Spike/sskj-h3
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
sskj-h3/vbench-score/vbench-lora
History
Spike e917109d9b chore: keep benchmark repository source-only
2026-09-04 10:49:20 +08:00
..
scripts
update
2026-08-31 15:57:13 +08:00
README.md
update
2026-08-31 15:57:13 +08:00

README.md

MiniMax-H3 Larry v4-600 LoRA VBench-v1

This run is a one-variable comparison against ../vbench-base/results/h3-vbench-base-dense-tp2x4-20260826-run1.

  • Same official VBench-v1 metadata and all 16 dimensions
  • Same 944 unique prompts, one fixed-seed sample per prompt
  • Same seed 1101, 768P, 16:9, 5 seconds, flow shifts 12.0/3.0
  • Same four TP2 SGLang services and deterministic prompt balancing (236 each)
  • Same official static filter before temporal-flickering scoring
  • Changed only the serving environment/LoRA and sampler schedule: SGLang 0.5.18, Larry v4-600 EMA, 9 grid points = 8 denoiser evaluations

Larry v4-600 is intended for FL2VA, which is also the task used by VBench text-to-video generation here.

The launcher is resumable: completed videos recorded in generation/results.jsonl are reused after a safe restart.