supervision just hit 40,000 GitHub stars!
it now powers over 6.5k open-source computer vision projects, including all my demos like basketball AI
link: https://t.co/xXMRaS4ejS
Paper is becoming a major contender for the best vector creation tool.
Also it’s SVG generations and vectorizations are powered by Quiver’s Arrow 1.1 — let’s go!
Today, we’re excited to introduce Miso One, the most emotive voice model in the world.
Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency.
We’ve open-sourced the model weights, with API access coming soon.
Hear how Miso One sounds in the thread below.
Motion design with Claude + Higgsfield MCP 🧩
Turn a single text prompt into pro-level motion videos.
It’s actually insanely simple:
1. Describe your idea to Claude
2. Ask it to generate a storyboard
3. Pick your favorite concept
4. Let Higgsfield MCP render the final video
🚀 Screenforge v0.6.3 is out now
Cinematic Zoom is live 🔥
Based on the amazing feedback people shared on the feature, I went back and tried improving it further.
The demo below is a combination of Cinematic Zoom + 2D Zoom. Feels a lot more cinematic and flexible now.
🔊 Sound on.
Let me know if we cooked with this one.
Other updates in v0.6.3:
• Hide the cursor completely
• Cut camera clips, reposition the camera, and smoothly transition between shots
Download link in the comments.
Most loaders are forgettable. I built this as a design exploration at Mistral to see what happens when they’re not.
Today, I’m open sourcing it. Build something wild, tag me, and send over any feedback or bugs you find.