Expand character helper fact fields

This commit is contained in:
2026-08-14 13:14:59 +00:00
parent 23d2c20a50
commit 21a4d788ed
3 changed files with 118 additions and 6 deletions
+3 -3
View File
@@ -28,10 +28,10 @@
- Reads back the seven optional images for a selected MiniMax H3 plan scene, for example by connecting the current `clip_index`.
- `Dumas Character Helper`
- Inputs: `image1`, `image2`, `image1_picture_id`, `image2_picture_id`, `character_id`, `name`, `height_feet`, `height_inches`, `accent`, `general`
- Inputs: `image1`, `image2`, `image1_picture_id`, `image2_picture_id`, `character_id`, `name`, `alias`, `pronouns`, `age`, `nationality`, `occupation`, `height_feet`, `height_inches`, `accent`, `general`
- Outputs: `image1`, `image2`, `character_text`
- Passes both images through unchanged and builds a character reference string such as `<Picture 2> and <Picture 3> reference the same character who is called Dave.`
- Appends optional sentences for character ID, height, accent, and freeform notes only when those fields are filled in.
- Appends optional sentences for non-visual facts such as ID, alias, pronouns, age, nationality, occupation, height, accent, and freeform notes only when those fields are valid and filled in.
- `Dumas JSON String to Object`
- Input: `json_string`
@@ -189,7 +189,7 @@ decr -> use index - 1
`Dumas H3 Plan Attach Scene Images` and `Dumas H3 Plan Extract Scene Images` are a companion pair for `ComfyUI-MiniMaxH3-Contex-Loop`. The upstream H3 plan node cannot dynamically grow six new image sockets for every JSON-defined scene, so Dumas stores scene image bindings beside the plan using a lightweight token and an in-memory registry. That keeps `plan.json` archiving intact while still letting you wire up six IMAGE sockets per scene through chained helper nodes.
`Dumas Character Helper` lives in `Dumas/String`. Use the picture ID dropdowns to decide which `<Picture N>` tags get mentioned in the generated text, while the two IMAGE sockets continue downstream unchanged.
`Dumas Character Helper` lives in `Dumas/String`. Use the picture ID dropdowns to decide which `<Picture N>` tags get mentioned in the generated text, while the two IMAGE sockets continue downstream unchanged. The node is tuned for useful non-visible facts rather than visual descriptions already obvious from the reference images.
`Dumas Strip Iteration Suffix` keeps the part before the first underscore and drops the rest. Names like `char123_pose_final.png` become `char123.png`, while names with no underscore such as `char123.png` are left untouched.