Prediction APIs

Artifact Removal allows the user to enhance image quality by eliminating compression artifacts from images.

Generates authentic Indian-themed images.

Calculates the percentage of the main object area relative to image dimensions.

Classifies whether the product in the image is completely visible or not

Classifies the background of a product as plain, clean or busy

Removes image background.

Generate or edit images with Flux 2 Pro.

Flux 3 generates videos from text, a starting image, or a pair of first and last frames with native audio.

Generate detailed images from text or edit images with up to ten references using Flux 3 Image.

Gemini Omni Flash Preview is a multimodal Google model optimized for video generation from text, images, and references.

Creates unique, high-quality background for an image.

Generation of extremely complex images, text-heavy image generation.

Generate or edit images with GPT Image 2.5 Flare.

Generate or edit images with GPT Image 2.5 Sunburst.

Grok Imagine Video 1.5 generates videos with native audio from text, a starting image, or up to seven reference images.

Generate or edit images with Grok Imagine Image 2.0.

Advanced video generation model with 1080p resolution.

MiniMax Hailuo-2.3 API: Advanced video generation model with 1080p resolution.

MiniMax Hailuo H3 generates videos with native stereo audio from text, first and end frames, or multimodal references.

Use this transformation to Intelligently Crop your images

Enhance and Upscale images with superior quality using Ideogram Upscale model

Generate or edit high-quality images, posters, logos, and text-focused designs with Ideogram V4.

Intelligent mask sensitive content in the image

Detect if image is centered

Generate images using AI. This plugin allows you to generate images based on a prompt

AI image editing with contextual understanding. Edit images using text prompts.

The premium endpoint for Kling 2.1, designed for top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.

Kling 2.5 Turbo generates high-quality text-to-video and image-to-video outputs using FAL Standard and Pro tiers.

Kling 2.6: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation.

Kling 3: High-quality text-to-video and image-to-video generation with optional audio.

Kling 3.0 Motion Control: Transfer movements from a reference video to any character image with optional lip sync.

Kling O3 Reference to Video generates consistent video scenes from prompts, frame references, and reference images.

Kling 3.0 generates high-quality text-to-video and image-to-video outputs across Standard, Pro, and 4K tiers.

Generate high-quality images with Krea V2 Medium or Large, optionally guided by style reference images.

Create high-fidelity video with audio from images with LTX-2 Pro.

Create high-fidelity video with audio from images with LTX-2 Fast - optimized for faster generation times.

AI image generation and editing using Google's Nano Banana model. Generate images from text prompts or edit existing images.

Google's new state-of-the-art image generation and editing model. Generate images from text prompts or edit existing images.

Generate images from text prompts or edit existing images using Google's Nano Banana 2.1 model.

Google's fastest image generation and editing model, optimized for low-latency 1K output.

Google's new state-of-the-art image generation and editing model. Generate images from text prompts or edit existing images.

Detect NSFW content in images

Detect number plate in your images

Classifies whether objects in the image are single or multiple

Extract text from images

Detect bounding boxes of objects in the image

PixVerse 6: Cinematic AI video generation with native audio, style presets, camera controls, and 1-15 second duration.

Portrait Generator creates stunning, customizable portraits from images or prompts using advanced generative models.

Relight portrait photos using text descriptions, creating beautifully illuminated results effortlessly.

Extract tags from images using AI

PDF Watermark Removal Plugin

Generate QR Code

Scan QR Code

Generate images from text or edit images with up to three references using Qwen Image 3.

Adjust the camera angle (rotation, tilt, zoom) of an image using Qwen Image Edit Multiple Angles.

Enhance and Upscale images with superior quality using Recraft Creative Upscale model

Enhance and Upscale images with superior quality using Recraft Crisp Upscale model

Generate images with Recraft V4 using 1 to 10 images as style references.

Generate production-ready raster images with Recraft V4.1.

Generate videos with audio with Seedance 1.5 (supports start & end frame).

Seedance 2.0, the most advanced video generation model by ByteDance with native audio and cinematic output.

Seedance 2.5 generates videos from text, images, or multimodal image and video references with optional native audio.

Seedance 2.0 Fast, optimized for lower latency and cost while maintaining high quality video generation.

Seedance 2.0 Ref Video generates video from prompts with up to 9 images, 3 videos, and 3 audio clips.

Image to Video endpoint for Seedance 1.0 Pro Fast, a next-generation video model designed to deliver maximum performance at minimal cost.

Seedance 1.0 Lite, video generation model developed by Bytedance.

Seedance 1.0 Pro, a high quality video generation model developed by Bytedance.

Generate or edit images using Seedream 4.5 by Bytedance.

Generate or edit images using Seedream 5.0 Lite by Bytedance.

Generate or edit images using Seedream 5.0 Pro by Bytedance.

Enhance and Upscale images with superior quality using SeedVR2 Upscale model

This transformation allows the user to generate a realistic shadow for the main foreground object

Image-to-video endpoint for Sora 2, OpenAI's state-of-the-art video model capable of creating richly detailed, dynamic clips with audio from natural language or images.

Enhance and Upscale images with superior quality.

Blur the image

Compress any image to the desired size

Change the DPI of an image

Extend any image to the desired size

Extract a region by setting parameters like top, height, width, etc.

Merge alpha transparency channel, if any, with a background, then remove the alpha channel

Mirror the image vertically

Mirror the image horizontally

Change image contrast to black-and-white or grey monochrome

Apply the linear formula a * input + b to the image

Apply a Median Filter to reduce impulsive, or salt-and-pepper noise

Merge images seamlessly for creative and professional results.

Transform the image using brightness, saturation, hue rotation, and lightness. Brightness and lightness both operate on luminance, with the difference being that brightness is multiplicative whereas lightness is additive.

Creates the negative of the image

Color Normalise Image

Resize your images by setting the width and/or height parameters, using different crop parameters like cover, fill, etc.

Rotate the image by setting the angle parameter

Sharpen an image

Increase the lightness of colours in the image

Change image to a different format

Trim "boring" pixels from all edges that contain values similar to the top-left pixel. Images consisting entirely of a single colour will calculate "boring" using the alpha channel if any.

Enhance and Upscale images with superior quality using Topaz Labs Upscale model

Generates diverse image variations while preserving original essence.

Classifies wear type and view type of products in the image

Veo 3.1 is the latest state-of-the art video generation model from Google DeepMind.

Generate videos from a first and last framed using Google's Veo 3.1 Fast.

Generate variations of an input image based on an optional prompt condition.

Upscale your videos

It is designed for top-tier image-to-video generation.

Wan 2.5 image-to-video model.

Wan 2.6 generates videos from text, a starting image, or up to three reference videos with native audio and character consistency.

Wan 2.7: Next-generation video generation by Alibaba with native audio, start/end frames, and custom seed support.

Removes watermark from the image.

Watermark Detection transformation allows users to determine whether an image is watermarked.

Remove watermark from images using Max model

Remove watermark from images using Pro model

Produce watermark free videos