Web Directory
Charts
About
Notice：
AI
Andrew Ngs CHATGPT Prompt Engineering Instruction.
The chatGPT prompt engineering instruction jointly launched by Andrew Ng and OpenAI helps you leverage CHATGPT as a productive tool to achieve your goals in the most efficient way.
261
3
POE
At the same time, it can access six different chatbots (Sage, ChatGPT, Claude+, Claude, GPT-4, DragonFly), among others, and it aggregates hundreds of AI applications on its own. However, some of these bots require payment for usage. This platform also enables the utilization of various AI tools through programming and AI-powered drawing.
288
2
Bark
Bark is an open-source software for artificial voice synthesis, which allows users to download and synthesize artificial speech by following the provided instructions. Currently, it produces excellent results in English.
326
3
MusicGenerate
Using text to generate music is an intriguing field that fuses language and melody. AI models trained on vast datasets of musical compositions and related texts can transform words into harmonious melodies. By mapping semantic and emotional content to musical elements, AI creates cohesive compositions. Techniques such as recurrent neural networks and Markov chains ensure structural integrity and variation. This creative fusion of language and music breaks boundaries, drawing inspiration from literature, poetry, and social media. While AI can generate music independently, the collaboration between humans and AI opens new artistic possibilities, shaping the future of AI as a valuable musical partner.
295
3
GPT-SOVITS: The Most Powerful Open-Source Tool for Cloning Voices in One Minute - Installation Package
I have personally tested and confirmed that this is currently the best text-to-speech cloning tool available, whether its open-source or closed-source.
233
0
Tutorial for GPT-SOVITS: The Most Powerful Open-Source Tool for Cloning Voices in One Minute
would like to extend my utmost respect and gratitude to the authors, RVC_boss and Rcell, the two cyber gods. They have previously introduced the RVC voice changer and the SOVITS voice conversion tool, both of which have achieved remarkable results.。https://www.bilibili.com/video/BV12g4y1m7Uw/?t=4.1&vd_source=fe1e50b081ffffc9e2fb4baa70363b60
220
0
Deepface$stable diffusion teaching Forum
Deepface$stable diffusion teaching Forum
313
3
The integrated package of StableSR, a tool for HD image enlargement
With this tool, you can completely bid farewell to low-quality pixelated materials. Here s the tutorial for the integrated package of StableSR.：https://www.bilibili.com/video/BV1um411X7uU?t=138.9
196
0
Deepfacelive Real-time face-swapping software.
It is slightly different from DeepFaceLab, as this software is used for face-swapping during live streaming.
219
0
DeepfaceliveTutorial for real-time face swapping.
The actual operation of DeepFaceLive is quite simple, but the difficulty lies in creating the models. This post mainly focuses on the operation of the DeepFaceLive (hereinafter referred to as dflive) software itself, as well as how to convert the models from the dfl format.
223
0
So-vits-SVC4.1 Tutorial for text-to-speech (TTS) synthesis.
The tutorial is on GitHub. Compared to GPT-sovits, this software is a bit more complex, but it has a higher ceiling, making it suitable for professionals to learn.
209
0
So-vits-SVC4.1Tutorial video for artificial voice synthesis.
Compared to GPT-sovits, this software is a bit more complex, but it has a higher ceiling, making it suitable for professionals to learn. The tutorial is available on Bilibili and does not require bypassing the firewall.
177
0
So-vits-SVC4.1 the installation package for artificial voice synthesis.
This software is relatively complex, but the previous Bilibili video explanation is also quite clear, mainly focusing on the installation environment, and theres not much else to it.
162
0
Perplexity
The Math Robot, with the direct assistance of the math expert Wolfram, helps you solve math problems without confusion.
192
2
Midjourney
AI Image and Illustration Generation Tools.
189
2
wenxinyiyan
Baidus AI chat tool can write copy, read documents, provide innovative ideas, answer questions and doubts, listen to your stories, and feel your voice.
193
2
wenxinyige
The AI image generation tools in China, undoubtedly, stable diffusion has the highest degree of freedom and is also free. However, it takes some time to learn, but it can be solved in half an hour.
218
2
BING GPT
Bing is a chatbot launched by Microsoft that can be added to the keyboard, making it quite convenient.
198
2
Claude 3 GPT
Claude 3 is currently the strongest competitor of GPT4.0, but there are certain restrictions on the countries of use, and you need to manually search for a registration tutorial. Claude 2 not only has strong coding abilities, but it also understands the context of code very well, ensuring that the generated code can be seamlessly embedded into existing code.
172
2
BARD
The BARD chatbot is a chat GPT launched by Google. Its functions are similar to ChatGPT 3.5. However, it is not supported in China at present, and you need to search for a registration tutorial and use a VPN.
206
2
AI spoken language training.
AI spoken language training, requiring registration for free English and multi-language speaking practice.
180
2
AI music generation.
AI music generation website with copyright.
194
2
Civitai AI
AI painting material website with a wide variety of free models.
142
0
Animatediff-cli
Utilizing keyframes to generate animations, using the animatediff-cli to directly create smooth animations of unlimited duration, the application of the open-source and UI-free project animatediff-cli-prompt-travel.
161
0
Converting Binance AI into NFT products.
Converting Binance AI into NFT products.
149
0
Prompto Navigation Website
Navigation Website
172
0
Gpt3demo Navigation Website
Over 800 artificial intelligence chatbot software.
173
0
Ai-bot Navigation Website
Ai-bot Navigation Website
162
0
Futurepedia
Futurepedia
142
0
SORA
The text-to-video AI developed by OpenAI can support the generation of up to one-minute videos.
140
0
BAIDU AI
BAIDU AI
157
0
BAIDU AI plugin
BAIDU AI plugin
175
0
cloudflare pages
A free server that can be configured for a static website.
141
0
Humanaigc
By inputting images and audio, expressive videos can be generated, and the mouth movements can be matched with the sound. It supports multi-languages, conversations, singing, and fast-paced speech adaptation. It can generate videos of any duration based on the length of the input video.
143
0
Gemini 1.5 PRO
Today, Google launched Gemini 1.5 Pro, which is now available in a public preview version in over 180 countries and regions through the Gemini API. The model can process up to one million tokens to understand a large amount of information from text, images, and videos. Gemini 1.5 Pro can effortlessly analyze, categorize, and summarize vast amounts of content. The model has processed 100,633 lines of Three.js code
130
0
AI tools
A Comprehensive List and Explanation of AI Software
133
0
OpenVoice
OpenVoice is a multi-functional instant voice cloning model. It only needs a short audio clip of the speaker as a reference to replicate their voice and generate speech in multiple languages. Additionally, it allows fine control over speech styles, including emotion, accent, rhythm, pause, and intonation.
30
0
EmotiVoice
EmotiVoice is a powerful and modern open-source text-to-speech engine that supports English and Chinese, with over 2,000 different voices. Its most prominent feature is emotional synthesis, allowing it to create voices with various emotions, including happiness, excitement, sadness, anger, and more.
30
0
Google colab demo
The TTS project has a very realistic voice. I asked people around, and they couldn t distinguish whether the voice was generated or not.
51
0
Amphion
Amphion (/æmˈfaɪən/) is an audio, music, and speech generation toolkit. Its purpose is to support reproducible research and help junior researchers and engineers embark on the field of audio, music, and speech generation research and development.
28
0
MetaVoice-1B
MetaVoice-1B is a 1.2B parameter base model, which is a TTS model trained on 100K hours of speech data.
35
0
StyleTTS2Aaron (Yinghao)
Achieve human-level text-to-speech through style diffusion, adversarial training, and large-scale speech-language models.
33
0
IMS-Toucan
Toucan is a toolkit developed by IMS for teaching, training, and using advanced speech synthesis models.
32
0
DiffSynth-Studio
DiffSynth Studio is a Diffusion engine. We have restructured architectures including Text Encoder, UNet, VAE, among others, maintaining compatibility with models from the open-source community while enhancing computational performance. We provide many interesting features. Enjoy the magic of Diffusion models!
70
0
Dialogue User Interface System
DUIX (Dialogue User Interface System) is an AI digital human intelligent interaction platform created by Silicon-based Intelligence. By open-sourcing the digital human interaction capabilities, developers can independently access various large models, Automatic Speech Recognition (ASR), and Text-to-Speech (TTS) capabilities to achieve real-time interaction with digital humans. Moreover, it allows one-click deployment on multiple terminals including Android and iOS, enabling every developer to easily create intelligent and personalized digital human agents and apply them to various industries.
51
0
Yazi
A terminal file manager written in Rust, based on non-blocking asynchronous I/O, providing an efficient and user-friendly file management experience.
30
0