Add MiniMax H3 LongVideos candidate

This commit is contained in:
Morpheus
2026-09-28 14:37:51 +00:00
parent 93c444be26
commit 0064d7d6be
2 changed files with 48 additions and 0 deletions
+37
View File
@@ -0,0 +1,37 @@
# MiniMax H3 LongVideos candidate
This is the next R2V candidate after rejecting connected-chunk continuation.
It generates the clip directly from the character reference and a
paragraph-driven shot plan; it does not load or encode a previous video.
## Fixed baseline
- Reference: `reference.png`
- Prompt: `prompt.txt` equivalent bright park scene, expressed as a scene
paragraph plus one action paragraph in the API graph
- Resolution target: 960×544 landscape (`0.55` megapixels, 16:9)
- Duration: 10 seconds
- Steps: 8
- Sampler: `res_multistep`
- Scheduler: `simple`
- Seed: 20260927
- Shift video/audio: 12 / 3
- Reference noise augmentation: 0.999
- Latent and post upscaling: disabled for this baseline
## Files
- `h3-longvideos-api.json` — direct API workflow
- `reference.png` — fixed character reference
- `prompt.txt` — shared reference-to-video prompt source
## Why this candidate
The installed `H3LongVideos` node supports paragraph-driven shot chaining,
synchronized audio, identity references, and later latent/RTX upscale paths.
It is the appropriate next workflow for multi-shot generation without loading
the previous clip into VRAM.
The imported source workflow remains at
`models/minimax/minimax-h3-longvideos-smite79/workflow.json`. This optimized
API graph is intentionally reduced to the fixed reference-video baseline.