Hacker News: zzsshh

New comment by zzsshh in "Ask HN: What Are You Working On? (April 2026)"

zzsshh — Mon, 13 Apr 2026 00:42:02 +0000

My wife and I have been working on a platform for close to year now, called The Influencer AI (https://www.theinfluencer.ai) that helps you generate a consistent AI person, and use them for images and talking video. We've been growing and polishing it based on user feedback since then. You can go from idea of a person in your head, to the finished video of her doing or saying anything you need, all on one platform, with the best ai models for each step leveraged for you.

New comment by zzsshh in "Ask HN: What are you working on? (January 2026)"

zzsshh — Sun, 11 Jan 2026 19:57:47 +0000

I'm working on The Influencer AI(www.theinfluencer.ai), a platform that lets you create realistic and consistent AI personas('ai influencers') to use on social media or as your brand ambassador. You can use this unique AI person in photos and talking videos, for use cases like talking about your product, creating a high quality Instagram persona, photos for your e-commerce site, etc.

New comment by zzsshh in "Steam Frame"

zzsshh — Wed, 12 Nov 2025 21:18:12 +0000

Google has also agreed to officially open up to competing app stores from the next version(https://www.theverge.com/policy/813991/epic-google-proposed-...), so the time is ideal for this. Valve, if you're reading this, please release Steam for Android.

New comment by zzsshh in "FFmpeg 8.0 adds Whisper support"

zzsshh — Wed, 13 Aug 2025 10:38:43 +0000

Does this finally enable dynamically generating subtitles for movies with AI?

Show HN: The Influencer AI – consistent AI "models" for photos and talking video

zzsshh — Tue, 22 Jul 2025 11:48:58 +0000

Hi HN, We’re a two‑person team (Anika & Zeeshaan) and we’ve spent the last 8 months building The Influencer AI: https://www.theinfluencer.ai

What it does: Spin up a consistent AI persona from either a handful of trait sliders or

~10 photos of a real person (yourself, a model, a client).

Use that same "AI influencer" to generate:

- photos & virtual try‑ons

- talking‑head video reels (image‑to‑video + voice)

-ad creatives in any pose, setting or style.

All assets come with full commercial rights.

How it works under the hood: Frontend: Next.js 15 (static where possible)

Backend / Auth: Supabase

Replicate/FalAI for AI models

Pricing / free tier Plans: $19, $39 (typical), $99 per month.

Looking for feedback on Does “one consistent AI person” actually solve a pain you have?

Which feature (or price point) would make this a no‑brainer?

Any red flags in UX, copy, or tech stack decisions?

Happy to set anyone up with extra credits for testing and answer questions. Thanks for reading, and would love to hear any thoughts.

Comments URL: https://news.ycombinator.com/item?id=44645705

Points: 1

# Comments: 0

New comment by zzsshh in "Using the Internet without IPv4 connectivity"

zzsshh — Sun, 29 Jun 2025 23:23:59 +0000

Why not just add the VPS to the Tailscale network and use it as an exit node?

New comment by zzsshh in "Show HN: I built a web app to edit photos with a prompt using Flux Kontext"

zzsshh — Wed, 18 Jun 2025 19:12:15 +0000

Thanks for trying it out!

Show HN: I built a web app to edit photos with a prompt using Flux Kontext

zzsshh — Wed, 18 Jun 2025 13:37:00 +0000

Built this to show off the recently released Flux Kontext model which is great at making edits based on your description, while keeping everything else the same. Eg. "make him wear a suit", "change the background to the beach", etc. No mask, etc needed.

I've used Nextjs 15, and this page is static and fully client side. I'm still torn between the value of RSC, and the downside of it not being served from a CDN.

I use Supabase for Db and Auth. Happy with these general, but their auth needs some work. The official supabase auth docs still recommend logic in nextjs middleware which hits your DB for protected routes.

My app gives you 3 free edits per day with no sign up required. There's rudimentary vibe-coded logic to enforce this, please don't bankrupt me, i have a wife and kids.

There's potential to expand on what the app can do with flux kontext also supporting multiple images as a prompt, for things like combining people into one photo.

Open to feedback and ideas on the tech, product or pricing.

Comments URL: https://news.ycombinator.com/item?id=44309782

Points: 2

# Comments: 2

New comment by zzsshh in "Ask HN: What are you working on? (May 2025)"

zzsshh — Mon, 26 May 2025 11:09:55 +0000

We're building a service to generate consistent AI personas, and create any media you need with them, photos, videos, tryons, product photos, etc.

- Works by selecting traits, which then trains a model(flux) OR uploading your own photos.

- Hopefully useful for shopify/ecomm store owners, digital agencies, or just about anyone to drastically speed up the time and reduce the cost to test creatives, create media content, or just do what you want with a model of yourself.

- Web with Nextjs, DB with Supabase, marketing with nothing.

- Happy to share more details into how we built this, and hear feedback and thoughts.

https://www.theinfluencer.ai/

New comment by zzsshh in "Impact of early life adversity on reward processing in young adults (2014)"

zzsshh — Fri, 18 Oct 2024 15:42:43 +0000

I wish scientific papers would have their conclusion at the top of the page.

New comment by zzsshh in "Nobody can separate AI headshots from real ones anymore"

zzsshh — Mon, 19 Jun 2023 22:47:58 +0000

I got a 7/10. I have a 70% chance of telling the Terminator apart from a regular guy who works out a lot when Skynet attacks.