Support per-chunk timeline durations
tests / test (push) Canceled after 0s
tests / windows-storage (push) Canceled after 0s

This commit is contained in:
2026-11-10 11:46:19 +00:00
parent 3716b02a57
commit 92135c0db0
13 changed files with 153 additions and 58 deletions
+3 -1
View File
@@ -59,6 +59,8 @@ For the supplied `2 × 10 s` workflow, put each time header on its own line and
Use the actual subjects and actions from your images; this is a syntax example, not a saved prompt in the downloadable workflow. Do not place prompt text on the same line as `[0-10s]`: that is not a Timeline header. A Reference can still influence a chunk without an explicit `@R` mention when its checkbox is enabled.
Timeline ranges can use different durations. For example, `[0-10s]`, `[10-15s]`, and `[15-25s]` create 10-second, 5-second, and 10-second chunks. The prompt plan reports those durations and the Sampler uses them during generation. Each duration must be at least 4.1 seconds; the normal recommended range remains 5–15 seconds.
The [official V3.9 workflow](../examples/workflows/MiniMax_H3_Continuum_V39.json) is the latest user-supplied JSON, copied without editing; its [single-workflow ZIP](../examples/workflows/MiniMax_H3_Continuum_V39.zip) is also available. It preserves the full V38X2 model/LoRA, Decode Cache, Finalize and Save chain. Six image loaders are prewired (initially bypassed); to use Image 7–9, add `H3 Continuum Load Image` nodes and connect them to the matching helper slots. The Sequence Prompt input remains connected but is intentionally blank: write your own prompt before Queue. The saved graph uses `Timeline`, two 10-second chunks, `Full Run` (displayed as Generate Full Video), First Image + Draft 0.30 MP size selection, and a separate Project ID. The earlier [Reference Inline migration fixture](../examples/workflows/MiniMax_H3_Continuum_V39_Reference_Inline.json) remains available unchanged. See the [step-by-step Reference Images guide](V39_REFERENCE_INLINE.md). Replace local media and model filenames as needed before Queue; enabling an image requires choosing a real file. Seven to nine active references can be particularly memory-intensive: start with fewer, smaller source images. A full ComfyUI backend restart and browser hard-refresh are required before the new node definitions appear. Browser save/reload and GPU acceptance of this unchanged default graph are still pending; a GitHub Release does not imply these gates or a Registry package have been completed.
**Compatibility:** Existing V3.8X2 workflows still use the V3.8 Sampler and old Reference Images 4–9 helper. V3.9 needs its new helper and connection. Open the new V3.9 workflow instead of only changing the Sampler type in an old graph: older V3.9 prototype workflows with direct 1–3 connections and Sampler-side routing widgets need manual rewiring, and their saved widget positions may differ. Accepted V3.8 Runs/Takes are not automatically migrated. Keep a copy of the previous workflow and use a new Run Name for V3.9.
@@ -307,7 +309,7 @@ Every `H3 Continuum Load Image` has `Enable Image`. `ON` loads through ComfyUI C
| `Control After Generate` | What ComfyUI does to `Base Seed` after a Queue | `fixed` for `Review Each Chunk`, resume, and controlled comparisons |
| `Audio Continuity` | Carries generated-audio context across boundaries | `true` for normal audiovisual generation |
| `Chunks` | Planned total chunk count, from 1 to 16 | Enter the final total, not the number to add next |
| `Seconds per Chunk` | Duration shared by every chunk | 5–15 seconds is the validated range; see duration notes below |
| `Seconds per Chunk` | Fallback duration when the prompt does not define per-chunk durations | 5–15 seconds is the validated range; see duration notes below |
| `Total Length` | Read-only `Chunks × Seconds per Chunk` | Check only; it never edits either input |
| `Size Source` | `First Image` or `Manual` output geometry | First Image for I2VA/FL2VA; Manual for T2VA or exact dimensions |
| `Resolution` | First-Image sizing preset | `Draft — 0.30 MP` for tests, `Balanced — 0.60 MP` for more detail, or `Native 768` for the H3-native short edge |