track-gate: RefMod workflows author segments as task_mode ref (generation_type r2v) even with no timeline images - user-verified: refmods pair with reference-mode conditioning; Sam payload flipped default->ref, regenerated, validator green
This commit is contained in:
parent
b45e6b72e7
commit
9b197ae024
8
easy-media-track-gate/references/track-schema.md
Normal file → Executable file
8
easy-media-track-gate/references/track-schema.md
Normal file → Executable file
@ -146,6 +146,14 @@ video tracks `var(--primary)`. Keep an existing track's own color.
|
|||||||
```
|
```
|
||||||
|
|
||||||
- `task_mode`: `default`, `l2v`, `ref`, `edit`.
|
- `task_mode`: `default`, `l2v`, `ref`, `edit`.
|
||||||
|
- RefMod workflows (identity driven by `MiniMaxH3RefModsLoader` + `MiniMaxH3RefModApply`
|
||||||
|
outside the timeline): author segments as `task_mode: "ref"` even with no per-segment
|
||||||
|
images — the payload then carries `generation_type: "r2v"`, TaskOutput TYPE becomes
|
||||||
|
`r2v`, and the matchLine/promptLine pair switches `minimaxH3ToVideo` to `reference`
|
||||||
|
mode, which pairs with the RefMod conditioning. `ref` rows with `images: []` are
|
||||||
|
legal (refmod pictures ride the conditioning, not the timeline); prompts stay
|
||||||
|
picture-token-free. Verified live by the user: the relay one-pass render works with
|
||||||
|
r2v and refmods "work better with ref2va (r2v)".
|
||||||
- `continuity_mode`: `shot` (standalone shot), `context` (normal context join) or
|
- `continuity_mode`: `shot` (standalone shot), `context` (normal context join) or
|
||||||
`context_drift` (context drift control); the legacy value `context_swap` is still read.
|
`context_drift` (context drift control); the legacy value `context_swap` is still read.
|
||||||
- `ref_image_size`: `match` or `max`.
|
- `ref_image_size`: `match` or `max`.
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user