chris.dumas/DumasNodes
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

Replace Long Videos with upstream sampler

Browse Source
This commit is contained in:
chris.dumas
2026-09-10 09:46:37 +00:00
parent 8d4232a142
commit 72f9b07ed8
7 changed files with 12793 additions and 9925 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6 -12
View File
@@ -33,18 +33,12 @@
- Outputs: `plan`, `image1`..`image9`, `connected_images`
- 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_1`..`ref_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.
- Full user guide: [`H3_LONG_VIDEOS_GUIDE.md`](./H3_LONG_VIDEOS_GUIDE.md)
- Only the canonical `DumasH3LongVideos` node key is exposed now; the older FL2VA/REF2VA alias entries are no longer duplicated in the Add Node menu.
- Prompt `<Picture N>` tags now map to the actual ref socket numbers you wire, even with gaps such as only `ref_2` and `ref_7` connected.
- Character refs now contribute appearance and wardrobe context from the same structured object, while location refs contribute environment context from theirs.
- The default ref2v bias is now stronger: `ref_mode` defaults to `auto ref2v` so untagged prompts condition every shot instead of only shot 1, and `ref_noise_aug` defaults to `0.95` rather than the upstream-literal `0.999`.
- `Dumas H3 Latent Upscale Params` provides the optional pre-decode latent refinement stage for the long-video node.
- Per-shot directives now support `continuity:`, `ref_mode:`, `ref_noise_aug:`, `anchor_add:`, `soundscape:`, and `music:` in addition to the existing timing and wardrobe directives.
- `Dumas H3 Long Videos`
- Inputs/outputs: the current upstream `MiniMax-H3-Longvideos` sampler surface, exposed under the existing `DumasH3LongVideos` key for saved Dumas workflows.
- The local Dumas prompt-engineering fork has been removed from this node. Long Videos now wraps the upstream sampler/engine directly so it can track the source project again.
- Upstream compatibility keys `H3LongVideos`, `H3LongVideosFL2VA`, `H3LongVideosV1`, and `H3LongVideosREF2VA` are also registered to the same class.
- The old Dumas browser widget grouping script is disabled for this node because it targeted controls that no longer exist on the upstream sampler.
- Upstream license text is included in [`H3_LONGVIDEOS_UPSTREAM_LICENSE.txt`](./H3_LONGVIDEOS_UPSTREAM_LICENSE.txt).
- `Dumas H3 Latent Upscale Params`
- Inputs: `mode`, `model_name`, `method`, `width`, `height`, `device`, `precision`, `sampler_name`, `scheduler`, `steps`, `denoise`, `megapixels`, `tile_width`, `tile_height`, `overlap`, `fade_width`, `fade_height`, `overlap_mode`, `overlap_blend`, `tile_size_mode`, `grid_rows`, `grid_cols`, `spatial_w_overlap`, `spatial_h_overlap`, `min_tile_size`, `masked_area_noise`, `brightness_match`, `dynamic_fade`, `dynamic_fade_min`, `chunk_length`, `temporal_overlap`, `resize_conditioning`, `anchor_strength`