github/ai-toolkit
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Remove color pallet for individual objects in the caption prompts

Browse Source
This commit is contained in:
Jaret Burkett
2026-06-19 06:56:18 -06:00
parent 60c1ac6a50
commit 022d1c29e0
3 changed files with 9 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
extensions_built_in/captioner/prompts/ideogram4_caption_prompt.py
View File

@@ -67,11 +67,11 @@ Field meanings:
Each element is one of (keys in EXACTLY this order):
```
{"type":"obj","bbox":[x1,y1,x2,y2],"desc":"...","color_palette":["#RRGGBB"]}
{"type":"text","bbox":[x1,y1,x2,y2],"text":"LINE ONE\\nLINE TWO","desc":"...","color_palette":["#RRGGBB"]}
{"type":"obj","bbox":[x1,y1,x2,y2],"desc":"..."}
{"type":"text","bbox":[x1,y1,x2,y2],"text":"LINE ONE\\nLINE TWO","desc":"..."}
```
`bbox` and `color_palette` are both OPTIONAL per-element; when present they keep the order shown above (`color_palette` is always LAST). `bbox`: see BBOX section below. `color_palette`: up to 5 UPPERCASE `#RRGGBB` strings of that element's own dominant colours — include it when the element has distinctive colours worth pinning (a red jacket, a brand logo, coloured text), omit it for colour-neutral elements.
`bbox` is OPTIONAL per-element (see BBOX section below). Do NOT emit a per-element `color_palette` — an element's colours belong in its `desc` as prose; the only colour-conditioning field is the top-level `style_description.color_palette`.
### SINGLE SUBJECT = SINGLE ELEMENT

6
extensions_built_in/captioner/prompts/ideogram4_prompt.py
View File

@@ -53,11 +53,11 @@ Name a recognized style ONCE here (see PLANNING → Style commitment); do not ap
Each element is one of (keys in EXACTLY this order):
```
{"type":"obj","bbox":[y1,x1,y2,x2],"desc":"...","color_palette":["#RRGGBB"]}
{"type":"text","bbox":[y1,x1,y2,x2],"text":"LINE ONE\nLINE TWO","desc":"...","color_palette":["#RRGGBB"]}
{"type":"obj","bbox":[y1,x1,y2,x2],"desc":"..."}
{"type":"text","bbox":[y1,x1,y2,x2],"text":"LINE ONE\nLINE TWO","desc":"..."}
```
`bbox` and `color_palette` are both OPTIONAL per-element; when present they keep the order shown (`color_palette` is always LAST). `bbox`: see BBOX section below. `color_palette`: up to 5 UPPERCASE `#RRGGBB` strings steering that element's own dominant colours — include it when the element has a distinctive colour (a red jacket, a brand logo, coloured text), omit it otherwise.
`bbox` is OPTIONAL per-element (see BBOX section below). Do NOT emit a per-element `color_palette` — an element's colours belong in its `desc` as prose; the only colour-conditioning field is the top-level `style_description.color_palette`.
### SINGLE SUBJECT = SINGLE ELEMENT

6
extensions_built_in/captioner/prompts/ideogram4_upsample_prompt.py
View File

@@ -53,10 +53,10 @@ Respect FIDELITY: if the prompt NAMES a style, medium, artist, or look, put it i
Each element is one of (keys in EXACTLY this order):
```
{"type":"obj","bbox":[y1,x1,y2,x2],"desc":"...","color_palette":["#RRGGBB"]}
{"type":"text","bbox":[y1,x1,y2,x2],"text":"LINE ONE\nLINE TWO","desc":"...","color_palette":["#RRGGBB"]}
{"type":"obj","bbox":[y1,x1,y2,x2],"desc":"..."}
{"type":"text","bbox":[y1,x1,y2,x2],"text":"LINE ONE\nLINE TWO","desc":"..."}
```
`bbox` and `color_palette` are both OPTIONAL per element; when present they keep the order shown (`color_palette` is always LAST). `bbox`: see BBOX. `color_palette`: up to 5 UPPERCASE `#RRGGBB` strings of that element's dominant colours — include it when the prompt gives the element a distinctive colour (a red jacket, coloured text), otherwise omit.
`bbox` is OPTIONAL per element (see BBOX). Do NOT emit a per-element `color_palette` — an element's colours belong in its `desc` as prose; the only colour-conditioning field is the top-level `style_description.color_palette`.
- **One coherent subject = ONE element.** A person, animal, vehicle, building, or plant is a single element; its parts are attributes of that element's `desc`, never separate elements. Multiple distinct subjects = multiple elements (one each).
- **`desc`:** identity first, then only the attributes the user gave (or that the structure plainly needs). For a named person/trigger: name + action/pose/placement ONLY, no appearance. For a generic un-named subject, you may state the concrete attributes the prompt implies, but do not invent an identity or backstory.