neuralframes.com

AI

generative video

SHOW HN2023

247points
72comments
#199of 3,109 in 2023
Top 7%of 2023 by points

How HN took it

MixedNo clear lean

6 positive, 13 neutral or asking, 2 mixed, 12 critical, out of 33 comments about the project. Thread score -0.21.

Design: 0 for, 6 againstPerformance: 2 for, 2 againstExecution: 1 for, 1 againstIdea: 0 for, 1 againstDocs: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Impressive concept and output; looks great.

    From 3 comments
    • Couple suggestions after playing with this: 1) the experience mostly works on mobile (where I first tried it). With only minimal changes in the fixed sizing I think you could…
      jsjohnst on HN
    • Very cool, your demo video looks great, would love to try it when it's working again. You can also do this type of thing on colab with Deforum Stable Diffusion:…
      tekni5 on HN
    • I put it on for hundreds of hours to try out a 24 fps video myself: https://www.youtube.com/watch?v=f3GfUKJBUYA
      jimhi on HN

Objections

  • Site overloaded and hard to use during launch traffic.

    From 3 comments
    • Seems to be overloaded. "There's a lot of requests currently and our servers are overloaded - sorry. I am trying to increase the capacity. Please try again later."
      tekni5 on HN
    • Might want to put notice: “There's a lot of requests currently and our servers are overloaded - sorry. I am trying to increase the capacity. Please try again later.” …prior to…
      O__________O on HN
    • Then, if I finally try to render a 5 second click I get: “There's high demand on the servers currently. Sorry for any inconvenience. I am trying to scale up the servers.” RIP
      O__________O on HN
  • Landing page lacks a visible demo video.

    From 3 comments
    • The site should have a demo video of what an output looks like instead of a static image. I stopped at the signup form.
      theogravity on HN
    • Is there an example video somewhere? Edit: Nevermind - I don't have autoplay active and there was no way to see that the "image" on the landing page is actually a video (no UI…
      kruuuder on HN
    • I’m just getting a static image on iPhone as well. Is there a youtube channel?
      ada1981 on HN
  • Stable Diffusion faces copyright lawsuits, so using it is risky.

    From 1 comment
    • The company that makes stablediffusion is being sued for copyright infringement. Don't use this.
      NicoleJO on HN
  • Hosted service is more expensive than running Deforum yourself.

    From 1 comment
    • I suggest that people simply run Stable Diffusion Deforum themselves (there's an extension for automatic1111's web UI). You can run it in a google colab notebook and the cost…
      lukeplato on HN

Requests

  • Mobile-friendly layout.

    From 1 comment
    • Couple suggestions after playing with this: 1) the experience mostly works on mobile (where I first tried it). With only minimal changes in the fixed sizing I think you could…
      jsjohnst on HN
  • Support for Dreambooth or LoRA fine-tuning.

    From 2 comments
    • do you plan on adding dreambooth? I would give it a try.
      conidig on HN
    • Try the Lora fine-tuning method with few MB results: https://github.com/cloneofsimo/lora
      spyder on HN
  • Run it locally or open source the code.

    From 1 comment
    • I’d much prefer to run this locally on my own. Any chance you’re willing to share code (or suggestions / links since it looks like you might be trying to monetize this per your…
      jsjohnst on HN

Questions

  • What denoising strength and guidance scale values were used?

    From 1 comment
    • This is very cool! What sort of values are you using for the denoising strength/guidance scale? Each frame is a nice level of similar/different to the last to create flowing video.
      francis_lewis on HN
  • What prompts were used for the video?

    From 1 comment

Alternatives named

  • Deforum Stable Diffusion in Colab or automatic1111 extension.

    From 2 comments
    • I suggest that people simply run Stable Diffusion Deforum themselves (there's an extension for automatic1111's web UI). You can run it in a google colab notebook and the cost…
      lukeplato on HN
    • Very cool, your demo video looks great, would love to try it when it's working again. You can also do this type of thing on colab with Deforum Stable Diffusion:…
      tekni5 on HN
  • computerender API.

    From 1 comment
    • Very cool! I just released a tutorial on how to do this using the computerender api! https://github.com/computerender/tutorials/tree/main/python/vid2vid If you’re interested in…
      tehsauce on HN
  • banana.dev and pipeline.ai for GPU hosting.

    From 1 comment
    • I don’t usually comment, but aws is actually rather expensive and i’ve hit this annoying quota problem as well. Been back and forth and still hasn’t been raised. I can also…
      atylerrice on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/34389041)