T=16 flow model generates 16 frames per inference for smoother motion
pixlpa · x · 2026-10-16
The author shares an alternative T=16 flow model for their video pipeline: it generates 16-frame flow grains per inference. Higher T-values produce noisier flow maps but improve motion continuity since more frames are generated at once. The earlier version generated 8 frames per inference, conditioned on the current image, previous 4 flow frames, and motion parameters. Side-by-side comparison video included.
More from Multimodal
- Train Your Own LTX IC-LoRA With Grok Doing the Heavy Lifting — PurzBeats · 2026-10-16
- Hugging Face launches Open TTS Leaderboard: objective metrics to rank 8K+ open TTS models — dl_weekly · 2026-10-16
- Flux 3 Klein excels at lighting and atmosphere but fumbles living subjects — Schattenmensch · 2026-10-16
- Circus clown nails tightrope stunts in impressive Seedance 2.5 video demo — azed_ai · 2026-10-16
- ComfyUI puts up $25,000 to counter Higgsfield's broken open-source promise — PurzBeats · 2026-10-16
- Underwater brand films built from one jellyfish with an open-source Minimax template — w1kke · 2026-10-16