Add FLUX 3 Klein layout outputs to clothing planner

This commit is contained in:
2026-11-04 10:36:37 +00:00
parent 91c6659306
commit f677b7e567
3 changed files with 147 additions and 4 deletions
+16
View File
@@ -140,6 +140,22 @@ Outputs:
- `layout_json`: reusable normalized coordinates and warnings
- `layout_preview`: a diagnostic IMAGE showing the regions and optional labels
Optional FLUX.3 outputs:
- `flux3_prompt`: a complete FLUX.3 scene caption followed by the native
bounding-box JSON array. Connect this to the FLUX.3 Klein prompt input; keep
the workflow's official prompt upsampler in the normal position.
- `flux3_boxes_json`: the same bounding-box array separately for inspection or
downstream processing.
The `output_format` setting selects `legacy`, `flux3`, or `both` (default).
FLUX.3 boxes use `[top, left, bottom, right]` integer coordinates on a 0–1000
top-left-origin grid. Every generated ID is also emitted as `<id>` in the
caption. `flux3_reference_mode=editing` is intentionally rejected until source
coordinates and reference-image identifiers are available; the current VLM
inventory schema supports generation-style layouts only. Bounding boxes guide
placement and scale but are not hard pixel masks.
The planner uses normalized top-left-origin coordinates, configurable margins
and spacing, and rejects malformed or invalid inventory fields with actionable
errors. The preview is diagnostic only; feeding it to an image model does not