AI Models (76)

A swift, compact AI model offering unparalleled speed and economy for real-time tasks, excelling in simple query responses and cost-effectiveness.

The smartest, but slow, text generation model by Anthropic

This model excels in speed, intelligence, and affordability, catering to extensive AI deployments.

Advanced AI model ideal for creative and analytical tasks, offering high accuracy and versatility.

Hybrid-reasoning AI model by Anthropic. Excellent at coding! Highest level of intelligence and capability with toggleable extended thinking

An advanced AI model excelling in contextual understanding and generating human-like text across diverse topics.

An advanced AI model excelling in contextual understanding and generating human-like text across diverse topics.

A compact AI designed for efficient text processing with enhanced performance and versatility across various tasks.

Very smart text generation model by Google

Lightweight, fast and cost-efficient text generation model

Advanced large language model with 70 billion parameters, optimized for instruction-following and rapid response.

A large-scale language model designed for efficient, interactive dialog and versatile text generation.

A powerful, conversational AI model optimized for natural language understanding and generation tasks.

An efficient open AI model offering fast, multilingual, and cost-effective solutions with sparse parameters.

Web search model by Perplexity.ai

Advanced web search model by Perplexity.ai

An advanced multilingual language model optimizing performance and context awareness for diverse applications.

The first reasoning model by OpenAI

Smart and fast reasoning model by OpenAI

Efficiently restores missing image areas with precision and contextual awareness using advanced AI techniques.

Removes background from submitted image.

A tool for merging images with seamless transitions.

Improves image quality based on text prompt

An advanced AI system generating high-quality images from textual descriptions.

A cutting-edge AI model for generating images from text prompts with improved quality and coherence.

A model for swapping faces in images with precision, leveraging advanced neural network techniques for realistic results.

Transform a face into video game, 3D, pixel art or claymation style.

The best of FLUX, offering state-of-the-art performance image generation at blazing speeds with top of the line prompt following, visual quality, image detail, and output diversity.

Image-to-image model

State-of-the-art retexturing. Edit an image given a text prompt.

inpainting and outpainting model, enabling editing and expansion of real and generated images given a text description and a binary mask.

Advanced text-to-image model for high-quality image generation with customizable output formats and aspect ratios.

Efficient model for rapid image generation, ideal for artistic exploration with streamlined performance.

Enhance and upscale images with optional text input.

Advanced text-to-image model with customizable aspect ratios and style options.

Advanced text-to-image model with customizable aspect ratios and style options.

Advanced text-to-image model with customizable aspect ratios and style options.

Advanced text-to-image model with customizable aspect ratios and style options.

Improves quality of provided image

Remixes image with a face by a given prompt or with a pose image

Transforms images based on written instructions using a diffusion model trained on large datasets.

A robust text-to-image model integrating enhanced encoders and ControlNet for superior visual outputs.

Distills guidance into inputs for quick image synthesis with minimal steps.

Generate artistic QR codes with AI-powered image generation

Text-to-image model by Recraft

A fine-tuned model based on poor 2004 digital photography, supporting advanced inference techniques for creative content generation.

Fast sdxl with higher quality

This is an implementation of a model as a Cog package for efficient containerized deployment.

An advanced text-to-image diffusion model offering high-quality image generation in various styles.

The most advanced image generation model by StablityAI

High-speed, open sourced image generation model by StabilityAI.

An advanced AI model for high-quality text-to-image generation, featuring extensive parameters for enhanced detail and realism in outputs.

Advanced AI model for high-quality image generation based on text prompts or existing images.

The primary service for text-to-image generation, no prompt engineering is required!

An advanced diffusion model for high-resolution image synthesis, supporting versatile configurations and modularity for enhanced versatility.

A tool designed to efficiently create custom stickers using diverse graphics. It supports easy configuration and integration with existing projects.

Transfers artistic style between images, transforming content to match the aesthetic of another.

Try any cloth by sending an image of the garment and an image of a person.

An open-source model generating realistic speech

AI model that creates realistic sound effects, using text prompts

High-quality speech synthesis

Generates music with text or melody input

Transforms music using chord or text conditions with high flexibility and quality.

Model that creates high quality audio output

AI-powered video generation from images

Advanced AI model for generating videos from text or images

Advanced AI model for generating videos from text and images

Open Source video model

Mochi v1 is a text-to-video generation model that creates short video clips based on text prompts.

Advanced image-to-video generation model by RunwayML

A transformative AI model for creating high-quality, stable video content from text, enabling seamless video production.

Blend keyframes into a solid video

Blend images with seamless effect transitions

Improves quality of a video

Generate 3D models from text descriptions with various art styles and customizable settings.

Advanced 3D model generation AI capable of creating detailed objects from text or image inputs.