Model Releases
Video models are hard. Real-time video models are even harder. Loved this breakdown by @itunpredictable on how we productionized Runway Char…
Video models are hard. Real-time video models are even harder. Loved this breakdown by @itunpredictable on how we productionized Runway Characters, our real-time interactive avatar model. We had to fi
Video models are hard. Real-time video models are even harder. Loved this breakdown by @itunpredictable on how we productionized Runway Characters, our real-time interactive avatar model. We had to figure out a lot of things like causal training, lipsyncing, parallelizing the VAE and pinning the KV cache so CUDA graphs don't break. One of the most cracked, under the radar research teams is at @runwayml. They were on the OG Stable Diffusion paper and just released the first autoregressive video model. Did a technical deep dive on this + some interesting inference optimizations: https://www.amplifypartners.co…
Source: Cristobal Valenzuela (X) | 2026-06-25