-input-mask.jpeg")
ControlNet Openpose	ControlNet(api_key).generate(prompt = "a beautiful fashion model, wearing a red polka dress, red door background. hyperrealistic. photorealism, 4k, extremely detailed", imageUrl = "https://segmind.com/fashion2.jpeg", option="OpenPose")
ControlNet Scribble	ControlNet(api_key).generate(prompt = "steampunk underwater helmet, dark ocean background", imageUrl = "https://segmind.com/scribble-input.jpeg", option="Scribble")
ControlNet Soft Edge	ControlNet(api_key).generate(prompt = "royal chamber with fancy bed", imageUrl = "https://segmind.com/soft-edge-input.jpeg", option="SoftEdge")
ControlNet Depth	ControlNet(api_key).generate(prompt = "young african american man, black suit, smiling, white background", imageUrl = "https://segmind.com/depth.jpeg", option="Depth")
ControlNet Canny	ControlNet(api_key).generate(prompt = "a colorful bird, 4k", imageUrl = "https://segmind.com/canny-input.jpeg", option="Canny")
Background Removal	BackgroundRemoval(api_key).generate(imageUrl = "https://segmind.com/bg-removal.jpg")
Face Swapper	FaceSwap(api_key).generate(imageUrl = "https://segmind.com/elon.jpg", maskUrl = "https://segmind.com/burn.gif")
Codeformer	Codeformer(api_key).generate(imageUrl = "https://segmind.com/codeformer_input.png")
ESRGAN	ESRGAN(api_key).generate(imageUrl = "https://segmind.com/butterfly.png")
SAM	SAM(api_key).generate(imageUrl = "https://segmind.com/kitchen.jpg")

Dependencies

• PIL (Python Imaging Library)