@HuggingApps: text-to-motion that can follow precise commands and sequences "a person walks forward, then sits down on the floor" — a…

X AI KOLs Following Models

Summary

PRISM is a 1.4 billion parameter text-to-motion model that can generate precise motion sequences from text commands, returning SMPL-X parameters for use in 3D rigs.

text-to-motion that can follow precise commands and sequences "a person walks forward, then sits down on the floor" — and it does them in that order 🚶🪑 PRISM (1.4B) hands you back SMPL-X params, so you can drop it on your own rig ▶️ on Spaces https://t.co/sXprTxZ2y0 https://t.co/ofyysWqpKI
Original Article
View Cached Full Text

Cached at: 08/24/26, 04:01 PM

text-to-motion that can follow precise commands and sequences

“a person walks forward, then sits down on the floor” — and it does them in that order 🚶🪑

PRISM (1.4B) hands you back SMPL-X params, so you can drop it on your own rig

▶️ on Spaces https://t.co/sXprTxZ2y0 https://t.co/ofyysWqpKI


PRISM Text-to-Motion - a Hugging Face Space by hugging-apps

Source: https://huggingface.co/spaces/hugging-apps/prism-text-to-motion Fetching metadata from the HF Docker repository...

Similar Articles

PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning

arXiv cs.AI

PRISM is a large-scale benchmark of 10,372 human-calibrated instruction-code pairs for evaluating programmatic video generation, with a funnel-style framework of four metrics. Evaluation of seven LLMs reveals a significant gap between code executability and spatial coherence.