Tencent's Hunyuan team has released HY-Motion 1.0, an open-source model that generates 3D human motion from natural-language text prompts. Combining a Diffusion Transformer (DiT) with Flow Matching, it is the first text-to-motion model scaled to a billion parameters, and its inference code and pretrained weights are already available.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.