The best Hacker News stories from Show from the past day
Latest posts:
Show HN: Dump entire Git repos into a single file for LLM prompts
Hey! I wanted to share a tool I've been working on. It's still very early and a work in progress, but I've found it incredibly helpful when working with Claude and OpenAI's models.<p>What it does:
I created a Python script that dumps your entire Git repository into a single file. This makes it much easier to use with Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems.<p>Key Features:
- Respects .gitignore patterns
- Generates a tree-like directory structure
- Includes file contents for all non-excluded files
- Customizable file type filtering<p>Why I find it useful for LLM/RAG:
- Full Context: It gives LLMs a complete picture of my project structure and implementation details.
- RAG-Ready: The dumped content serves as a great knowledge base for retrieval-augmented generation.
- Better Code Suggestions: LLMs seem to understand my project better and provide more accurate suggestions.
- Debugging Aid: When I ask for help with bugs, I can provide the full context easily.<p>How to use it:
Example: python dump.py /path/to/your/repo output.txt .gitignore py js tsx<p>Again, it's still a work in progress, but I've found it really helpful in my workflow with AI coding assistants (Claude/Openai). I'd love to hear your thoughts, suggestions, or if anyone else finds this useful!<p><a href="https://github.com/artkulak/repo2file">https://github.com/artkulak/repo2file</a><p>P.S. If anyone wants to contribute or has ideas for improvement, I'm all ears!
Show HN: Shelly – A pure and vanilla shell-like interface for the web
shelly is a shell-like inteface for the web made with pure and vanilla HTML, CSS and JavaScript.
It's completely configurable and should run decently on any browser.
Show HN: Retronews – TUI for HN and Lobsters emulating classical Usenet readers
Show HN: Retronews – TUI for HN and Lobsters emulating classical Usenet readers
Show HN: Retronews – TUI for HN and Lobsters emulating classical Usenet readers
Show HN: Pulsar, micro creative coding playground
Show HN: Using SQL's Turing completeness to build Tetris
Show HN: Using SQL's Turing completeness to build Tetris
Show HN: Using SQL's Turing completeness to build Tetris
Show HN: Using SQL's Turing completeness to build Tetris
Show HN: Infinity – Realistic AI characters that can speak
Hey HN, this is Lina, Andrew, and Sidney from Infinity AI (<a href="https://infinity.ai/">https://infinity.ai/</a>). We've trained our own foundation video model focused on people. As far as we know, this is the first time someone has trained a video diffusion transformer that’s driven by audio input. This is cool because it allows for expressive, realistic-looking characters that actually speak. Here’s a blog with a bunch of examples: <a href="https://toinfinityai.github.io/v2-launch-page/" rel="nofollow">https://toinfinityai.github.io/v2-launch-page/</a><p>If you want to try it out, you can either (1) go to <a href="https://studio.infinity.ai/try-inf2">https://studio.infinity.ai/try-inf2</a>, or (2) post a comment in this thread describing a character and we’ll generate a video for you and reply with a link. For example:
“Mona Lisa saying ‘what the heck are you smiling at?’”: <a href="https://bit.ly/3z8l1TM" rel="nofollow">https://bit.ly/3z8l1TM</a>
“A 3D pixar-style gnome with a pointy red hat reciting the Declaration of Independence”: <a href="https://bit.ly/3XzpTdS" rel="nofollow">https://bit.ly/3XzpTdS</a>
“Elon Musk singing Fly Me To The Moon by Sinatra”: <a href="https://bit.ly/47jyC7C" rel="nofollow">https://bit.ly/47jyC7C</a><p>Our tool at Infinity allows creators to type out a script with what they want their characters to say (and eventually, what they want their characters to do) and get a video out. We’ve trained for about 11 GPU years (~$500k) so far and our model recently started getting good results, so we wanted to share it here. We are still actively training.<p>We had trouble creating videos of good characters with existing AI tools. Generative AI video models (like Runway and Luma) don’t allow characters to speak. And talking avatar companies (like HeyGen and Synthesia) just do lip syncing on top of the previously recorded videos. This means you often get facial expressions and gestures that don’t make sense with the audio, resulting in the “uncanny” look you can’t quite put your finger on. See blog.<p>When we started Infinity, our V1 model took the lip syncing approach. In addition to mismatched gestures, this method had many limitations, including a finite library of actors (we had to fine-tune a model for each one with existing video footage) and an inability to animate imaginary characters.<p>To address these limitations in V2, we decided to train an end-to-end video diffusion transformer model that takes in a single image, audio, and other conditioning signals and outputs video. We believe this end-to-end approach is the best way to capture the full complexity and nuances of human motion and emotion. One drawback of our approach is that the model is slow despite using rectified flow (2-4x speed up) and a 3D VAE embedding layer (2-5x speed up).<p>Here are a few things the model does surprisingly well on: (1) it can handle multiple languages, (2) it has learned some physics (e.g. it generates earrings that dangle properly and infers a matching pair on the other ear), (3) it can animate diverse types of images (paintings, sculptures, etc) despite not being trained on those, and (4) it can handle singing. See blog.<p>Here are some failure modes of the model: (1) it cannot handle animals (only humanoid images), (2) it often inserts hands into the frame (very annoying and distracting), (3) it’s not robust on cartoons, and (4) it can distort people’s identities (noticeable on well-known figures). See blog.<p>Try the model here: <a href="https://studio.infinity.ai/try-inf2">https://studio.infinity.ai/try-inf2</a><p>We’d love to hear what you think!
Show HN: Infinity – Realistic AI characters that can speak
Hey HN, this is Lina, Andrew, and Sidney from Infinity AI (<a href="https://infinity.ai/">https://infinity.ai/</a>). We've trained our own foundation video model focused on people. As far as we know, this is the first time someone has trained a video diffusion transformer that’s driven by audio input. This is cool because it allows for expressive, realistic-looking characters that actually speak. Here’s a blog with a bunch of examples: <a href="https://toinfinityai.github.io/v2-launch-page/" rel="nofollow">https://toinfinityai.github.io/v2-launch-page/</a><p>If you want to try it out, you can either (1) go to <a href="https://studio.infinity.ai/try-inf2">https://studio.infinity.ai/try-inf2</a>, or (2) post a comment in this thread describing a character and we’ll generate a video for you and reply with a link. For example:
“Mona Lisa saying ‘what the heck are you smiling at?’”: <a href="https://bit.ly/3z8l1TM" rel="nofollow">https://bit.ly/3z8l1TM</a>
“A 3D pixar-style gnome with a pointy red hat reciting the Declaration of Independence”: <a href="https://bit.ly/3XzpTdS" rel="nofollow">https://bit.ly/3XzpTdS</a>
“Elon Musk singing Fly Me To The Moon by Sinatra”: <a href="https://bit.ly/47jyC7C" rel="nofollow">https://bit.ly/47jyC7C</a><p>Our tool at Infinity allows creators to type out a script with what they want their characters to say (and eventually, what they want their characters to do) and get a video out. We’ve trained for about 11 GPU years (~$500k) so far and our model recently started getting good results, so we wanted to share it here. We are still actively training.<p>We had trouble creating videos of good characters with existing AI tools. Generative AI video models (like Runway and Luma) don’t allow characters to speak. And talking avatar companies (like HeyGen and Synthesia) just do lip syncing on top of the previously recorded videos. This means you often get facial expressions and gestures that don’t make sense with the audio, resulting in the “uncanny” look you can’t quite put your finger on. See blog.<p>When we started Infinity, our V1 model took the lip syncing approach. In addition to mismatched gestures, this method had many limitations, including a finite library of actors (we had to fine-tune a model for each one with existing video footage) and an inability to animate imaginary characters.<p>To address these limitations in V2, we decided to train an end-to-end video diffusion transformer model that takes in a single image, audio, and other conditioning signals and outputs video. We believe this end-to-end approach is the best way to capture the full complexity and nuances of human motion and emotion. One drawback of our approach is that the model is slow despite using rectified flow (2-4x speed up) and a 3D VAE embedding layer (2-5x speed up).<p>Here are a few things the model does surprisingly well on: (1) it can handle multiple languages, (2) it has learned some physics (e.g. it generates earrings that dangle properly and infers a matching pair on the other ear), (3) it can animate diverse types of images (paintings, sculptures, etc) despite not being trained on those, and (4) it can handle singing. See blog.<p>Here are some failure modes of the model: (1) it cannot handle animals (only humanoid images), (2) it often inserts hands into the frame (very annoying and distracting), (3) it’s not robust on cartoons, and (4) it can distort people’s identities (noticeable on well-known figures). See blog.<p>Try the model here: <a href="https://studio.infinity.ai/try-inf2">https://studio.infinity.ai/try-inf2</a><p>We’d love to hear what you think!
Show HN: Infinity – Realistic AI characters that can speak
Hey HN, this is Lina, Andrew, and Sidney from Infinity AI (<a href="https://infinity.ai/">https://infinity.ai/</a>). We've trained our own foundation video model focused on people. As far as we know, this is the first time someone has trained a video diffusion transformer that’s driven by audio input. This is cool because it allows for expressive, realistic-looking characters that actually speak. Here’s a blog with a bunch of examples: <a href="https://toinfinityai.github.io/v2-launch-page/" rel="nofollow">https://toinfinityai.github.io/v2-launch-page/</a><p>If you want to try it out, you can either (1) go to <a href="https://studio.infinity.ai/try-inf2">https://studio.infinity.ai/try-inf2</a>, or (2) post a comment in this thread describing a character and we’ll generate a video for you and reply with a link. For example:
“Mona Lisa saying ‘what the heck are you smiling at?’”: <a href="https://bit.ly/3z8l1TM" rel="nofollow">https://bit.ly/3z8l1TM</a>
“A 3D pixar-style gnome with a pointy red hat reciting the Declaration of Independence”: <a href="https://bit.ly/3XzpTdS" rel="nofollow">https://bit.ly/3XzpTdS</a>
“Elon Musk singing Fly Me To The Moon by Sinatra”: <a href="https://bit.ly/47jyC7C" rel="nofollow">https://bit.ly/47jyC7C</a><p>Our tool at Infinity allows creators to type out a script with what they want their characters to say (and eventually, what they want their characters to do) and get a video out. We’ve trained for about 11 GPU years (~$500k) so far and our model recently started getting good results, so we wanted to share it here. We are still actively training.<p>We had trouble creating videos of good characters with existing AI tools. Generative AI video models (like Runway and Luma) don’t allow characters to speak. And talking avatar companies (like HeyGen and Synthesia) just do lip syncing on top of the previously recorded videos. This means you often get facial expressions and gestures that don’t make sense with the audio, resulting in the “uncanny” look you can’t quite put your finger on. See blog.<p>When we started Infinity, our V1 model took the lip syncing approach. In addition to mismatched gestures, this method had many limitations, including a finite library of actors (we had to fine-tune a model for each one with existing video footage) and an inability to animate imaginary characters.<p>To address these limitations in V2, we decided to train an end-to-end video diffusion transformer model that takes in a single image, audio, and other conditioning signals and outputs video. We believe this end-to-end approach is the best way to capture the full complexity and nuances of human motion and emotion. One drawback of our approach is that the model is slow despite using rectified flow (2-4x speed up) and a 3D VAE embedding layer (2-5x speed up).<p>Here are a few things the model does surprisingly well on: (1) it can handle multiple languages, (2) it has learned some physics (e.g. it generates earrings that dangle properly and infers a matching pair on the other ear), (3) it can animate diverse types of images (paintings, sculptures, etc) despite not being trained on those, and (4) it can handle singing. See blog.<p>Here are some failure modes of the model: (1) it cannot handle animals (only humanoid images), (2) it often inserts hands into the frame (very annoying and distracting), (3) it’s not robust on cartoons, and (4) it can distort people’s identities (noticeable on well-known figures). See blog.<p>Try the model here: <a href="https://studio.infinity.ai/try-inf2">https://studio.infinity.ai/try-inf2</a><p>We’d love to hear what you think!
Show HN: Infinity – Realistic AI characters that can speak
Hey HN, this is Lina, Andrew, and Sidney from Infinity AI (<a href="https://infinity.ai/">https://infinity.ai/</a>). We've trained our own foundation video model focused on people. As far as we know, this is the first time someone has trained a video diffusion transformer that’s driven by audio input. This is cool because it allows for expressive, realistic-looking characters that actually speak. Here’s a blog with a bunch of examples: <a href="https://toinfinityai.github.io/v2-launch-page/" rel="nofollow">https://toinfinityai.github.io/v2-launch-page/</a><p>If you want to try it out, you can either (1) go to <a href="https://studio.infinity.ai/try-inf2">https://studio.infinity.ai/try-inf2</a>, or (2) post a comment in this thread describing a character and we’ll generate a video for you and reply with a link. For example:
“Mona Lisa saying ‘what the heck are you smiling at?’”: <a href="https://bit.ly/3z8l1TM" rel="nofollow">https://bit.ly/3z8l1TM</a>
“A 3D pixar-style gnome with a pointy red hat reciting the Declaration of Independence”: <a href="https://bit.ly/3XzpTdS" rel="nofollow">https://bit.ly/3XzpTdS</a>
“Elon Musk singing Fly Me To The Moon by Sinatra”: <a href="https://bit.ly/47jyC7C" rel="nofollow">https://bit.ly/47jyC7C</a><p>Our tool at Infinity allows creators to type out a script with what they want their characters to say (and eventually, what they want their characters to do) and get a video out. We’ve trained for about 11 GPU years (~$500k) so far and our model recently started getting good results, so we wanted to share it here. We are still actively training.<p>We had trouble creating videos of good characters with existing AI tools. Generative AI video models (like Runway and Luma) don’t allow characters to speak. And talking avatar companies (like HeyGen and Synthesia) just do lip syncing on top of the previously recorded videos. This means you often get facial expressions and gestures that don’t make sense with the audio, resulting in the “uncanny” look you can’t quite put your finger on. See blog.<p>When we started Infinity, our V1 model took the lip syncing approach. In addition to mismatched gestures, this method had many limitations, including a finite library of actors (we had to fine-tune a model for each one with existing video footage) and an inability to animate imaginary characters.<p>To address these limitations in V2, we decided to train an end-to-end video diffusion transformer model that takes in a single image, audio, and other conditioning signals and outputs video. We believe this end-to-end approach is the best way to capture the full complexity and nuances of human motion and emotion. One drawback of our approach is that the model is slow despite using rectified flow (2-4x speed up) and a 3D VAE embedding layer (2-5x speed up).<p>Here are a few things the model does surprisingly well on: (1) it can handle multiple languages, (2) it has learned some physics (e.g. it generates earrings that dangle properly and infers a matching pair on the other ear), (3) it can animate diverse types of images (paintings, sculptures, etc) despite not being trained on those, and (4) it can handle singing. See blog.<p>Here are some failure modes of the model: (1) it cannot handle animals (only humanoid images), (2) it often inserts hands into the frame (very annoying and distracting), (3) it’s not robust on cartoons, and (4) it can distort people’s identities (noticeable on well-known figures). See blog.<p>Try the model here: <a href="https://studio.infinity.ai/try-inf2">https://studio.infinity.ai/try-inf2</a><p>We’d love to hear what you think!
Show HN: Wealthfolio: Private, open-source investment tracker
Thank you for your comments, just some context:<p>- The app is a simple desktop application that works on macOS, Windows, and Ubuntu.<p>- I developed this app for my own needs. Getting tired of SaaS app subscriptions and privacy concerns.<p>- For now, the activities are logged manually or imported from a CSV file. No integration with Plaid or other platforms.<p>- No monetization is planned for now (only a "buy me a coffee" if you use and appreciate the app).
Show HN: Wealthfolio: Private, open-source investment tracker
Thank you for your comments, just some context:<p>- The app is a simple desktop application that works on macOS, Windows, and Ubuntu.<p>- I developed this app for my own needs. Getting tired of SaaS app subscriptions and privacy concerns.<p>- For now, the activities are logged manually or imported from a CSV file. No integration with Plaid or other platforms.<p>- No monetization is planned for now (only a "buy me a coffee" if you use and appreciate the app).
Show HN: Wealthfolio: Private, open-source investment tracker
Thank you for your comments, just some context:<p>- The app is a simple desktop application that works on macOS, Windows, and Ubuntu.<p>- I developed this app for my own needs. Getting tired of SaaS app subscriptions and privacy concerns.<p>- For now, the activities are logged manually or imported from a CSV file. No integration with Plaid or other platforms.<p>- No monetization is planned for now (only a "buy me a coffee" if you use and appreciate the app).
Show HN: I made CMS less than 15 kilobytes, flat file
<a href="https://github.com/turboblack/HamsterCMS">https://github.com/turboblack/HamsterCMS</a><p><a href="http://web1.0hosting.net/" rel="nofollow">http://web1.0hosting.net/</a> - free hosting based on this CMS
Show HN: We built a FOSS documentation CMS with a pretty GUI
Kalmia started as a small hobby project about two months ago, but it quickly evolved when we needed a better solution to manage our office's documentation. It has now become our go-to tool for both internal and user-facing docs.<p>Recently, we decided to open source it, as we believe others might benefit from a lightweight, customizable documentation system like this. We're excited to see how the community can take it further, contribute, and adapt it to their own needs!
Show HN: We built a FOSS documentation CMS with a pretty GUI
Kalmia started as a small hobby project about two months ago, but it quickly evolved when we needed a better solution to manage our office's documentation. It has now become our go-to tool for both internal and user-facing docs.<p>Recently, we decided to open source it, as we believe others might benefit from a lightweight, customizable documentation system like this. We're excited to see how the community can take it further, contribute, and adapt it to their own needs!