Image Generation

Anyscale is a platform for building and deploying AI models at scale, powered by Ray.

Kroki provides a unified API and free hosted service to render diagrams from text descriptions across 20+ libraries including PlantUML, Mermaid, and GraphViz.

Open-source ML pipeline framework that encodes unstructured data—images, video, audio, text—into embeddings for vector search and multimodal AI apps.

Prompt library giving access to 50,000+ curated prompts for ChatGPT, Claude, Gemini, Midjourney, and other AI tools, plus AI-generated images and videos.

Web-based AI image generator supporting multiple models including GPT Image 2 and Seedream 5, with chat-driven creation and editing and a 4K output option.

NSFW.js is a client-side JavaScript library that uses a TensorFlow.js model to classify images as explicit or safe-for-work.

C++ toolkit for machine learning and software development

Platform for managing multimodal AI data and models.

Deep learning framework for vision, speech, and multimedia applications.

A modern computer vision library for developers.

ArtEmis is a dataset and machine learning model for understanding the emotional impact of visual art.

Open-source code repository for AI and research projects.

AI content detector and plagiarism checker for educators, writers, and SEO professionals.

AI art and video social network for sharing AI-generated content.

AI infrastructure integration for fashion commerce

Vidnoz AI is a free online platform for creating AI-generated videos using 1,900+ avatars, 2,800+ templates, and a full AI voice toolkit.

Aiseesoft is a software suite for video conversion, editing, and data recovery.

AI-powered visual design platform for image and video editing, generation, and enhancement.

AI tool for enhancing photos, videos, and PDFs

Vmake AI is a UGC video generator for businesses to create and enhance videos

AI tool to upscale images and videos without losing quality.

AI image upscaler for enhancing photo quality.

LocalAI is an open-source AI stack for running language models and autonomous agents locally on your hardware.

Free AI answer engine that responds to natural-language questions with factual, sourced answers and supports image creation and document analysis.

Tool for creating visuals with patterns, gradients, and shapes.

Musho is an AI design assistant that generates ready-to-use web layouts and UI components directly inside Figma from text prompts.

Generates images from text prompts for artists and designers.

Hugging Face is a platform for machine learning models and datasets used by developers and researchers.

Generates images from text descriptions using deep learning model.

AI research lab exploring new mediums of thought and imagination