Discussion summary
InstantVideos.org offers ~30 second documentaries, with recent discussions focusing on video rendering performance and platform features.
What the discussion says
- Users are experimenting with video rendering times and GPU acceleration.
- Some users report issues with image generation and rate limits.
- The platform is appreciated for its simplicity and accurate narration.
“The audio narration is great and the documentary is accurate.”
“I'm no expert here and was working w/ GLM-5.2, but rendering was CPU bound.”
Comments
Hacker News
by jazzyjackson
by pw
by mellosouls
by pw
Quotations from Chairman Mao Tse-tung (Short form)
The audio narration is great and the documentary is accurate. Improvements could include more pictures or animations.
This is a very great tool and framework! Thank you so much.
by kittikitti
by pw
by ms7892
by pw
by pw
by pw
by pw
by bitelchux
by pw
by urbnspacecowboy
by ramon156
by pw
by eckelhesten
by pw
---
File "/usr/lib/python3.10/concurrent/futures/thread.py", line 58, in run result = self.fn(self.args, *self.kwargs) File "/home/ubuntu/byclaude/video/harness/pipeline/pipeline.py", line 829, in build_clip clip = round(dur + TAIL, 3) TypeError: unsupported operand type(s) for +: 'NoneType' and 'float' Video build failed (pipeline exit 1) — please try again. Powered by AI · by Claude · ~
by albert_e
by pw
by f055
One small quirk I noticed with the generated short video: for each new slide/photo, there is a very gradual "zoom in" effect that occurs, which causes text to jitter a bit and is a bit disorienting. Not sure if that is specific to the "The Great Molasses Flood of 1919 in Boston" prompt I used or not.
Also, is Claude involved in the video generation itself? I noticed the generated video has "By Claude" in the top left corner, but the logs seem to indicate that only GLM-5.2, Gemini Flash, and GPT-4o are involved (just curious!)
by nickvec
by pw
For example, I have several posts that explain concepts in detail, with supporting images. They're written in Markdown, and I keep refining them until I'm confident that the average person can read them and immediately understand the concept.
The problem is that text is becoming a less popular medium for learning, while short form videos are increasingly being used to explain the same ideas.
From what I can tell, this tool only lets you provide a prompt. Can it turn my existing Markdown posts and images into videos, or is it mainly intended for generating videos from simple prompts? I'm looking for something that preserves the explanations I've already written rather than creating something entirely new.
by faangguyindia
by pw
Style 1: https://www.youtube.com/shorts/vGjrv2zjfsM
Style 2: https://www.youtube.com/shorts/6KoRHpAZ4zk
These are the two styles that consistently keep me watching. I can't really describe them well in words, so I linked the videos directly to avoid losing important details in the translation from visual format to text.
Maybe someone with more experience in video production can explain what techniques are being used here and why they're so effective at holding viewers' attention.
by faangguyindia
Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- Did you really rent a 64 vCPU EC2 without exploiting ffmpeg GPU acceleration?by jazzyjackson
- I'm no expert here and was working w/ GLM-5.2, but whatever rendering we were doing ended up being CPU bound.by pw
- I'm guessing its being hugged now - it says generate in under a minute but my short is taking ten minutes and counting; anyway I like the simplicity and am interested in seeing the results - though I do think it is quite depressing as we will see this sort of service mostly put to use for slop.by mellosouls
- Hi! Sorry yeah, I'm been bumping up against rate limits, but it should be working again now!by pw
- https://instantvideos.org/video/6be78e5ea542
Quotations from Chairman Mao Tse-tung (Short form)
The audio narration is great and the documentary is accurate. Improvements could include more pictures or animations.
This is a very great tool and framework! Thank you so much.
by kittikitti - No, thank you for trying it!by pw
- Image not generating?by ms7892
- Working on it!by pw
- Fixed!by pw
- Ugh looks like I'm hitting my Gemini Tier 1 usage limits. Sorry!by pw
- Fixed!by pw
- Could you publish the source code or how to do it for our sueltes?by bitelchux
- I'm around to answer questions or receive feedback if anyone as any!by pw
- Please, pretty please, link some pre-generated examples.by urbnspacecowboy
- Cool idea! Looks like my prompt is stuck, though. Might be an idea to provide a share link at the moment of hitting the button so you can check back later, because if I close the tab I will lose my promptby ramon156
- Yeah the disk on the instance filled up and it was down. Sorry. It's up again now.by pw
- It’s an interesting concept, perhaps it could go more from ”narrated slide show” to ”video clip” in the near future if it doesn’t cost too much.by eckelhesten
- Yeah I'd been thinking of Gemini Omni for that but it adds about 10 cents per second of video, so not cheap.by pw
- Currently getting errors
---
File "/usr/lib/python3.10/concurrent/futures/thread.py", line 58, in run result = self.fn(self.args, *self.kwargs) File "/home/ubuntu/byclaude/video/harness/pipeline/pipeline.py", line 829, in build_clip clip = round(dur + TAIL, 3) TypeError: unsupported operand type(s) for +: 'NoneType' and 'float' Video build failed (pipeline exit 1) — please try again. Powered by AI · by Claude · ~
by albert_e - Should be fixed nowby pw
- You could probably make your infra cheaper if you sent the generated slides to the web client and use some js ffmpeg wasm to compile the video in the browser. This way you could probably use the cheapest VPS to handle this.by f055
- Fun idea! Hope it doesn't cost you too much to keep up depending on how much traction this thread gets ;)
One small quirk I noticed with the generated short video: for each new slide/photo, there is a very gradual "zoom in" effect that occurs, which causes text to jitter a bit and is a bit disorienting. Not sure if that is specific to the "The Great Molasses Flood of 1919 in Boston" prompt I used or not.
Also, is Claude involved in the video generation itself? I noticed the generated video has "By Claude" in the top left corner, but the logs seem to indicate that only GLM-5.2, Gemini Flash, and GPT-4o are involved (just curious!)
by nickvec - Yeah, that's suppose to be a Ken Burns style zoom but I haven't figured out how to stop the shake the should probably just remove it. And I need to remove the "By Claude" too. That's a remnant from porting from my internal framework for the [By Claude)(https://www.youtube.com/@byclaude) Youtube, TikTok, etc channels.by pw
- How would I create a video like this?
For example, I have several posts that explain concepts in detail, with supporting images. They're written in Markdown, and I keep refining them until I'm confident that the average person can read them and immediately understand the concept.
The problem is that text is becoming a less popular medium for learning, while short form videos are increasingly being used to explain the same ideas.
From what I can tell, this tool only lets you provide a prompt. Can it turn my existing Markdown posts and images into videos, or is it mainly intended for generating videos from simple prompts? I'm looking for something that preserves the explanations I've already written rather than creating something entirely new.
by faangguyindia - So this is really just a kinda proof of concept, but I'd be pretty easy to turn it into what you want. It sounds like you've already got both basically a script and images to go with it?by pw
- it works, but can u add different style of videos like this one:
Style 1: https://www.youtube.com/shorts/vGjrv2zjfsM
Style 2: https://www.youtube.com/shorts/6KoRHpAZ4zk
These are the two styles that consistently keep me watching. I can't really describe them well in words, so I linked the videos directly to avoid losing important details in the translation from visual format to text.
Maybe someone with more experience in video production can explain what techniques are being used here and why they're so effective at holding viewers' attention.
by faangguyindia
Related stories
Decoding the obfuscated bash script on a Uniqlo t-shirt
tris.sherliker.net · 1072 points · 181 comments
StreetComplete: Fixing OpenStreetMap, one tiny quest at a time
streetcomplete.app · 761 points · 182 comments
Every new car sold in the European Union must include a driver monitoring camera
allaboutcookies.org · 737 points · 969 comments
Chat Control 1.0 and 2.0 Explained
fightchatcontrol.eu · 645 points · 238 comments
Microsoft fire idTech team at Id software
gamefromscratch.com · 597 points · 533 comments
Chat Control passed first round in EU Parliament
heise.de · 567 points · 246 comments