⠋ building cool stuff ⠙ 23 ┃product engineer @HeyGen based in Toronto ┃ Built @editfa_st ┃Building @HyperFrames_ by HeyGen
🇪🇸/🇨🇦/🇺🇸
- Tweets 13,045
- Following 1,480
- Followers 3,477
- Likes 72,739
Pinned Tweet
just a happy boy from a small town in Spain, here in SF
thanks @HeyGen_Official @joshua_xu_ @liu8in for making it possible ❤️
10
97
16,299
merged this PR that enables coding harnesses like claude code to look to their own usage while making @HyperFrames_ videos so they should be more aware and have higher sense of urgency to make a HyperFrames videos without consuming ton of usage github.com/heygen-com/hyperf…
6
1
21
955
we have grown +600k downloads/month this September in @HyperFrames_, we are seeing more adoption and it's more stable + fast than prior months
btw join our discord server if you want to chat with us! discord.gg/EbK98HBPdk
10
1
53
2,011
made with @HyperFrames_ btw
1
1
23
2,007
Miguel Ángel retweeted
Spain produces incredible engineers.
Spain produces incredible founders.
Spain produces incredible researchers.
What Spain lacks is enough connection between them.
That's fixable.
8
21
173
3,815
new feature for the @HyperFrames_ CLI:
$ npx hyperframes timeline
we now provide a timeline for agents 🏃
2
4
45
1,735
star the repo if you haven't! github.com/heygen-com/hyperf…
1
97
love this video so much,
remixed it with some eastern asian culture!
all i did was sending the artifact to @HyperFrames_ studio and @claudeai did the rest
proof 🧵
Welcome To the era of Super intelligence : Fable 5.5
behold superman in continuous animation in different art style
5
3
18
1,812
required skill: @HyperFrames_
and the audacity to go battle the corporate giants in the industry
We're hiring an AI-native content creator
Your job: make AI video that people actually stop scrolling for. X, Reels, TikTok, Shorts
You should live in viral formats, obsess over retention, and have your version of a trend up the same night it starts
DM us your 5 best examples
19
1
53
3,519
We're hiring an AI-native content creator
Your job: make AI video that people actually stop scrolling for. X, Reels, TikTok, Shorts
You should live in viral formats, obsess over retention, and have your version of a trend up the same night it starts
DM us your 5 best examples
169
64
506
31,917
from may 1st -> oct 1st, trending on github, again
and every time, it's cuz the SOTA LLMs (& agents) getting better and better at Code2Video tasks
opus 5.5 made this celebration video with just one prompt + access to our latest skills: github.com/heygen-com/hyperf…
the open-sourced foundation layer for agents to make videos.
$ npx skills add heygen-com/hyperframes
“anything a browser can render can be part of your video”
agents writes HTML+CSS+JS, HyperFrames gives you preview, NLE tools and renders into MP4
github.com/heygen-com/hyperf…
8
6
46
4,180
In September, we shipped three tools for builders.
An open-source real-time avatar stack with OpenAI's GPT-Live-1
The Code2Video Benchmark with Kaggle, measuring if AI-made video is actually well made
And a Professional Voice Clone for API
Read More: heygen.com/blog/heygen-septe…
16
13
98
9,555
star it btw if you haven't already: github.com/heygen-com/hyperf…
2
94
Miguel Ángel retweeted
1/ @HeyGen Video 1 is now on OpenRouter.
Built for businesses. In blind side-by-side tests, it holds up against the top video models at a fraction of the price.
openrouter.ai/heygen/heygen-…
5
12
191
25,415
all of this is code
Sonnet 5.5 max made this 39s video in 17 hours w/ @HyperFrames_ , prompt below
concept: depth is the hierarchy. On a screen you look into, focus picks what matters and going deeper shows more.
• One object: a black glass instrument with three windows, all showing the same tide reading, 3.67 m.
• Three depths, three levels: the shallowest window shows only the number, the middle one adds range, high water and rate, the deepest adds a trend and twelve readings.
• The camera pulls focus from window to window, so focus, not layout, decides what you read. It ends on the engraved line "Depth is the hierarchy".
• The design idea: information hierarchy carried by optical depth (glass, refraction, real depth of field) instead of size, weight and position on a flat screen. The starting point was Ferrari Luce's layered display.
• Built as one HyperFrames page: three.js glass and metal, live HTML text drawn into the 3D scene through HTML-in-Canvas, thin-lens depth of field, every frame deterministic.
Introducing Claude Sonnet 5.5, the second model in the Claude 5.5 family.
It’s a clear upgrade over Sonnet 5, runs more than 30% faster, and costs up to 30% less for most work.
26
14
343
29,381