Harden and streamline H3 reference matching

This commit is contained in:
2026-08-28 13:49:01 +00:00
parent 1ad68ee9e4
commit ddd7dbb5af
3 changed files with 100 additions and 29 deletions
+13 -11
View File
@@ -944,23 +944,23 @@ Character wardrobe seeding:
What the long-videos code actually uses:
- `image`: the real location reference image H3 sees when that slot is selected for a shot
- `description`: injected as location context when that slot is explicitly tagged
- `general`: injected as location notes when that slot is explicitly tagged
- `name`, `location_id`, `alias`: used mainly as labels in summaries and injected sentences, not for automatic prose matching
- `description`: injected as location context when that location ref is matched
- `general`: injected as location notes when that location ref is matched
- `name`, `location_id`, `alias`: used for location-name matching in beat text and as labels in injected sentences
Important difference from character refs:
- location refs are **not** auto-matched from location names in beat prose
- if you write `in the cafe` and do not tag `<Picture N>`, the location image may still be in the shot because of `ref_mode`, but the location text metadata is not auto-injected just from that name
- location refs can now be matched from location names or aliases in beat prose
- explicit `<Picture N>` tags are still the strongest way to force an exact slot on an exact beat
### When location data gets used
Location node data has two separate paths:
1. The location image can be attached to shots through normal ref routing.
2. The location text metadata is only injected when you explicitly tag that slot with `<Picture N>`.
2. The location text metadata is injected when the beat tags that slot with `<Picture N>` or names the location by `name`, `id`, or `alias`.
So location references are more tag-driven than character references.
So location references are no longer tag-only, but tags are still the safest exact-routing tool.
Simple usage patterns:
@@ -972,7 +972,8 @@ What to remember:
- tags control explicit slot placement
- names can pull matching character refs into the real image-conditioning list
- location refs are often tagged because they are about where the shot happens
- names can now pull matching location refs into the real image-conditioning list too
- location refs are still often tagged because they are about where the shot happens
- character refs are often named because they are about who is in the shot
### Scenarios
@@ -1021,12 +1022,13 @@ Setup:
What happens:
- with `auto ref2v` or `every shot`, the cafe image may still be conditioning the shot
- but the location `description` and `general` fields are not auto-injected from the word `cafe`
- the word `cafe` can now match the location ref by name or alias
- that means the location image and location text context can both be pulled in even without a tag
- `<Picture 3>` is still better if you want exact manual slot routing on that specific beat
What to do:
- add `<Picture 3>` on the beat where the location wording matters
- add `<Picture 3>` when you want to force that exact location slot on that exact beat
### Scenario: character face is partly right, but identity is weak