Expand H3 ref2v slots and tag routing

This commit is contained in:
2026-08-25 19:35:48 +00:00
parent 27d1b76cd5
commit efce589cc5
3 changed files with 163 additions and 92 deletions
+2 -1
View File
@@ -34,10 +34,11 @@
- Reads back the nine optional images for a selected MiniMax H3 plan scene, for example by connecting the current `clip_index`.
- `Dumas H3 Long Videos (FL2VA + REF2VA)`
- Inputs: H3 model stack, prompt socket, optional `first_frame`, optional `ref_image_1`..`ref_image_4`, plus the upstream long-video control surface for pacing, continuity, audio, overlays, and guards
- Inputs: H3 model stack, prompt socket, optional `first_frame`, optional `ref_image_1`..`ref_image_9`, plus the upstream long-video control surface for pacing, continuity, audio, overlays, and guards
- Outputs: `images`, `audio`, `info`, `script`, `frames_per_shot`, `total_frames`, `shots`, `video_seconds`, `fps`, `fps_int`, `latent`, `soundscape`
- First-pass Dumas port of the `MiniMax-H3-Longvideos` sampler, brought in as a local starting point for long-form H3 chaining work.
- Keeps the upstream split-beats / handoff / ref-routing behavior close to source so future Dumas-specific improvements can be compared against a known baseline.
- Prompt `<Picture N>` tags now map to the actual ref socket numbers you wire, even with gaps such as only `ref_image_2` and `ref_image_7` connected.
- `Dumas H3 Shot Length`
- Inputs: `shot_seconds`, `fps`, optional `cap_to_h3_max`