01:28
2026-08-26
gist.github.com
generative-ai
MiniMax H3 (ComfyUI) R2V workflow with SLA sparse attention - 0.6MP 10s in 3m12s on RTX 3080 10GB
A developer shared a ComfyUI workflow for MiniMax H3 that runs a 0.6MP 10-second R2V generation in 3 minutes 12 seconds on an RTX 3080 10GB. The setup uses the H3SLAAttention custom node with SLA spar…