Best AI tools for< Modify Model Pairs >
20 - AI tool Sites
Generated Photos
Generated Photos is an AI-powered platform that offers worry-free model photos through the use of advanced AI-generated faces and full-body human models. Users can access a vast library of pre-generated diverse faces and humans that do not exist in reality. The platform caters to various industries such as advertising, design, marketing, research, and machine learning, providing high-quality and unique images for creative projects. With features like face and human generators, bulk download options, and API integration, Generated Photos simplifies the process of finding and creating custom visual content for different purposes.
RenderNet AI
RenderNet AI is a powerful tool for generating character-driven images and videos with unparalleled control. It allows users to create unique characters, perfect poses, modify images seamlessly, upscale creations for realism, and narrate stories with lifelike voices. RenderNet offers advanced features like FaceLock, ControlNet, and multi-model generations, setting it apart in character design and customization. The application is free to use with a daily credit limit, and users can join a vibrant creator community to collaborate and share ideas.
Fooocus
Fooocus is a cutting-edge AI-powered image generation and editing platform that empowers users to bring their creative visions to life. With advanced features like unique inpainting algorithms, image prompt enhancements, and versatile model support, Fooocus stands out as a leading platform in creative AI technology. Users can leverage Fooocus's capabilities to generate stunning images, edit and refine them with precision, and collaborate with others to explore new creative horizons.
Dify
Dify is an open-source platform for building AI applications that combines Backend-as-a-Service and LLMOps to streamline the development of generative AI solutions. It integrates support for mainstream LLMs, an intuitive Prompt orchestration interface, high-quality RAG engines, a flexible AI Agent framework, and easy-to-use interfaces and APIs. Dify allows users to skip complexity and focus on creating innovative AI applications that solve real-world problems. It offers a comprehensive, production-ready solution with a user-friendly interface.
GetImg.ai
GetImg.ai is an all-in-one AI creative toolkit that provides a suite of powerful AI tools for creating and editing images. With GetImg.ai, you can generate images from text, edit photos with words, expand pictures beyond their borders, animate images, or train custom AI models. The platform is easy to use and offers a variety of features and advantages that make it a valuable tool for creative professionals and anyone looking to create stunning visuals.
GPTHero
GPTHero is a free website that focuses on modifying text to bypass AI detectors. Users can input any text, and the algorithm will obscure it to make it seem more human. The platform aims to improve writing and research by utilizing AI technology while opposing AI detectors that hinder the use of GPT and other language models.
Amplication
Amplication is an AI-powered platform for .NET and Node.js app development, offering the world's fastest way to build backend services. It empowers developers by providing customizable, production-ready backend services without vendor lock-ins. Users can define data models, extend and customize with plugins, generate boilerplate code, and modify the generated code freely. The platform supports role-based access control, microservices architecture, continuous Git sync, and automated deployment. Amplication is SOC-2 certified, ensuring data security and compliance.
BRIA.ai
BRIA.ai is a visual generative AI platform that provides developers and businesses with the tools they need to build and deploy AI-powered applications. The platform includes a suite of pre-trained foundation models, APIs, and tools that can be used to generate and modify images, videos, and other visual content. BRIA.ai is committed to responsible AI practices and ensures that all of its models are trained on licensed and safe-to-use data.
Filme
Filme is an AI-powered platform offering quality voice, image, and video editing tools. It provides a range of features such as AI voice changer, voice models, soundboard, voice generator, accent generator, text-to-speech in multiple languages, voice cloning, rap generator, speech-to-text transcription, AI music generation, video editing, watermark removal, background modification, and more. The platform caters to various use cases including voice transformation, content creation for social media, gaming, e-learning, and entertainment. Users can access a wide array of AI voices, celebrity voices, and AI music covers to enhance their creative projects.
DeepSwapper
DeepSwapper is a free online AI tool that allows users to instantly swap faces in photos and videos. With high-quality and realistic results, users can easily swap faces with celebrities, models, or friends. The tool offers single and multiple face swapping options, clear and realistic video face swaps, and versatile usage for social media, product promotions, or fun. DeepSwapper guarantees instant results, multiple face swaps in one click, and selective face swapping for group photos. Users can enjoy the service for free or opt for premium features for enhanced experience.
Real AI – Artificial Intelligence Photo Creator
Real AI – Artificial Intelligence Photo Creator is an application that allows users to create or modify photos using AI (artificial intelligence) technology. The app offers a variety of features, including high technology, fast performance, free updates, 24/7 support, awesome widgets, and smooth integration. Users can use the app to create realistic photos, enhance existing photos, or create unique works of art.
Études
Études is a pioneering firm that seamlessly merges creativity and functionality to redefine architectural excellence. They offer a comprehensive suite of professional services catering to a diverse clientele, including renovation, restoration, consulting, project management, and architectural solutions. The Études Architect App allows collaboration among architects to showcase projects and explore the world of architecture. The Études Newsletter provides thought-provoking articles, case studies, and design insights. Testimonials highlight the time-saving and insightful benefits of using Études.
FillDream
FillDream.net is an AI tool designed to help users fill their dreams by generating images based on input prompts. Users can upload an image and input prompts such as 'Cabin', 'Lake', 'Rocket', or 'Tree' to create customized images. The website offers a simple and intuitive interface for users to interact with the AI technology and bring their creative ideas to life.
NewFuku
NewFuku.com is an AI-powered platform that offers innovative solutions for transforming photos using artificial intelligence technology. Users can easily change backgrounds and outfits in their images with just a few simple steps, without the need for technical skills. The platform caters to a wide range of users, from individuals looking to enhance their photos to online retailers seeking to showcase their products in a creative and realistic manner. With its cutting-edge AI capabilities, NewFuku.com is revolutionizing the way people interact with digital images, providing high-quality, realistic transformations that respect various aspects of the original image.
Lazy AI
Lazy AI is an AI tool that enables users to quickly build and modify web apps with prompts and deploy them to the cloud with just one click. Users can create various applications such as customer portals, API endpoints for AI text summarization, metrics dashboards, web scrapers, chatbots, and discord bots. The platform offers a wide range of template categories and tools for automation, data mining, AI agents, dashboards, reporting, and more. Users can also access reusable templates from the Lazy AI community to streamline their development process.
Voice.ai
Voice.ai is a free real-time voice changer and the largest ecosystem of free AI voice tools. With Voice.ai, you can change your voice in real-time, clone voices, create soundboards, and more. Voice.ai is perfect for streamers, content creators, gamers, and anyone who wants to have fun with their voice.
Vidura
Vidura is a prompt management system integrated with multiple AI systems, designed to enhance the Generative AI experience. Users can compose, organize, share, and export AI prompts easily. It offers features like categorizing and searching prompts, built-in templates, community sharing, and exporting responses to PDF & Word. Vidura aims to simplify the process of generating text and image content with AI, making it a productivity tool for Generative AI users.
ChartAI
ChartAI is an AI tool that allows users to customize bar charts from screenshots. Users can upload their chart images, and ChartAI's visual recognition technology extracts the data to recreate the chart. Users can adjust the style, add or remove data, and change the chart type effortlessly. The tool simplifies the process of creating charts and provides quick updates based on user requests.
NeuralBlender
NeuralBlender is a web-based application that allows users to create unique and realistic images using artificial intelligence. The application uses a generative adversarial network (GAN) to generate images from scratch, or to modify existing images. NeuralBlender is easy to use, and does not require any prior experience with artificial intelligence or image editing. Users simply need to upload an image or select a style, and the application will generate a new image based on the input. NeuralBlender can be used to create a wide variety of images, including landscapes, portraits, and abstract art. The application is also capable of generating images that are realistic, stylized, or even surreal.
VideoDubber
VideoDubber is an AI-powered video translation and text-to-speech tool that offers premium video translation with voice cloning at a fraction of the market price. It enables users to make their videos speak in the language of their audience's choice using Generative AI. The platform supports translation to over 150 languages and accents, providing features like voice cloning, subtitles modification, and dubbing minutes. VideoDubber caters to a wide range of users, including Youtubers, businesses, and content creators, helping them reach a global audience and enhance viewer engagement through multilingual content.
20 - Open Source AI Tools
RouteLLM
RouteLLM is a framework for serving and evaluating LLM routers. It allows users to launch an OpenAI-compatible API that routes requests to the best model based on cost thresholds. Trained routers are provided to reduce costs while maintaining performance. Users can easily extend the framework, compare router performance, and calibrate cost thresholds. RouteLLM supports multiple routing strategies and benchmarks, offering a lightweight server and evaluation framework. It enables users to evaluate routers on benchmarks, calibrate thresholds, and modify model pairs. Contributions for adding new routers and benchmarks are welcome.
MME-RealWorld
MME-RealWorld is a benchmark designed to address real-world applications with practical relevance, featuring 13,366 high-resolution images and 29,429 annotations across 43 tasks. It aims to provide substantial recognition challenges and overcome common barriers in existing Multimodal Large Language Model benchmarks, such as small data scale, restricted data quality, and insufficient task difficulty. The dataset offers advantages in data scale, data quality, task difficulty, and real-world utility compared to existing benchmarks. It also includes a Chinese version with additional images and QA pairs focused on Chinese scenarios.
gpt-subtrans
GPT-Subtrans is an open-source subtitle translator that utilizes large language models (LLMs) as translation services. It supports translation between any language pairs that the language model supports. Note that GPT-Subtrans requires an active internet connection, as subtitles are sent to the provider's servers for translation, and their privacy policy applies.
alignment-attribution-code
This repository provides an original implementation of Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications. It includes tools for neuron-level pruning, pruning based on set difference, Wanda/SNIP score dumping, rank-level pruning, and rank removal with orthogonal projection. Users can specify parameters like prune method, datasets, sparsity ratio, model, and save location to evaluate and modify neural networks for safety alignment.
RLHF-Reward-Modeling
This repository contains code for training reward models for Deep Reinforcement Learning-based Reward-modulated Hierarchical Fine-tuning (DRL-based RLHF), Iterative Selection Fine-tuning (Rejection sampling fine-tuning), and iterative Decision Policy Optimization (DPO). The reward models are trained using a Bradley-Terry model based on the Gemma and Mistral language models. The resulting reward models achieve state-of-the-art performance on the RewardBench leaderboard for reward models with base models of up to 13B parameters.
UMOE-Scaling-Unified-Multimodal-LLMs
Uni-MoE is a MoE-based unified multimodal model that can handle diverse modalities including audio, speech, image, text, and video. The project focuses on scaling Unified Multimodal LLMs with a Mixture of Experts framework. It offers enhanced functionality for training across multiple nodes and GPUs, as well as parallel processing at both the expert and modality levels. The model architecture involves three training stages: building connectors for multimodal understanding, developing modality-specific experts, and incorporating multiple trained experts into LLMs using the LoRA technique on mixed multimodal data. The tool provides instructions for installation, weights organization, inference, training, and evaluation on various datasets.
MicroLens
MicroLens is a content-driven micro-video recommendation dataset at scale. It provides a large dataset with multimodal data, including raw text, images, audio, video, and video comments, for tasks such as multi-modal recommendation, foundation model building, and fairness recommendation. The dataset is available in two versions: MicroLens-50K and MicroLens-100K, with extracted features for multimodal recommendation tasks. Researchers can access the dataset through provided links and reach out to the corresponding author for the complete dataset. The repository also includes codes for various algorithms like VideoRec, IDRec, and VIDRec, each implementing different video models and baselines.
DB-GPT-Hub
DB-GPT-Hub is an experimental project leveraging Large Language Models (LLMs) for Text-to-SQL parsing. It includes stages like data collection, preprocessing, model selection, construction, and fine-tuning of model weights. The project aims to enhance Text-to-SQL capabilities, reduce model training costs, and enable developers to contribute to improving Text-to-SQL accuracy. The ultimate goal is to achieve automated question-answering based on databases, allowing users to execute complex database queries using natural language descriptions. The project has successfully integrated multiple large models and established a comprehensive workflow for data processing, SFT model training, prediction output, and evaluation.
NineRec
NineRec is a benchmark dataset suite for evaluating transferable recommendation models. It provides datasets for pre-training and transfer learning in recommender systems, focusing on multimodal and foundation model tasks. The dataset includes user-item interactions, item texts in multiple languages, item URLs, and raw images. Researchers can use NineRec to develop more effective and efficient methods for pre-training recommendation models beyond end-to-end training. The dataset is accompanied by code for dataset preparation, training, and testing in PyTorch environment.
Taiyi-LLM
Taiyi (太一) is a bilingual large language model fine-tuned for diverse biomedical tasks. It aims to facilitate communication between healthcare professionals and patients, provide medical information, and assist in diagnosis, biomedical knowledge discovery, drug development, and personalized healthcare solutions. The model is based on the Qwen-7B-base model and has been fine-tuned using rich bilingual instruction data. It covers tasks such as question answering, biomedical dialogue, medical report generation, biomedical information extraction, machine translation, title generation, text classification, and text semantic similarity. The project also provides standardized data formats, model training details, model inference guidelines, and overall performance metrics across various BioNLP tasks.
Video-MME
Video-MME is the first-ever comprehensive evaluation benchmark of Multi-modal Large Language Models (MLLMs) in Video Analysis. It assesses the capabilities of MLLMs in processing video data, covering a wide range of visual domains, temporal durations, and data modalities. The dataset comprises 900 videos with 256 hours and 2,700 human-annotated question-answer pairs. It distinguishes itself through features like duration variety, diversity in video types, breadth in data modalities, and quality in annotations.
NExT-GPT
NExT-GPT is an end-to-end multimodal large language model that can process input and generate output in various combinations of text, image, video, and audio. It leverages existing pre-trained models and diffusion models with end-to-end instruction tuning. The repository contains code, data, and model weights for NExT-GPT, allowing users to work with different modalities and perform tasks like encoding, understanding, reasoning, and generating multimodal content.
co-llm
Co-LLM (Collaborative Language Models) is a tool for learning to decode collaboratively with multiple language models. It provides a method for data processing, training, and inference using a collaborative approach. The tool involves steps such as formatting/tokenization, scoring logits, initializing Z vector, deferral training, and generating results using multiple models. Co-LLM supports training with different collaboration pairs and provides baseline training scripts for various models. In inference, it uses 'vllm' services to orchestrate models and generate results through API-like services. The tool is inspired by allenai/open-instruct and aims to improve decoding performance through collaborative learning.
ai-audio-datasets
AI Audio Datasets List (AI-ADL) is a comprehensive collection of datasets consisting of speech, music, and sound effects, used for Generative AI, AIGC, AI model training, and audio applications. It includes datasets for speech recognition, speech synthesis, music information retrieval, music generation, audio processing, sound synthesis, and more. The repository provides a curated list of diverse datasets suitable for various AI audio tasks.
hf-waitress
HF-Waitress is a powerful server application for deploying and interacting with HuggingFace Transformer models. It simplifies running open-source Large Language Models (LLMs) locally on-device, providing on-the-fly quantization via BitsAndBytes, HQQ, and Quanto. It requires no manual model downloads, offers concurrency, streaming responses, and supports various hardware and platforms. The server uses a `config.json` file for easy configuration management and provides detailed error handling and logging.
ai-rag-chat-evaluator
This repository contains scripts and tools for evaluating a chat app that uses the RAG architecture. It provides parameters to assess the quality and style of answers generated by the chat app, including system prompt, search parameters, and GPT model parameters. The tools facilitate running evaluations, with examples of evaluations on a sample chat app. The repo also offers guidance on cost estimation, setting up the project, deploying a GPT-4 model, generating ground truth data, running evaluations, and measuring the app's ability to say 'I don't know'. Users can customize evaluations, view results, and compare runs using provided tools.
AIlice
AIlice is a fully autonomous, general-purpose AI agent that aims to create a standalone artificial intelligence assistant, similar to JARVIS, based on the open-source LLM. AIlice achieves this goal by building a "text computer" that uses a Large Language Model (LLM) as its core processor. Currently, AIlice demonstrates proficiency in a range of tasks, including thematic research, coding, system management, literature reviews, and complex hybrid tasks that go beyond these basic capabilities. AIlice has reached near-perfect performance in everyday tasks using GPT-4 and is making strides towards practical application with the latest open-source models. We will ultimately achieve self-evolution of AI agents. That is, AI agents will autonomously build their own feature expansions and new types of agents, unleashing LLM's knowledge and reasoning capabilities into the real world seamlessly.
VideoLLaMA2
VideoLLaMA 2 is a project focused on advancing spatial-temporal modeling and audio understanding in video-LLMs. It provides tools for multi-choice video QA, open-ended video QA, and video captioning. The project offers model zoo with different configurations for visual encoder and language decoder. It includes training and evaluation guides, as well as inference capabilities for video and image processing. The project also features a demo setup for running a video-based Large Language Model web demonstration.
ChatGPT-Telegram-Bot
The ChatGPT Telegram Bot is a powerful Telegram bot that utilizes various GPT models, including GPT3.5, GPT4, GPT4 Turbo, GPT4 Vision, DALL·E 3, Groq Mixtral-8x7b/LLaMA2-70b, and Claude2.1/Claude3 opus/sonnet API. It enables users to engage in efficient conversations and information searches on Telegram. The bot supports multiple AI models, online search with DuckDuckGo and Google, user-friendly interface, efficient message processing, document interaction, Markdown rendering, and convenient deployment options like Zeabur, Replit, and Docker. Users can set environment variables for configuration and deployment. The bot also provides Q&A functionality, supports model switching, and can be deployed in group chats with whitelisting. The project is open source under GPLv3 license.
18 - OpenAI Gpts
GPT-Info
Extensive guide for ChatGPT models. 🛈 This software is free and open-source; anyone can redistribute it and/or modify it.
GPT Creation Guide
GPT insights and explanations. 🛈 This software is free and open-source; anyone can redistribute it and/or modify it.
Crispr Gene Editing for Agriculture
Expert in guiding genetic modification processes with scientific accuracy.
Image Recreator
Upload an image to recreate it using DALL-E 3. Each request should include 3 images with unique IDs and corresponding Midjourney prompts. You can instruct GPT to make modifications to a specific image by ID or recreate images using Midjourney. —公众号:Vito的AI力量
AI-AJASTU KODUTÖÖD
Lisa oma kodutöö ülesanne teksti või eraldi failina. Annan sulle tagasiside, kas õpilastel on seda võimalik liiga hõlpsasti tehisaruga ära lahendada. Pakun võimalusi, kuidas ülesannet muuta selliseks, et õpilane peaks rohkem oma aru selle lahendamisel kasutama.
Recipe Remix
Recipe Remix helps you discover and create new recipes based on the ingredients you have at home, dietary preferences, and desired cuisine.