Generative thermodynamic computing produces images with zero neural network calls
mikeflache · x · 2026-09-24
Researchers demonstrated "Generative Thermodynamic Computing": a physical thermodynamic system that generates images without a single neural network call. Current image generators rely on billions of parameters and millions of dollars in GPU compute to mathematically denoise static. Instead of coding the denoising, this approach lets physical matter evolve over time according to the laws of physics—information is stored in the physical system rather than software weights. If engineered at scale, it could dramatically cut the cost of generation.
More from Multimodal
- MiniMax H3-Image image model debuts on Tencent's Miora, free to try Nov 11–17 — aziz4ai · 2026-11-11
- MiniMax H3 hits 100 days open-source: 1,472 derivative models, 148M+ downloads — linoy_tsaban · 2026-11-11
- MiniMax H3-Image explodes an espresso machine photo into 15 labeled parts — Charlietest123 · 2026-11-11
- Indie dev built a tool that clips best moments from 4-hour streams in 30 minutes — kissaadams · 2026-11-11
- Non-Blender user makes a video in 30 minutes with Claude and Seedance — FinanceYF5 · 2026-11-11
- Whimsical Woodland: A Watercolor AI Art Prompt Template for Dreamy Forest Scenes — LudovicCreator · 2026-11-11