🚀 Just released on HF: Spark-TTS, an LLM-powered text-to-speech model that does zero-shot voice cloning & fine-grained voice creation — all in a single stream!
> Built on Qwen2.5
> Control pitch, speed, & speaker style directly from text.
Procedural waterfall sparkles. 🙂
Intersecting geometry triggers glowing bioluminescent 'particles' in the shader and interacts with realtime flowing lights (watch the mesh surface).
#unity3d#realtimevfx#gamedev
The wait is finally over!!! 😁
We just dropped an in-depth tutorial on how to build your own robot!
Teach it new skills by showing it a few moves with just a laptop.
Then watch your homemade robot act autonomously 🤯
1/🧵👇
I've open-sourced my interactive GPU wave sim on GitHub. If I have time I'll come up with some more interesting examples.
🔗 github.com/MirzaBeig/Wave-Si…
Shader Graph used for rendering, so you can easily preview the output and see how channels are mapped.
#unity3d#gamedev#indiedev
Tired of "baked" texture from AI generated 3D objects?
Intrinsic Image Diffusion solves this by predicting materials and generates albedo, roughness, and metallic maps from a single image.
Pre-baked texture maps bye bye.
peter-kocsis.github.io/Intri…
Introducing EdgeSAM, the first SAM variant that can run at over 30 FPS on an iPhone 14 with minimal compromise in performance.
Code, models, and Hugging Face demo are available!
arXiv: arxiv.org/abs/2312.06660
Project page: mmlab-ntu.github.io/project/…
As destiny approaches, let's listen to Elon's 2018 speech one more time.
“It's time to go forth... be out there among the stars... I find that incredibly exciting, that makes me glad to be alive. I hope you feel the same way” - Elon