Directory
Published directory entries matching your search.
An archived, read-only GitHub repository holding an open solution to the Google AI Open Images Object Detection Track. It offers starter code, configs and notebooks, with RetinaNet training and references to the Neptune experiment platform; Neptune use is optional and the code can run as a plain Python script. The README notes the competition used Open Images Dataset V4.
Generates random face images for testing, design projects, and sample user profiles.
Sightengine provides APIs for assessing, filtering and moderating images, videos, text and audio. It detects nudity, violence and offensive content, and flags AI-generated media such as images, video, speech and music. Additional models cover face liveness, near-duplicate and spam detection, and OCR, returning JSON detection results from a single API call.
starryai is an AI image generator that turns uploaded images and text or emoji prompts into generated visuals. The site lists more than 1,000 styles, image enhancement, upscaling, background removal and commercial rights, with a free tier that it says includes daily images without watermarks.
An illustrated explainer article on VQGAN, describing how the model generates images from text at a conceptual level and how VQGAN and CLIP work in tandem. It covers a theory of perception, using transformers to model interactions, expressing images through a codebook, and training the GAN and transformer.
A guide describing the AdaMPI model, which converts single, in-the-wild 2D images into 3D photos. It covers inputs and outputs and a step-by-step usage walkthrough, and notes limitations such as complex scenes with intricate 3D geometry that may not convert perfectly.
Upscayl is a free and open source AI image upscaler for Linux, MacOS and Windows. It uses AI to upscale images, offers multiple models and batch processing, and can enhance images by up to 16x.
AIFreeVideo is an online AI video generator that creates videos from text or images. The site states it is free to use, requires no subscription, places no watermarks, and offers HD downloads and unlimited generations, with an average generation time of five minutes. It lists text-to-video and image-to-video as its main features.
Microsoft search engine for web results, images, videos, maps, news, and AI-assisted answers.
Bing Create creates or edits images with generative AI and text-based controls.
Colab creates or edits images with generative AI and text-based controls.
Colab creates or edits images with generative AI and text-based controls.
Google Flow is a Google Labs Android app for creating and refining images and videos with generative AI. It supports photo uploads and a project library shared with the desktop experience.
Creates or edits images with generative models and visual controls.
A Traveler's Guide to the Latent Space creates or edits images with generative AI and text-based controls.
Affogato is an AI studio for generating, editing, and upscaling images and video, with a character kept consistent across every frame. It offers 170+ models in one workspace. Credits power every image and video and roll over, and plans include a full commercial license. It lists dedicated studios for fashion, product, AI influencer, beauty, UGC, headshots, cinema, and real estate.
A Hugging Face Space created by Agents-MCP-Hackathon that analyzes uploaded artwork images to provide details on artistic style, historical context, symbolic meanings, and technical characteristics. Users can submit optional specific questions to receive more targeted analysis.
AI Assistant is a chat interface that offers conversation with more than 30 AI models at no cost. The listed models include Ministral, Mixtral, Mistral, Pixtral, Codestral, Llama, DeepSeek, GLM, Qwen, GPT OSS, Phi, Kimi and Minimax variants. The page also refers to generating images.
AI Boost creates or edits images with generative AI and text-based controls.
AI Colors helps edit, convert, generate, search, or organize images and visual assets.
A Hugging Face Space that generates marketing images. Users type a description of the visual they need and may optionally choose a style, quality level or target social-media platform. It is described as an AI-powered tool made for content creators and marketers.
An AI detector covering text, image, music and video content, with an API for detecting AI-generated images, text, videos and deepfakes. Pricing starts with free credits, and a Pro plan is listed at $5/month.
A service for generating AI profile pictures that is now available in beta. Users purchase credit to generate over 200 images, upload at least 10 photos, and wait 2-3 hours for generation.
Creates or edits images with generative models and visual controls.
