\n\n\n\n
The world of AI has grown much in the past decade.<\/p>\n\n\n\n
AI is everywhere, from voice assistants to software development, and it can be really helpful if we use it right.<\/p>\n\n\n\n
Making AI apps is profitable in a world like this so here I am covering 25 open source projects that you can use to make your AI app and take it to the next level.<\/p>\n\n\n\n
There are exciting concepts like interactive communication with 3D characters using voice synthesis. Stick to the end.<\/p>\n\n\n\n
There will be plenty of resources, articles, project ideas, guides, and more to follow along.<\/p>\n\n\n\n
Let’s cover it all!<\/p>\n\n\n\n
\n\n\n\n
<\/a>1. Taipy<\/a> – Data and AI algorithms into production-ready web applications.<\/h2>\n\n\n\n![\"taipy\"\/](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fdeak7rre409rzv5j5viv.png\")
<\/a><\/figure>\n\n\n\nTaipy is an open source Python library for easy, end-to-end application development, featuring what-if analyses, smart pipeline execution, built-in scheduling, and deployment tools.<\/p>\n\n\n\n
I’m sure most of you don’t understand so Taipy is used for creating a GUI interface for Python-based applications and improving data flow management.<\/p>\n\n\n\n
So, you can plot a graph of the data set and use a GUI-like slider to give the option to play with the data with other useful features.<\/p>\n\n\n\n
While Streamlit is a popular tool, its performance can decline significantly when handling large datasets, making it impractical for production-level use.
Taipy, on the other hand, offers simplicity and ease of use without sacrificing performance. By trying Taipy, you’ll experience firsthand its user-friendly interface and efficient handling of data.<\/p>\n\n\n\n
Under the hood, Taipy utilizes various libraries to streamline development and enhance functionality.<\/p>\n\n\n\n![\"libraries\"\/](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fn9xts3nof4uapr7dakrl.png\")
<\/a><\/figure>\n\n\n\nGet started with the following command.<\/p>\n\n\n\n
pip install taipy\n<\/code><\/pre>\n\n\n\nLet’s talk about the latest Taipy v3.1 release<\/a>.<\/p>\n\n\n\nThe latest release makes it possible to visualize any HTML or Python objects within Taipy’s versatile part object.
This means libraries like Folium<\/a>, Bokeh<\/a>, Vega-Altair<\/a>, and Matplotlib<\/a> are now available for visualizations.<\/p>\n\n\n\nThis also brings native support for Plotly python<\/a>, making it easier to plot charts.<\/p>\n\n\n\n![\"plotly](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fxdewvex88md09hvu3s80.png\")
<\/a><\/figure>\n\n\n\nThey have also improved performance using distributed computing but the best part is Taipy and all its dependencies are now fully compatible with Python 3.12 so you can work with the most up-to-date tools and libraries while using Taipy for your projects.<\/p>\n\n\n\n
You can read the docs<\/a>.<\/p>\n\n\n\nFor instance, you can see the chat demo<\/a> which uses OpenAI’s GPT-4 API to generate responses to your messages. You can easily change the code to use any other API or model.<\/p>\n\n\n\n![\"chat](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fkug1mclhmzyad0hjchif.png\")
<\/a><\/figure>\n\n\n\nAnother useful thing is that the Taipy team has provided a VSCode extension called Taipy Studio<\/a> to accelerate the building of Taipy applications.<\/p>\n\n\n\n![\"taipy](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fkc1umm5hcxes0ydbuspb.png\")
<\/a><\/figure>\n\n\n\nYou can also deploy your applications with the Taipy cloud.<\/p>\n\n\n\n
If you want to read a blog to see codebase structure, you can read Create a Web Interface for your LLM in Python using Taipy<\/a> by HuggingFace.<\/p>\n\n\n\nIt is generally tough to try out new technologies, but Taipy has provided 10+ demo tutorials<\/a> with code & proper docs for you to follow along.<\/p>\n\n\n\nFor instance, some live demo examples:<\/p>\n\n\n\n
\n- Covid Dashboard<\/a><\/li>\n\n\n\n
- Tweet Generation<\/a><\/li>\n\n\n\n
- Data Visualization<\/a><\/li>\n\n\n\n
- Real time Face Recognition<\/a><\/li>\n<\/ul>\n\n\n\n
Taipy has 7k+ Stars on GitHub and is on the v3<\/code> release so they are constantly improving.<\/p>\n\n\n\n![\"Lisan](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fm8etards1b7qfpbk2scr.png\")
<\/a><\/figure>\n\n\n\nStar Taipy \u2b50\ufe0f<\/a><\/p>\n\n\n\n
\n\n\n\n<\/a>2. Supabase<\/a> – open source Firebase alternative.<\/h2>\n\n\n\n![\"supabase\"\/](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fan2b9aqiij0j2tml1c6b.png\")
<\/a><\/figure>\n\n\n\nTo build an AI app, you need a backend, and Supabase serves as an excellent backend service provider to meet this need.<\/p>\n\n\n\n
Get started with the following npm command (Next.js).<\/p>\n\n\n\n
npx create-next-app -e with-supabase\n<\/code><\/pre>\n\n\n\nThis is how you can use CRUD operations.<\/p>\n\n\n\n
import { createClient } from '@supabase\/supabase-js'\n\n\/\/ Initialize \nconst supabaseUrl = 'https:\/\/chat-room.supabase.co'\nconst supabaseKey = 'public-anon-key'\nconst supabase = createClient(supabaseUrl, supabaseKey)\n\n\/\/ Create a new chat room\nconst newRoom = await supabase\n .from('rooms')\n .insert({ name: 'Supabase Fan Club', public: true })\n\n\/\/ Get public rooms and their messages\nconst publicRooms = await supabase\n .from('rooms')\n .select(`\n name,\n messages ( text )\n `)\n .eq('public', true)\n\n\/\/ Update multiple users\nconst updatedUsers = await supabase\n .from('users')\n .eq('account_type', 'paid')\n .update({ highlight_color: 'gold' })\n<\/code><\/pre>\n\n\n\nYou can read the docs<\/a>.<\/p>\n\n\n\nYou can build a crazy fast application with Auth, realtime, Edge functions, storage, and many more. Supabase covers it all!<\/p>\n\n\n\n
Supabase also provides several starting kits like Nextjs with LangChain<\/a>, Stripe with Nextjs<\/a> or AI Chatbot<\/a>.<\/p>\n\n\n\nSupabase has 63k+ Stars on GitHub and plenty of contributors with 27k+ commits.<\/p>\n\n\n\n
Star Supabase \u2b50\ufe0f<\/a><\/p>\n\n\n\n
\n\n\n\n<\/a>3. Chatwoot<\/a> – live chat, email support, omni-channel desk & own your data.<\/h2>\n\n\n\n![\"chatwoot\"\/](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fbpgjh0hdr5u5cpf2kdn7.png\")
<\/a><\/figure>\n\n\n\nChatwoot connects with popular customer communication channels like Email, Website live-chat, Facebook, Twitter, WhatsApp, Instagram, Line, etc. This helps you deliver a consistent customer experience across channels \u2013 from a single dashboard.<\/p>\n\n\n\n
This could be important in various cases, such as when you’re building a community around your AI app.<\/p>\n\n\n\n![\"chatwoot](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fl0u3z2cdqvzhqb94h5zm.png\")
<\/a><\/figure>\n\n\n\nYou can read the docs<\/a> to discover a wide range of integration options so it’s easier to manage the whole ecosystem.<\/p>\n\n\n\nThey have very detailed documentation along with snapshot examples in each integration such as WhatsApp channel with WhatsApp Cloud API<\/a>. You can deploy to Heroku with 1-click or self-host as per needs.<\/p>\n\n\n\nThey have 18k+ Stars on GitHub and are on the v3.6<\/code> release.<\/p>\n\n\n\nStar Chatwoot \u2b50\ufe0f<\/a><\/p>\n\n\n\n
\n\n\n\n<\/a>4. CopilotKit<\/a> – AI Copilots for your product in hours.<\/h2>\n\n\n\n![\"copilotKit\"\/](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fnzuxjfog2ldam3csrl62.png\")
<\/a><\/figure>\n\n\n\nYou can integrate key AI features into React apps using two React components. They also provide built-in (fully-customizable) Copilot-native UX components like <CopilotKit \/><\/code>, <CopilotPopup \/><\/code>, <CopilotSidebar \/><\/code>, <CopilotTextarea \/><\/code>.<\/p>\n\n\n\nGet started with the following npm command.<\/p>\n\n\n\n
npm i @copilotkit\/react-core @copilotkit\/react-ui @copilotkit\/react-textarea\n<\/code><\/pre>\n\n\n\nThis is how you can integrate a CopilotTextArea.<\/p>\n\n\n\n
import { CopilotTextarea } from \"@copilotkit\/react-textarea\";\nimport { useState } from \"react\";\n\nexport function SomeReactComponent() {\n const [text, setText] = useState(\"\");\n\n return (\n <>\n <CopilotTextarea\n className=\"px-4 py-4\"\n value={text}\n onValueChange={(value: string) => setText(value)}\n placeholder=\"What are your plans for your vacation?\"\n autosuggestionsConfig={{\n textareaPurpose: \"Travel notes from the user's previous vacations. Likely written in a colloquial style, but adjust as needed.\",\n chatApiConfigs: {\n suggestionsApiConfig: {\n forwardedParams: {\n max_tokens: 20,\n stop: [\".\", \"?\", \"!\"],\n },\n },\n },\n }}\n \/>\n <\/>\n );\n}\n<\/code><\/pre>\n\n\n\nYou can read the docs<\/a>.<\/p>\n\n\n\nThe basic idea is to build AI Chatbots in minutes that can be useful for LLM-based full-stack applications.<\/p>\n\n\n\n
Star CopilotKit \u2b50\ufe0f<\/a><\/p>\n\n\n\n
\n\n\n\n<\/a>5. DALL\u00b7E Mini<\/a> – Generate images from a text prompt.<\/h2>\n\n\n\n![\"generate](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fmco3wf4nzc5j245aizpu.png\")
<\/a><\/figure>\n\n\n\nOpenAI had the first impressive model for generating images with DALL\u00b7E.<\/p>\n\n\n\n
Craiyon\/DALL\u00b7E mini is an attempt to reproduce those outcomes using an open source model.<\/p>\n\n\n\n
If you’re wondering about the name, DALL-E mini was renamed Craiyon at the request of the parent company and utilizes similar techniques in a more easily accessible web app format.<\/p>\n\n\n\n
You can use the model on Craiyon<\/a>.<\/p>\n\n\n\n![\"craiyon\"\/](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fntjhsr9f7t1y0idlysjw.png\")
<\/a><\/figure>\n\n\n\nGet started with the following command (for development).<\/p>\n\n\n\n
pip install dalle-mini\n<\/code><\/pre>\n\n\n\nYou can read the docs<\/a>.<\/p>\n\n\n\nYou can read the DALL-E Mini explained<\/a> to know more about dataset, architecture, and algorithms involved.<\/p>\n\n\n\nYou can read Ultimate Guide to the Best Photorealistic AI Images & Prompts<\/a> for better understanding with good resources.<\/p>\n\n\n\nDALL\u00b7E Mini has 14k+ Stars on GitHub, and it’s currently at the v0.1<\/code> release.<\/p>\n\n\n\nStar DALL\u00b7E Mini \u2b50\ufe0f<\/a><\/p>\n\n\n\n
\n\n\n\n<\/a>6. Deepgram<\/a> – Build Voice AI into your apps.<\/h2>\n\n\n\n![\"deepgram\"\/](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F32enxrtcwqk6g81eazay.png\")
<\/a><\/figure>\n\n\n\nFrom startups to NASA, Deepgram APIs are used to transcribe and understand millions of audio minutes every day. Fast, accurate, scalable, and cost-effective.<\/p>\n\n\n\n
It provides speech-to-text and audio intelligence models for developers.<\/p>\n\n\n\n![\"deepgram](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Frdc3tqg7fvt3sw6ktle7.png\")
<\/a><\/figure>\n\n\n\nEven though they have a freemium model, the limits on the free tier are sufficient to get you started.<\/p>\n\n\n\n
The visualization is next-level. You can check live streaming response, or audio files and compare the intelligence levels of audio.<\/p>\n\n\n\n![\"streaming\"\/](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F4wcvzzrqzn94gxe594hf.png\")
<\/a><\/figure>\n\n\n\n![\"sentiment](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fuw6wkhzg7g6vgq7lphri.png\")
<\/a><\/figure>\n\n\n\nYou can read the docs<\/a>.<\/p>\n\n\n\nYou can also read a sample blog by Deepgram on How to Add Speech Recognition to Your React and Node.js Project<\/a>.<\/p>\n\n\n\nIf you want to try the APIs to see for yourself with flexibility in models, do check out their API Playground<\/a>.<\/p>\n\n\n\nStar Deepgram \u2b50\ufe0f<\/a><\/p>\n\n\n\n
\n\n\n\n<\/a>7. InvokeAI<\/a> – leading creative engine for Stable Diffusion models.<\/h2>\n\n\n\n![\"invoke](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fa1uira3ta4ufauefp0ff.png\")
<\/a><\/figure>\n\n\n\nAbout<\/p>\n\n\n\n
InvokeAI is an implementation of Stable Diffusion, the open source text-to-image and image-to-image generator.<\/p>\n\n\n\n
It runs on Windows, Mac, and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.<\/p>\n\n\n\n
The solution offers an industry-leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.<\/p>\n\n\n\n![\"invoke](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fg5802r0wtxlbkqdtclce.png\")
<\/a><\/figure>\n\n\n\nYou can read about installation and hardware requirements<\/a>, How to install different Models<\/a>, and most important Automatic Installation<\/a>.<\/p>\n\n\n\nThe exciting feature is the ability to generate an image using another image, as described in the docs<\/a>.<\/p>\n\n\n\nInvokeAI has almost 21k stars on GitHub,<\/p>\n\n\n\n
Star InvokeAI \u2b50\ufe0f<\/a><\/p>\n\n\n\n
\n\n\n\n<\/a>8. OpenAI<\/a> – Everything you will ever need.<\/h2>\n\n\n\n![\"openAI\"\/](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fk02duibi54zzzddck91z.png\")
<\/a><\/figure>\n\n\n\nGemini by Google and OpenAI are very popular, but we’re focusing on OpenAI for this list.<\/p>\n\n\n\n
If you want to know more, you can read Google AI Gemini API in web using React \ud83e\udd16<\/a> on Medium. It’s simple and to the point.<\/p>\n\n\n\nWith OpenAI, you can use DALL\u00b7E (create original, realistic images and art from a text description), Whisper (speech recognition model), and GPT-4. Tell us about Sora in the comments!<\/p>\n\n\n\n
You can start building with a simple API.<\/p>\n\n\n\n
completion = openai.ChatCompletion.create(\n model=\"gpt-3.5-turbo\",\n messages=[\n {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n {\"role\": \"user\", \"content\": \"What are some famous astronomical observatories?\"}\n ]\n)\n<\/code><\/pre>\n\n\n\nYou can read the docs<\/a>. It provides such an insane amount of options to build something very cool!<\/p>\n\n\n\n![\"docs](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fo9yi0tar96jxi4pkni81.png\")
<\/a><\/figure>\n\n\n\nEven Stripe uses GPT-4 to improve user experience.<\/p>\n\n\n\n
For instance, you can create Assistant applications<\/a> and see the API playground<\/a> to understand it better.<\/p>\n\n\n\n![\"gpt-3\"\/](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Ft89658h4drhy4a8zf3xs.png\")
<\/a><\/figure>\n\n\n\nIn case you want a guide, you can read Integrating ChatGPT With ReactJS<\/a> by Dzone.<\/p>\n\n\n\nBetween, OpenAI acquired Sora to get the monopoly. What do you think?<\/p>\n\n\n\n
Star OpenAI \u2b50\ufe0f<\/a><\/p>\n\n\n\n
\n\n\n\n<\/a>9. DeepFaceLab<\/a> – leading software for creating deepfakes.<\/h2>\n\n\n\n![\"deepfacelab\"\/](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fg32stb7uo201msv3jn8f.png\")
<\/a><\/figure>\n\n\n\nDeepFaceLab is the top open source tool for making deepfakes.<\/p>\n\n\n\n
Deepfakes are altered images and videos made with deep learning. They’re often used to swap faces in pictures or clips, sometimes as a joke, but also for harmful reasons.<\/p>\n\n\n\n
DeepFaceLab, built with Python is a strong deepfake tool. It can change faces in media and even erase wrinkles and signs of aging.<\/p>\n\n\n\n
These are some of the things that you can do with DeepFaceLab.<\/p>\n\n\n\n
\n- Replace the face.<\/li>\n<\/ul>\n\n\n\n
![\"replace](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F86jnuec9l6eaalwf9w51.png\")
<\/a><\/figure>\n\n\n\n\n- De-age the face – YouTube<\/a>.<\/li>\n<\/ul>\n\n\n\n
![\"Image](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Faxh2e6117felh4zhoh3p.png\")
<\/a><\/figure>\n\n\n\n\n- Replace the head.<\/li>\n<\/ul>\n\n\n\n
![\"replace](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fnyvbncox7k1u28nait50.png\")
<\/a><\/figure>\n\n\n\n\n- Manipulate the lips.<\/li>\n<\/ul>\n\n\n\n
You can use this basic tutorial on how to use DeepFaceLab<\/a> in an effective way to accomplish these things.<\/p>\n\n\n\nYou can see the videos on YouTube<\/a> that use this DeepLab algorithm.<\/p>\n\n\n\nUnfortunately, there is no “make everything ok” button in DeepFaceLab, but it’s worthwhile to learn its workflow for your specific needs.<\/p>\n\n\n\n
Despite being archived on November 9, 2023, with nearly 44k+ stars on GitHub, it remains a solid choice for your AI app due to its numerous tutorials and reliable algorithms.<\/p>\n\n\n\n
Star DeepFaceLab \u2b50\ufe0f<\/a><\/p>\n\n\n\n
\n\n\n\n<\/a>10. Detectron2<\/a> – a PyTorch-based modular object detection library.<\/h2>\n\n\n\n![\"detectron2\"\/](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fjxe7wuf8v8y7e039ziel.png\")
<\/a><\/figure>\n\n\n\nDetectron2 is Facebook AI Research’s next-generation library that provides state-of-the-art detection and segmentation algorithms. It is the successor of Detectron and maskrcnn-benchmark.
It supports several computer vision research projects and production applications on Facebook.<\/p>\n\n\n\n
Use this YouTube tutorial<\/a> to use Detectron2 with Machine Learning from the Developer Advocate at Facebook.<\/p>\n\n\n\nDetectron2 is designed to support a diverse array of state-of-the-art object detection and segmentation models, while also adapting to the continuously evolving field of cutting-edge research.<\/p>\n\n\n\n
You can read on How to Get Started<\/a>, and the Meta Blog<\/a> which covers the objectives of Detectron in deep.<\/p>\n\n\n\nThe old version of Detectron used Caffe, making it hard to use with later changes in code that combined Caffe2 and PyTorch. Responding to community feedback, Facebook AI released Detectron2 as an updated, easier-to-use version.<\/p>\n\n\n\n
Detectron2 comes with advanced algorithms for object detection like DensePose and panoptic feature pyramid networks.<\/p>\n\n\n\n
Plus, Detectron2 can do semantic segmentation and panoptic segmentation, which help detect and segment objects more accurately in images and videos.<\/p>\n\n\n\n
Detectron2 not only supports object detection using bounding boxes and instance segmentation masks but also can predict human poses, similar to Detectron.<\/p>\n\n\n\n
They have 28k+ Stars on GitHub repo and are used by 1.6k+ developers on GitHub.<\/p>\n\n\n\n
Star Detectron2 \u2b50\ufe0f<\/a><\/p>\n\n\n\n
\n\n\n\n<\/a>11. FastAI<\/a> – deep learning library.<\/h2>\n\n\n\n![\"fast](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F6qvxqd22q3qamqtvwe6p.png\")
<\/a><\/figure>\n\n\n\nFastai is a versatile deep-learning library designed to cater to both practitioners and researchers. It offers high-level components for practitioners to achieve top-notch results quickly in common deep-learning tasks.<\/p>\n\n\n\n
At the same time, it provides low-level components for researchers to experiment and develop new approaches.<\/p>\n\n\n\n
Detectron2 achieves a balance between ease of use and flexibility through its layered architecture.
This architecture breaks down complex deep-learning techniques into manageable abstractions, concisely using Python’s dynamic nature and PyTorch’s flexibility.<\/p>\n\n\n\n
It is built on top of a hierarchy of lower-level APIs which provide composable building blocks. This way, a user wanting to rewrite part of the high-level API or add particular behavior to suit their needs does not have to learn how to use the lowest level.<\/p>\n\n\n\n![\"architecture](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fkfooe2mxrh3xplcxeg75.png\")
<\/a><\/figure>\n\n\n\nGet started with the following command once you have installed pyTorch<\/a>.<\/p>\n\n\n\nconda install -c fastai fastai\n<\/code><\/pre>\n\n\n\nYou can read the docs<\/a>.<\/p>\n\n\n\nThey have different starting points as tutorials<\/a> for beginners, intermediate, and experts.<\/p>\n\n\n\nIf you’re looking to contribute to FastAI, you should read their code style guide<\/a>.<\/p>\n\n\n\nIf you’re more into videos, you can watch Lesson “0”: Practical Deep Learning for Coders (fastai)<\/a> on YouTube by Jeremy Howard.<\/p>\n\n\n\nThey have 25k+ Stars on GitHub and are already used by 16k+ developers on GitHub.<\/p>\n\n\n\n
Star FastAI \u2b50\ufe0f<\/a><\/p>\n\n\n\n
\n\n\n\n<\/a>12. Stable Diffusion<\/a> – A latent text-to-image diffusion model.<\/h2>\n\n\n\n![\"stable](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F63worvztgs1cmy2owtkf.png\")
<\/a><\/figure>\n\n\n\n\nWhat is stable diffusion?<\/p>\n<\/blockquote>\n\n\n\n
Stable diffusion refers to a technique used in generative models, particularly in the context of text-to-image synthesis, where the process of transferring information from text descriptions to images is done gradually and smoothly.<\/p>\n\n\n\n
In a latent text-to-image diffusion model, stable diffusion ensures that the information from the text descriptions is diffused or spread consistently throughout the latent space of the model. This diffusion process helps in generating high-quality and realistic images that align with the given textual input.<\/p>\n\n\n\n
Stable diffusion mechanisms ensure that the model doesn’t experience sudden jumps or instabilities during the generation process. I hope this clears things up!<\/p>\n\n\n\n
A simple way to download and sample Stable Diffusion is by using the diffusers library<\/a>.<\/p>\n\n\n\n# make sure you're logged in with `huggingface-cli login`\nfrom torch import autocast\nfrom diffusers import StableDiffusionPipeline\n\npipe = StableDiffusionPipeline.from_pretrained(\n \"CompVis\/stable-diffusion-v1-4\", \n use_auth_token=True\n).to(\"cuda\")\n\nprompt = \"a photo of an astronaut riding a horse on mars\"\nwith autocast(\"cuda\"):\n image = pipe(prompt)[\"sample\"][0] \n\nimage.save(\"astronaut_rides_horse.png\")\n<\/code><\/pre>\n\n\n\nYou can read the research paper<\/a> and more about Image Modification with Stable Diffusion<\/a>.<\/p>\n\n\n\nFor instance, this is the input.<\/p>\n\n\n\n![\"input\"\/](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fzpvxxhrrvthd8w1a0rrl.png\")
<\/a><\/figure>\n\n\n\nand this is the output after upscaling a bit.<\/p>\n\n\n\n![\"output\"\/](\"https:\/\/media.dev.to\/cdn-cgi\/image\/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto\/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fgzqvd06kse8ifhzry0la.png\")
<\/a><\/figure>\n\n\n\nStable Diffusion v1 is a specific model configuration that employs an 860M UNet and a CLIP ViT-L\/14 text encoder for the diffusion model, with a downsampling-factor 8 autoencoder. The model was pre-trained on 256×256 images and subsequently fine-tuned on 512×512 images.<\/p>\n\n\n\n
They have around 64k+ Stars on the GitHub repository.<\/p>\n\n\n\n
<\/a><\/figure>\n\n\n\nTaipy is an open source Python library for easy, end-to-end application development, featuring what-if analyses, smart pipeline execution, built-in scheduling, and deployment tools.<\/p>\n\n\n\n
I’m sure most of you don’t understand so Taipy is used for creating a GUI interface for Python-based applications and improving data flow management.<\/p>\n\n\n\n
So, you can plot a graph of the data set and use a GUI-like slider to give the option to play with the data with other useful features.<\/p>\n\n\n\n
While Streamlit is a popular tool, its performance can decline significantly when handling large datasets, making it impractical for production-level use.
Taipy, on the other hand, offers simplicity and ease of use without sacrificing performance. By trying Taipy, you’ll experience firsthand its user-friendly interface and efficient handling of data.<\/p>\n\n\n\n
Under the hood, Taipy utilizes various libraries to streamline development and enhance functionality.<\/p>\n\n\n\n Get started with the following command.<\/p>\n\n\n\n Let’s talk about the latest Taipy v3.1 release<\/a>.<\/p>\n\n\n\n The latest release makes it possible to visualize any HTML or Python objects within Taipy’s versatile part object. This also brings native support for Plotly python<\/a>, making it easier to plot charts.<\/p>\n\n\n\n They have also improved performance using distributed computing but the best part is Taipy and all its dependencies are now fully compatible with Python 3.12 so you can work with the most up-to-date tools and libraries while using Taipy for your projects.<\/p>\n\n\n\n You can read the docs<\/a>.<\/p>\n\n\n\n For instance, you can see the chat demo<\/a> which uses OpenAI’s GPT-4 API to generate responses to your messages. You can easily change the code to use any other API or model.<\/p>\n\n\n\n Another useful thing is that the Taipy team has provided a VSCode extension called Taipy Studio<\/a> to accelerate the building of Taipy applications.<\/p>\n\n\n\n You can also deploy your applications with the Taipy cloud.<\/p>\n\n\n\n If you want to read a blog to see codebase structure, you can read Create a Web Interface for your LLM in Python using Taipy<\/a> by HuggingFace.<\/p>\n\n\n\n It is generally tough to try out new technologies, but Taipy has provided 10+ demo tutorials<\/a> with code & proper docs for you to follow along.<\/p>\n\n\n\n For instance, some live demo examples:<\/p>\n\n\n\n Taipy has 7k+ Stars on GitHub and is on the Star Taipy \u2b50\ufe0f<\/a><\/p>\n\n\n\n To build an AI app, you need a backend, and Supabase serves as an excellent backend service provider to meet this need.<\/p>\n\n\n\n Get started with the following npm command (Next.js).<\/p>\n\n\n\n This is how you can use CRUD operations.<\/p>\n\n\n\n You can read the docs<\/a>.<\/p>\n\n\n\n You can build a crazy fast application with Auth, realtime, Edge functions, storage, and many more. Supabase covers it all!<\/p>\n\n\n\n Supabase also provides several starting kits like Nextjs with LangChain<\/a>, Stripe with Nextjs<\/a> or AI Chatbot<\/a>.<\/p>\n\n\n\n Supabase has 63k+ Stars on GitHub and plenty of contributors with 27k+ commits.<\/p>\n\n\n\n Star Supabase \u2b50\ufe0f<\/a><\/p>\n\n\n\n Chatwoot connects with popular customer communication channels like Email, Website live-chat, Facebook, Twitter, WhatsApp, Instagram, Line, etc. This helps you deliver a consistent customer experience across channels \u2013 from a single dashboard.<\/p>\n\n\n\n This could be important in various cases, such as when you’re building a community around your AI app.<\/p>\n\n\n\n You can read the docs<\/a> to discover a wide range of integration options so it’s easier to manage the whole ecosystem.<\/p>\n\n\n\n They have very detailed documentation along with snapshot examples in each integration such as WhatsApp channel with WhatsApp Cloud API<\/a>. You can deploy to Heroku with 1-click or self-host as per needs.<\/p>\n\n\n\n They have 18k+ Stars on GitHub and are on the Star Chatwoot \u2b50\ufe0f<\/a><\/p>\n\n\n\n You can integrate key AI features into React apps using two React components. They also provide built-in (fully-customizable) Copilot-native UX components like Get started with the following npm command.<\/p>\n\n\n\n This is how you can integrate a CopilotTextArea.<\/p>\n\n\n\n You can read the docs<\/a>.<\/p>\n\n\n\n The basic idea is to build AI Chatbots in minutes that can be useful for LLM-based full-stack applications.<\/p>\n\n\n\n Star CopilotKit \u2b50\ufe0f<\/a><\/p>\n\n\n\n OpenAI had the first impressive model for generating images with DALL\u00b7E.<\/p>\n\n\n\n Craiyon\/DALL\u00b7E mini is an attempt to reproduce those outcomes using an open source model.<\/p>\n\n\n\n If you’re wondering about the name, DALL-E mini was renamed Craiyon at the request of the parent company and utilizes similar techniques in a more easily accessible web app format.<\/p>\n\n\n\n You can use the model on Craiyon<\/a>.<\/p>\n\n\n\n Get started with the following command (for development).<\/p>\n\n\n\n You can read the docs<\/a>.<\/p>\n\n\n\n You can read the DALL-E Mini explained<\/a> to know more about dataset, architecture, and algorithms involved.<\/p>\n\n\n\n You can read Ultimate Guide to the Best Photorealistic AI Images & Prompts<\/a> for better understanding with good resources.<\/p>\n\n\n\n DALL\u00b7E Mini has 14k+ Stars on GitHub, and it’s currently at the Star DALL\u00b7E Mini \u2b50\ufe0f<\/a><\/p>\n\n\n\n From startups to NASA, Deepgram APIs are used to transcribe and understand millions of audio minutes every day. Fast, accurate, scalable, and cost-effective.<\/p>\n\n\n\n It provides speech-to-text and audio intelligence models for developers.<\/p>\n\n\n\n Even though they have a freemium model, the limits on the free tier are sufficient to get you started.<\/p>\n\n\n\n The visualization is next-level. You can check live streaming response, or audio files and compare the intelligence levels of audio.<\/p>\n\n\n\n You can read the docs<\/a>.<\/p>\n\n\n\n You can also read a sample blog by Deepgram on How to Add Speech Recognition to Your React and Node.js Project<\/a>.<\/p>\n\n\n\n If you want to try the APIs to see for yourself with flexibility in models, do check out their API Playground<\/a>.<\/p>\n\n\n\n Star Deepgram \u2b50\ufe0f<\/a><\/p>\n\n\n\n About<\/p>\n\n\n\n InvokeAI is an implementation of Stable Diffusion, the open source text-to-image and image-to-image generator.<\/p>\n\n\n\n It runs on Windows, Mac, and Linux machines, and runs on GPU cards with as little as 4 GB of RAM.<\/p>\n\n\n\n The solution offers an industry-leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.<\/p>\n\n\n\n You can read about installation and hardware requirements<\/a>, How to install different Models<\/a>, and most important Automatic Installation<\/a>.<\/p>\n\n\n\n The exciting feature is the ability to generate an image using another image, as described in the docs<\/a>.<\/p>\n\n\n\n InvokeAI has almost 21k stars on GitHub,<\/p>\n\n\n\n Star InvokeAI \u2b50\ufe0f<\/a><\/p>\n\n\n\n Gemini by Google and OpenAI are very popular, but we’re focusing on OpenAI for this list.<\/p>\n\n\n\n If you want to know more, you can read Google AI Gemini API in web using React \ud83e\udd16<\/a> on Medium. It’s simple and to the point.<\/p>\n\n\n\n With OpenAI, you can use DALL\u00b7E (create original, realistic images and art from a text description), Whisper (speech recognition model), and GPT-4. Tell us about Sora in the comments!<\/p>\n\n\n\n You can start building with a simple API.<\/p>\n\n\n\n You can read the docs<\/a>. It provides such an insane amount of options to build something very cool!<\/p>\n\n\n\n Even Stripe uses GPT-4 to improve user experience.<\/p>\n\n\n\n For instance, you can create Assistant applications<\/a> and see the API playground<\/a> to understand it better.<\/p>\n\n\n\n In case you want a guide, you can read Integrating ChatGPT With ReactJS<\/a> by Dzone.<\/p>\n\n\n\n Between, OpenAI acquired Sora to get the monopoly. What do you think?<\/p>\n\n\n\n Star OpenAI \u2b50\ufe0f<\/a><\/p>\n\n\n\n DeepFaceLab is the top open source tool for making deepfakes.<\/p>\n\n\n\n Deepfakes are altered images and videos made with deep learning. They’re often used to swap faces in pictures or clips, sometimes as a joke, but also for harmful reasons.<\/p>\n\n\n\n DeepFaceLab, built with Python is a strong deepfake tool. It can change faces in media and even erase wrinkles and signs of aging.<\/p>\n\n\n\n These are some of the things that you can do with DeepFaceLab.<\/p>\n\n\n\n You can use this basic tutorial on how to use DeepFaceLab<\/a> in an effective way to accomplish these things.<\/p>\n\n\n\n You can see the videos on YouTube<\/a> that use this DeepLab algorithm.<\/p>\n\n\n\n Unfortunately, there is no “make everything ok” button in DeepFaceLab, but it’s worthwhile to learn its workflow for your specific needs.<\/p>\n\n\n\n Despite being archived on November 9, 2023, with nearly 44k+ stars on GitHub, it remains a solid choice for your AI app due to its numerous tutorials and reliable algorithms.<\/p>\n\n\n\n Star DeepFaceLab \u2b50\ufe0f<\/a><\/p>\n\n\n\n Detectron2 is Facebook AI Research’s next-generation library that provides state-of-the-art detection and segmentation algorithms. It is the successor of Detectron and maskrcnn-benchmark. Use this YouTube tutorial<\/a> to use Detectron2 with Machine Learning from the Developer Advocate at Facebook.<\/p>\n\n\n\n Detectron2 is designed to support a diverse array of state-of-the-art object detection and segmentation models, while also adapting to the continuously evolving field of cutting-edge research.<\/p>\n\n\n\n You can read on How to Get Started<\/a>, and the Meta Blog<\/a> which covers the objectives of Detectron in deep.<\/p>\n\n\n\n The old version of Detectron used Caffe, making it hard to use with later changes in code that combined Caffe2 and PyTorch. Responding to community feedback, Facebook AI released Detectron2 as an updated, easier-to-use version.<\/p>\n\n\n\n Detectron2 comes with advanced algorithms for object detection like DensePose and panoptic feature pyramid networks.<\/p>\n\n\n\n Plus, Detectron2 can do semantic segmentation and panoptic segmentation, which help detect and segment objects more accurately in images and videos.<\/p>\n\n\n\n Detectron2 not only supports object detection using bounding boxes and instance segmentation masks but also can predict human poses, similar to Detectron.<\/p>\n\n\n\n They have 28k+ Stars on GitHub repo and are used by 1.6k+ developers on GitHub.<\/p>\n\n\n\n Star Detectron2 \u2b50\ufe0f<\/a><\/p>\n\n\n\n Fastai is a versatile deep-learning library designed to cater to both practitioners and researchers. It offers high-level components for practitioners to achieve top-notch results quickly in common deep-learning tasks.<\/p>\n\n\n\n At the same time, it provides low-level components for researchers to experiment and develop new approaches.<\/p>\n\n\n\n Detectron2 achieves a balance between ease of use and flexibility through its layered architecture. It is built on top of a hierarchy of lower-level APIs which provide composable building blocks. This way, a user wanting to rewrite part of the high-level API or add particular behavior to suit their needs does not have to learn how to use the lowest level.<\/p>\n\n\n\n Get started with the following command once you have installed pyTorch<\/a>.<\/p>\n\n\n\n You can read the docs<\/a>.<\/p>\n\n\n\n They have different starting points as tutorials<\/a> for beginners, intermediate, and experts.<\/p>\n\n\n\n If you’re looking to contribute to FastAI, you should read their code style guide<\/a>.<\/p>\n\n\n\n If you’re more into videos, you can watch Lesson “0”: Practical Deep Learning for Coders (fastai)<\/a> on YouTube by Jeremy Howard.<\/p>\n\n\n\n They have 25k+ Stars on GitHub and are already used by 16k+ developers on GitHub.<\/p>\n\n\n\n Star FastAI \u2b50\ufe0f<\/a><\/p>\n\n\n\n What is stable diffusion?<\/p>\n<\/blockquote>\n\n\n\n Stable diffusion refers to a technique used in generative models, particularly in the context of text-to-image synthesis, where the process of transferring information from text descriptions to images is done gradually and smoothly.<\/p>\n\n\n\n In a latent text-to-image diffusion model, stable diffusion ensures that the information from the text descriptions is diffused or spread consistently throughout the latent space of the model. This diffusion process helps in generating high-quality and realistic images that align with the given textual input.<\/p>\n\n\n\n Stable diffusion mechanisms ensure that the model doesn’t experience sudden jumps or instabilities during the generation process. I hope this clears things up!<\/p>\n\n\n\n A simple way to download and sample Stable Diffusion is by using the diffusers library<\/a>.<\/p>\n\n\n\n You can read the research paper<\/a> and more about Image Modification with Stable Diffusion<\/a>.<\/p>\n\n\n\n For instance, this is the input.<\/p>\n\n\n\n and this is the output after upscaling a bit.<\/p>\n\n\n\n Stable Diffusion v1 is a specific model configuration that employs an 860M UNet and a CLIP ViT-L\/14 text encoder for the diffusion model, with a downsampling-factor 8 autoencoder. The model was pre-trained on 256×256 images and subsequently fine-tuned on 512×512 images.<\/p>\n\n\n\n They have around 64k+ Stars on the GitHub repository.<\/p>\n\n\n\n<\/a><\/figure>\n\n\n\npip install taipy\n<\/code><\/pre>\n\n\n\n
This means libraries like Folium<\/a>, Bokeh<\/a>, Vega-Altair<\/a>, and Matplotlib<\/a> are now available for visualizations.<\/p>\n\n\n\n<\/a><\/figure>\n\n\n\n<\/a><\/figure>\n\n\n\n<\/a><\/figure>\n\n\n\n\n
v3<\/code> release so they are constantly improving.<\/p>\n\n\n\n<\/a><\/figure>\n\n\n\n
\n\n\n\n<\/a>2. Supabase<\/a> – open source Firebase alternative.<\/h2>\n\n\n\n
<\/a><\/figure>\n\n\n\nnpx create-next-app -e with-supabase\n<\/code><\/pre>\n\n\n\nimport { createClient } from '@supabase\/supabase-js'\n\n\/\/ Initialize \nconst supabaseUrl = 'https:\/\/chat-room.supabase.co'\nconst supabaseKey = 'public-anon-key'\nconst supabase = createClient(supabaseUrl, supabaseKey)\n\n\/\/ Create a new chat room\nconst newRoom = await supabase\n .from('rooms')\n .insert({ name: 'Supabase Fan Club', public: true })\n\n\/\/ Get public rooms and their messages\nconst publicRooms = await supabase\n .from('rooms')\n .select(`\n name,\n messages ( text )\n `)\n .eq('public', true)\n\n\/\/ Update multiple users\nconst updatedUsers = await supabase\n .from('users')\n .eq('account_type', 'paid')\n .update({ highlight_color: 'gold' })\n<\/code><\/pre>\n\n\n\n
\n\n\n\n<\/a>3. Chatwoot<\/a> – live chat, email support, omni-channel desk & own your data.<\/h2>\n\n\n\n
<\/a><\/figure>\n\n\n\n<\/a><\/figure>\n\n\n\nv3.6<\/code> release.<\/p>\n\n\n\n
\n\n\n\n<\/a>4. CopilotKit<\/a> – AI Copilots for your product in hours.<\/h2>\n\n\n\n
<\/a><\/figure>\n\n\n\n<CopilotKit \/><\/code>, <CopilotPopup \/><\/code>, <CopilotSidebar \/><\/code>, <CopilotTextarea \/><\/code>.<\/p>\n\n\n\nnpm i @copilotkit\/react-core @copilotkit\/react-ui @copilotkit\/react-textarea\n<\/code><\/pre>\n\n\n\nimport { CopilotTextarea } from \"@copilotkit\/react-textarea\";\nimport { useState } from \"react\";\n\nexport function SomeReactComponent() {\n const [text, setText] = useState(\"\");\n\n return (\n <>\n <CopilotTextarea\n className=\"px-4 py-4\"\n value={text}\n onValueChange={(value: string) => setText(value)}\n placeholder=\"What are your plans for your vacation?\"\n autosuggestionsConfig={{\n textareaPurpose: \"Travel notes from the user's previous vacations. Likely written in a colloquial style, but adjust as needed.\",\n chatApiConfigs: {\n suggestionsApiConfig: {\n forwardedParams: {\n max_tokens: 20,\n stop: [\".\", \"?\", \"!\"],\n },\n },\n },\n }}\n \/>\n <\/>\n );\n}\n<\/code><\/pre>\n\n\n\n
\n\n\n\n<\/a>5. DALL\u00b7E Mini<\/a> – Generate images from a text prompt.<\/h2>\n\n\n\n
<\/a><\/figure>\n\n\n\n<\/a><\/figure>\n\n\n\npip install dalle-mini\n<\/code><\/pre>\n\n\n\nv0.1<\/code> release.<\/p>\n\n\n\n
\n\n\n\n<\/a>6. Deepgram<\/a> – Build Voice AI into your apps.<\/h2>\n\n\n\n
<\/a><\/figure>\n\n\n\n<\/a><\/figure>\n\n\n\n<\/a><\/figure>\n\n\n\n<\/a><\/figure>\n\n\n\n
\n\n\n\n<\/a>7. InvokeAI<\/a> – leading creative engine for Stable Diffusion models.<\/h2>\n\n\n\n
<\/a><\/figure>\n\n\n\n<\/a><\/figure>\n\n\n\n
\n\n\n\n<\/a>8. OpenAI<\/a> – Everything you will ever need.<\/h2>\n\n\n\n
<\/a><\/figure>\n\n\n\ncompletion = openai.ChatCompletion.create(\n model=\"gpt-3.5-turbo\",\n messages=[\n {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n {\"role\": \"user\", \"content\": \"What are some famous astronomical observatories?\"}\n ]\n)\n<\/code><\/pre>\n\n\n\n<\/a><\/figure>\n\n\n\n<\/a><\/figure>\n\n\n\n
\n\n\n\n<\/a>9. DeepFaceLab<\/a> – leading software for creating deepfakes.<\/h2>\n\n\n\n
<\/a><\/figure>\n\n\n\n\n
<\/a><\/figure>\n\n\n\n\n
<\/a><\/figure>\n\n\n\n\n
<\/a><\/figure>\n\n\n\n\n
\n\n\n\n<\/a>10. Detectron2<\/a> – a PyTorch-based modular object detection library.<\/h2>\n\n\n\n
<\/a><\/figure>\n\n\n\n
It supports several computer vision research projects and production applications on Facebook.<\/p>\n\n\n\n
\n\n\n\n<\/a>11. FastAI<\/a> – deep learning library.<\/h2>\n\n\n\n
<\/a><\/figure>\n\n\n\n
This architecture breaks down complex deep-learning techniques into manageable abstractions, concisely using Python’s dynamic nature and PyTorch’s flexibility.<\/p>\n\n\n\n<\/a><\/figure>\n\n\n\nconda install -c fastai fastai\n<\/code><\/pre>\n\n\n\n
\n\n\n\n<\/a>12. Stable Diffusion<\/a> – A latent text-to-image diffusion model.<\/h2>\n\n\n\n
<\/a><\/figure>\n\n\n\n\n
# make sure you're logged in with `huggingface-cli login`\nfrom torch import autocast\nfrom diffusers import StableDiffusionPipeline\n\npipe = StableDiffusionPipeline.from_pretrained(\n \"CompVis\/stable-diffusion-v1-4\", \n use_auth_token=True\n).to(\"cuda\")\n\nprompt = \"a photo of an astronaut riding a horse on mars\"\nwith autocast(\"cuda\"):\n image = pipe(prompt)[\"sample\"][0] \n\nimage.save(\"astronaut_rides_horse.png\")\n<\/code><\/pre>\n\n\n\n<\/a><\/figure>\n\n\n\n<\/a><\/figure>\n\n\n\n