Show HN: AI prompt-to-storyboard videos w/ GPT, Coqui voices, StabilityAI images https://ift.tt/ybk4cOC

Show HN: AI prompt-to-storyboard videos w/ GPT, Coqui voices, StabilityAI images I had 2 weeks off from work and wanted a pet project before heading back. With GPT and Generative AI in the news, I decided to chain multiple Al products together to build something really cool. I set my end goal to be: prompt-to-storyboard (aka fun videos generated purely via generative AI). There exists some prompt-to-video products, but I wanted to tell stories with audio as well. The end product takes an initial prompt and produces a series of images and audio files, which I then combine (with subtitles) into the final video. To showcase videos, there is a basic upvote/downvote leaderboard. Text | OpenAI https://openai.com/ Text is generated in a few high-level steps that I ask GPT to work through. These are all based on the initial user prompt, as such (ideally) indirectly controlled by the user. - Create a concept for a movie scene based on the prompt, including the theme and setting - Define each character in the scene - Define how each character looks - Define how each character sounds - Define 'frames' of the storyboard All of this textual information is defined in a JSON object I describe to GPT. I then take GPT's output and build the storyboard with the tools below. Voices | Coqui https://coqui.ai/ From the GPT output, I needed three major pieces of information to build voices in a way that I found satisfying: - Description of the voice - Description of the performance - Text of the actual dialog spoken Coqui has a product called 'prompt-to-voice', where you can describe how a character will sound and a custom voice is made for that character - this is how GPT defines the characters to use in the storyboard. As such, every voice is unique per storyboard. GPT will decide that a certain character is an "older man with a raspy voice", and I'll ask Coqui for that type of voice. In addition to this, in order to describe the performance, GPT outputs a basic emotion to summarize the line of dialog (happy, sad, angry, etc) - this is also sent to Coqui per audio clip generated. Images | Stability AI https://stability.ai/ While I originally setup the storyboard generator to use DALL-E due to already integrating with OpenAl for GPI, I found the cost prohibitive. As such, the images generated for the storyboards are from Stability Al's Stable Diffusion (stable-diffusion-512-v2-1). I combine the description of the frame that GPT provides, in addition to the theme and setting that GPT output for the whole storyboard, to generate each frame. Since GPT controls the data sent to Stable Diffusion with the description of the frame as well as the theme and setting, if your prompt dictates a theme it should hopefully translate into a theme in your storyboard. Both the storyboard and the 'prompt enhanced' image generation in the 'Create Content' tab pre-feed a GPT request with a summary of Stability Al's prompt guide. It will try and pick keyword weights to improve the image, and much like the setting and theme, keywords should be influenced by the initial prompt provided to the product. Conclusion: Have fun and make my 2 weeks of work seem worth it! Voting on storyboards and creating storyboards both require a simple Google login to get access. https://meyer.id April 21, 2023 at 05:35AM

Show HN: Create new files in macOS Finder https://ift.tt/Mv0rfEh

Show HN: Create new files in macOS Finder Hi HN! One of the feature that is lacking in MacOS Finder is the ability to create a new file in any folder. This repo provides a quick action workflow that adds this functionality to Finder. https://ift.tt/sKzyuOU April 21, 2023 at 04:49AM

Show HN: Create your own full-featured VPN server https://ift.tt/6W1MNVI

Show HN: Create your own full-featured VPN server We think VPN providers encrypt our data and increase our security and it is true but there is a problem: we have to share our data with them instead of ISPs. AdminVPN is a side project that allows ordinary people to create their own VPN server. PS: This is my first post here, your feedback is really appreciated! https://adminvpn.co/ April 20, 2023 at 10:18PM

Show HN: LLM Playground, compare results side by side https://ift.tt/BjqHXmv

Show HN: LLM Playground, compare results side by side https://ift.tt/jbioHKQ April 21, 2023 at 01:48AM

Show HN: Komorebi – Windows 11 tiling window manager quickstart guide https://ift.tt/qv5WwQl

Show HN: Komorebi – Windows 11 tiling window manager quickstart guide https://www.youtube.com/watch?v=cBnLIwMtv8g April 21, 2023 at 01:23AM

Show HN: InsightFlow https://ift.tt/RYAOE8F

Show HN: InsightFlow Hey everyone, sharing InsightFlow, a (long) weekend project I made using GPT4. I am bit anxious sharing it since I barely knew how to code in Python before but I was simply amazed on how much GPT was able to help me write something that actually works (I hope). My goal was to create a library that empowers people to ask questions from their data, regardless of its source. InsightFlow does just that, it has some modules that allow s parsing information existing in (for now) video (its audio part), html, and in general text and provides a chat interface on top. I would love to expand this to image and eventually video parsing. I know there are some companies that aim for the same but I could not find an opensouce alternative for it. I tried making it modular so different modalities can be added later on. https://ift.tt/7l1ypnv April 20, 2023 at 06:22PM

Show HN: Create Comics Using Stable Diffusion https://ift.tt/56P7FtJ

Show HN: Create Comics Using Stable Diffusion https://ift.tt/d3TLt1Q April 20, 2023 at 12:11PM

Show HN: Question Extractor: turn text into LLM finetuning data https://ift.tt/IBL6SUm

Show HN: Question Extractor: turn text into LLM finetuning data https://ift.tt/fQoFN8T April 20, 2023 at 06:17AM

Show HN: ChatGPT to control your own app (text-to-action library) https://ift.tt/faH6Ych

Show HN: ChatGPT to control your own app (text-to-action library) ActionIt is a text-to-action library built to make it easier to perform actions based on natural language input. It opens the way for applications that don't only retrieve information but actually interact with functions, extracting necessary parameters or asking follow-up questions where necessary. In simple terms, your functions are presented to ChatGPT and the correct one is chosen and executed based on a natural language input. Would love any feedback or feature requests:) https://ift.tt/QE42VXq April 20, 2023 at 03:34AM

Show HN: AI Assisted Coding Tutorials https://ift.tt/eFPL6jk

Show HN: AI Assisted Coding Tutorials https://ift.tt/waKAnjV April 20, 2023 at 12:40AM

Show HN: GoGoBrowse – A Peer to Peer Web Browser https://ift.tt/VkJoC0M

Show HN: GoGoBrowse – A Peer to Peer Web Browser Hi HN! GoGoBrowse is a side project I've been working on that allows 2 users to browse the web together while voice chatting. It's a proof of concept for a new model of browsing the web I've been thinking about. My thought is that before a leap to a 3D Metaverse, we need a 2D Metaverse, which is simply social web browsing. I wrote more about it here: https://ift.tt/rhCfJZP... Though the goal of an entirely social web browser is still quite a ways off, I think of this as a small first step in that direction. I'd love any feedback on the app itself, and the general concept of social web browsing. https://gogobrowse.com April 19, 2023 at 11:50PM

Show HN: A web decision game 99% coded by GPT4. Uses agent to decide win/loss https://ift.tt/w8cgXIE

Show HN: A web decision game 99% coded by GPT4. Uses agent to decide win/loss Yeah... so I know some software development concepts well I haven't written any code in 10 years, so like half the time was just getting a development setup. At first it suggested PyCharm and honestly it wasted a lot of time. Eventually I got VS Code and GPT just seems to understand it so much better. The real secret to getting good responses with GPT-4 during this I found is to restart the conversation fresh with a complete description of what you need (2-3 paragraphs of detail is great) and the rest as code. [detailed description of what you need, make sure it's detailed and specific add examples if possible] #### [insert all the code, the more you can fit the better] That first code block it gives you back on the first output is the cleanest by far. If there is an error and you submit it back in the same chat conversation, it just gets diluted/saturated over time, hallucinations go up etc. So if there is a bug rather than continue in the same convo, repeat this process in a brand new conversation. Each time it gives a much cleaner, fresher look at the code and goals needed. If your codeblock is really small then this isn't so important, but I'm trying to maximize the amount of code per prompt for best responses. I also make sure to split files by concerns so they don't get too big for the prompt window otherwise it's annoying. #### And lastly the other interesting thing about this project is this simulates an Agent loop where it is constantly trying to determine if the player won or lost, decide what the next most cohesive step is based on the human feedback (click emoji) and looping it. Actually that was my main interest for the project and I just wanted to get something published as a secondary goal. Most of my time was probably spent playing with the prompt and trying to to see if I could get it to determine if the goal was achieved but its actually a hard problem and I have some cool ideas for the next project. https://ift.tt/4d6ShFC April 19, 2023 at 11:41AM

Show HN: Karma Design Suite – A powerful wireframe and UI toolkit for designers https://ift.tt/fXzwGE2

Show HN: Karma Design Suite – A powerful wireframe and UI toolkit for designers We've designed an extensive wireframe kit and a more extensive set of UI kits. All feedback is appreciated. https://karma.design/ April 19, 2023 at 04:31PM

Show HN: No-cloud P2P file transfer in the browser using latest WebTorrent v2 https://ift.tt/JnruK9k

Show HN: No-cloud P2P file transfer in the browser using latest WebTorrent v2 https://file.love/ April 18, 2023 at 10:27PM

Show HN: Database for analyzing US companies, visualize using Apache SuperSet https://ift.tt/AgB26qa

Show HN: Database for analyzing US companies, visualize using Apache SuperSet My main motivation was that I wanted to be able to drill down and filter across all the available stocks, look at the data for myself, and narrow down on the stocks I am interested based on my own sets of criteria, and make data-driven analysis for my personal investment strategies. I used PostgreSQL as the backend database for ELT data pipelines, and used Citus Data cstore_fdw for columnar compression for the final dataset. All financial data is coming from SEC Edgar, https://ift.tt/HzquX17 . I used Python for downloading most of the data. I also run the data load development locally on my home Ubuntu server that I built 5 years ago. I bought 4TB of M2 disks for best database performance, with PRIME B360M-A motherboard and Intel Chip Coffee Lake S. I built the website simply using WordPress, and I run Apache Superset using gunicorn via Apache Webserver reverse proxy. The registration form I had to build myself with PHP and some JavaScript, because it needed to automatically create a SuperSet user upon registration. Otherwise, I would need to input everyone manually. I used Python again for the data integration. Please don't use the database directly as an investment tool, as its in Beta, and the data still needs to undergo heavy data quality checks, please confirm all the numbers yourself, as I provide a link for every company to the SEC filings. https://ift.tt/JmlbAQ4 April 19, 2023 at 02:46AM

Show HN: AI Playground by Vercel Labs https://ift.tt/T5gAenr

Show HN: AI Playground by Vercel Labs Hey, Jared Palmer (creator of this playground) here. Really excited to ship this. I’ve been building this over the past few weeks to compare LLMs from different providers like OpenAI, Anthropic, Cohere, etc. At Vercel, I manage our Frameworks division (including Next.js, Svelte, and Turbo) and wanted to also dogfood some of the latest features in a slightly larger application. This playground takes a lot of inspiration from https://nat.dev and is built on Tailwind, ui.shadcn.com, and some upcoming Vercel products we’re announcing soon. We’re going to continue adding models to compare and add other frameworks to generate code snippets from. https://play.vercel.ai April 19, 2023 at 04:08AM

Show HN: Offsuit – Casual Poker, Redesigned https://ift.tt/K2VDea8

Show HN: Offsuit – Casual Poker, Redesigned For the past year my friend and I have been building a dead simple offline poker app that we actually wanted to spend time in. No constant pop-ups. No account needed. No waiting for tables. No fake felt or neon. Just free poker against intelligent AI opponents with helpful in-game stats. We’ve started offline, but are working towards online-multiplayer, tutorials for new players, and more in-game stats. Would love your feedback! https://offsuit.app/ April 18, 2023 at 07:37PM

Show HN: Cfddns – A No Nonsense Script to Dynamically Update Cloudflare IP https://ift.tt/echm2ol

Show HN: Cfddns – A No Nonsense Script to Dynamically Update Cloudflare IP I couldn't find a decent tool to dynamically update IP address in my Cloudflare account, so I created one for me. Thought share with others. It can be run directly, as a scheduled task, and as a docker container. Only API token and target domain is required. https://ift.tt/j1pleR7 April 18, 2023 at 04:30PM

Show HN: Cyte – A visual, searchable knowledge base of your screen time https://ift.tt/2vb17Rd

Show HN: Cyte – A visual, searchable knowledge base of your screen time https://ift.tt/mkO3Lju April 18, 2023 at 07:19AM

Show HN: ThinkGPT: a library to prompt GPT to think, memorize and self-refine https://ift.tt/6KkFT8m

Show HN: ThinkGPT: a library to prompt GPT to think, memorize and self-refine https://ift.tt/0ce5k9s April 18, 2023 at 04:36AM