#video-generation — Blog — ai-muninn

~ / blog / tag / video-generation

❯ grep -r "#video-generation" ~/blog

7 matches

datereadtitle
2026-10-0812m
FastH3 on an RTX 5090: a 5-second talking clip in under a minute, 2.9x faster than MiniMax-H3
#fasth3 #minimax-h3 #video-generation #lip-sync
2026-10-0813m
Kandinsky 6.0 Pro on an RTX 5090: lip-synced English dialogue works, Chinese isn't quite there yet
#kandinsky-6.0 #video-generation #lip-sync #text-to-video
2026-09-1424m
[Video] MiniMax H3 Super Acceleration on a DGX Spark: 2x native cold, 3.14x warm
#dgx-spark #gb10 #minimax-h3 #ltx-2.5
2026-09-1426m
[Benchmark] Two-stage MiniMax-H3 + LTX-2.5 on a 2080 Ti: 1344x768 with audio in 165s
#2080-ti #turing #minimax-h3 #ltx-2.5
2026-09-0312m
[Benchmark] From OOM to 8.6 minutes: a MiniMax-H3 config stack for one RTX 5090
#minimax-h3 #rtx-5090 #comfyui #nvfp4
2026-08-3114m
[Benchmark] Ten effect embeddings for MiniMax-H3 — 10 MB that buys you bullet time, fire breath and a full year of seasons
#minimax-h3 #comfyui #rtx-5090 #video-generation
2026-06-019m
[Benchmark] NVFP4 shrinks a video model 33% on a DGX Spark — with zero speed gain
#nvfp4 #sulphur-2 #ltx-2.3 #dgx-spark

← back to all posts