venice-video-harness 2.13.0 → 2.13.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -1,5 +1,17 @@
1
1
  # Changelog
2
2
 
3
+ ## 2.13.1 — 2026-08-05
4
+
5
+ ### Changed
6
+
7
+ - **README: Video Model Routing catches up with the 2.13.0 multi-shot default.**
8
+ The routing table gained a "Multi-shot units" row naming
9
+ `seedance-2-0-enhanced-reference-to-video` as the default lane (`Lens switch.`
10
+ separators, pure reference mode from the full slot plan) with
11
+ `kling-o3-pro-image-to-video` demoted to an explicit
12
+ `videoDefaults.multiShotModel` override, and the "carry these" rule 3 now
13
+ notes the planner applies Seedance native multi-shot by default. Docs only.
14
+
3
15
  ## 2.13.0 — 2026-08-05
4
16
 
5
17
  ### Changed
package/README.md CHANGED
@@ -433,6 +433,8 @@ Anti-Patterns" (28 entries). If you can only carry a few, carry these:
433
433
  3. **Prefer Seedance native multi-shot for any 2–3 beat scene.** One generation
434
434
  with `Lens switch.` separators holds identity, environment, and lighting
435
435
  across the beats and costs roughly 3× less than three separate renders.
436
+ (Since 2026-08-05 the planner does this by default: multi-shot units render
437
+ on Seedance R2V Enhanced with the full reference slot plan.)
436
438
  4. **Front-load style.** Aesthetic descriptions go at the start of a prompt, not
437
439
  the end, or style drifts across angles.
438
440
  5. **Keep Seedance prompts under 60 words**, using Subject, Action, Camera,
@@ -944,6 +946,7 @@ Every shot renders in **pure reference mode** — no start image — from an ord
944
946
  | **Character shots (up to ~6 characters)** | `seedance-2-0-enhanced-reference-to-video` | Default R2V — up to 9 `reference_image_urls` with `@Image` tags (chars + blocking plate + location angles), 1080p, up to 15s, native stereo audio |
945
947
  | **Character shots (budget overflow)** | `kling-o3-standard-reference-to-video` | Auto-fallback — structured `elements` for multi-character identity |
946
948
  | **Establishing / mood / action** | `seedance-2-0-enhanced-reference-to-video` | Anchors to location reference angles via `@Image` tags |
949
+ | **Multi-shot units (2+ grouped beats)** | `seedance-2-0-enhanced-reference-to-video` | Default since 2026-08-05 — ONE native multi-shot generation with `Lens switch.` separators, pure reference mode from the full slot plan. The old default `kling-o3-pro-image-to-video` (no reference support at all) is an explicit `videoDefaults.multiShotModel` override only |
947
950
 
948
951
  These defaults are overridable per-project via `series.json` → `videoDefaults`. To target a non-Seedance family (e.g. for accounts that lack Seedance access, or projects that need a different look), set `videoDefaults` to `kling-o3-standard-reference-to-video` (character consistency) and `veo3.1-fast-image-to-video` (atmosphere). Image models default to `nano-banana-2` / `nano-banana-2-edit` for all panels regardless of video family.
949
952
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "venice-video-harness",
3
- "version": "2.13.0",
3
+ "version": "2.13.1",
4
4
  "description": "Standalone consistency-first video production CLI powered by the Venice API",
5
5
  "homepage": "https://github.com/jordanurbs/venice-video-harness",
6
6
  "repository": {