@aswless_854771076/ai_short_studio_cli 0.1.155 → 0.1.157
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/README.md +1 -1
- package/dist/commands/canvas/document/get.js +3 -3
- package/dist/commands/canvas/document/save.js +8 -2
- package/dist/commands/canvas/documents.js +1 -1
- package/dist/commands/canvas/workflow/status.js +1 -1
- package/dist/domain/canvas-schema-key.d.ts +2 -0
- package/dist/domain/canvas-schema-key.js +21 -0
- package/dist/domain/vvicat-api.js +1 -1
- package/package.json +1 -1
- package/skills/using-vvicat-ai-short-studio-cli/SKILL.md +13 -13
- package/skills/using-vvicat-ai-short-studio-cli/references/commands/canvas.md +21 -3
- package/skills/using-vvicat-ai-short-studio-cli/references/humanizer/SOURCE.md +9 -0
- package/skills/using-vvicat-ai-short-studio-cli/references/humanizer/humanizer.md +408 -5
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/SKILL.md +16 -30
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/assets/generate-character-images.md +2 -2
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/assets/generate-character-profiles.md +2 -2
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/assets/generate-drama-art-style.md +3 -3
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/assets/generate-prop-assets.md +2 -2
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/assets/generate-scene-assets.md +2 -2
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/assets/manage-drama-art-styles.md +3 -3
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/assets/manage-drama-assets.md +4 -4
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/assets/modules/ideate-drama-from-market/prompts/market_inspiration.en.txt +1 -1
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/assets/modules/ideate-drama-from-market/prompts/market_inspiration.zh.txt +1 -1
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/assets/modules/plan-drama-production/prompts/production_plan.en.txt +1 -1
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/assets/plan-drama-assets.md +2 -2
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/codex-contracts.md +3 -3
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/creation/analyze-drama-source.md +2 -2
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/creation/define-drama-brief.md +1 -2
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/creation/design-drama-bible.md +1 -1
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/creation/humanizer.md +4 -4
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/creation/outline-drama-series.md +1 -1
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/creation/short-drama.md +1 -1
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/creation/write-drama-director-book.md +1 -2
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/creation/write-drama-episode.md +1 -2
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/editing/edit-deliver-drama.md +2 -2
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/editing/edit-drama-timeline.md +4 -5
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/editing/remotion-best-practices.md +4 -5
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/editing-workflow.md +8 -8
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/feature-completeness.md +25 -25
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/generation/configure-generation-providers.md +5 -11
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/generation/design-drama-audio.md +4 -2
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/generation/drama-generation-service.md +6 -6
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/generation/generate-drama-videos.md +4 -4
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/generation/generate-storyboard-images.md +3 -3
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/generation/monitor-drama-tasks.md +9 -7
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/generation/transform-drama-media.md +2 -2
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/generation/write-drama-video-prompts.md +9 -8
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/market/analyze-drama-market.md +8 -8
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/market/ideate-drama-from-market/market-inspiration.schema.json +1 -1
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/market/ideate-drama-from-market.md +1 -1
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/market/scripts/README.md +59 -0
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/market/scripts/analyze.mjs +517 -0
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/market/scripts/analyze.test.mjs +354 -0
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/market/scripts/juchacha-client.mjs +188 -0
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/market/scripts/juchacha-client.test.mjs +218 -0
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/market/scripts/normalize.mjs +458 -0
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/market/scripts/normalize.test.mjs +236 -0
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/market/scripts/report.mjs +69 -0
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/market/scripts/store.mjs +341 -0
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/market/scripts/store.test.mjs +302 -0
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/module-map.json +43 -133
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/music-catalog-providers.md +3 -3
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/operations/manage-drama-projects.md +5 -5
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/operations/orchestrate-short-drama.md +7 -8
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/operations/recover-drama-pipeline.md +1 -1
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/operations/short-drama-skill-index.md +7 -7
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/operations/use-short-drama-studio.md +4 -6
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/pipeline.md +40 -65
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/project-spec-v1.md +91 -131
- package/skills/using-vvicat-ai-short-studio-cli/references/{hypit/playbooks/craft → short-drama/prompt}/h3-prompt-writing.md +4 -4
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/prompt/prompt-craft.md +185 -0
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/prompt/seedance-prompting.md +64 -0
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/prompt-skill-index.md +2 -2
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/recreation/recreation-qa.md +87 -0
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/review/review-drama-script.md +2 -2
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/review/review-drama-shots.md +5 -5
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/storyboard/build-drama-storyboard.md +1 -3
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/storyboard/design-fight-video.md +0 -4
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/storyboard/direct-blender-previz/direction-contract.md +1 -1
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/storyboard/direct-blender-previz.md +1 -1
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/storyboard/generate-blender-previz.md +5 -10
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/storyboard/plan-drama-production.md +2 -6
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/storyboard/plan-shot-continuity.md +4 -4
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/usage-guide.md +28 -70
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/SKILL.md +0 -447
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/creation/brief.md +0 -93
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/creation/project-files.md +0 -246
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/creation/reference-video.md +0 -266
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/creation/script-and-time.md +0 -253
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/creation/transformations.md +0 -141
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/environment/distribution.md +0 -176
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/environment/local-tools.md +0 -411
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/environment/model-and-provider.md +0 -275
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/environment/profile.md +0 -286
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/asset-and-shot-preproduction.md +0 -193
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/b-roll.md +0 -94
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/caption-tracking.md +0 -125
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/captions.md +0 -252
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/examples/conversation-images.md +0 -218
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/examples/image-direction.md +0 -123
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/generated-dependencies.md +0 -38
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/graphic-compositions.md +0 -85
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/image-direction.md +0 -95
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/motion-graphics.md +0 -68
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/recreation-policy.md +0 -51
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/screen-demonstrations.md +0 -51
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/shot-production-contracts.md +0 -161
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/sound-mix.md +0 -76
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/video-direction.md +0 -433
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/voice-and-performance.md +0 -224
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/craft/voice-direction.md +0 -99
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/narration-led-demo.md +0 -87
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/presenter-led-explainer.md +0 -160
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/ranking-listicle.md +0 -71
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/reference-recreation-canvas.md +0 -19
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/short-drama-workflow.md +0 -165
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/short-drama.md +0 -88
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/street-interview.md +0 -92
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/talking-head.md +0 -82
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/formats/two-person-podcast.md +0 -101
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/playbooks/index.md +0 -77
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/audio-presentation.md +0 -49
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/authoring.md +0 -228
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/browser-capture.md +0 -112
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/builds.md +0 -330
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/caption-authoring.md +0 -156
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/caption-presentation.md +0 -66
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/component-design.md +0 -217
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/component-sharing.md +0 -150
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/component-visuals.md +0 -152
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/examples/detail.svrun +0 -8
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/examples/direction.svs +0 -14
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/examples/look.svs +0 -6
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/examples/material.svrun +0 -5
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/examples/production.svml +0 -73
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/examples/production.svrun +0 -5
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/examples/visuals.ts +0 -62
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/fonts-and-text.md +0 -138
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/image-operations.md +0 -102
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/index.md +0 -73
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/media-presentation.md +0 -111
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/media.md +0 -246
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/performance.md +0 -114
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/prompt-kits.md +0 -165
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/rendering.md +0 -141
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/review.md +0 -211
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/runs.md +0 -151
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/script-syntax.md +0 -236
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/snapshots.md +0 -90
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/sound.md +0 -75
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/source-syntax.md +0 -163
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/spatial.md +0 -189
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/studio-companions.md +0 -186
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/studio.md +0 -249
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/system.md +0 -169
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/timeline.md +0 -74
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/timing.md +0 -96
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/track-authoring.md +0 -215
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/tracks.md +0 -67
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/video-downloads.md +0 -47
- package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/vocabulary.md +0 -119
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/README.md +0 -11
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/comfly-provider.md +0 -12
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/generation/seedance-community-skills.md +0 -23
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/recreation/publish-drama-references/litterbox.md +0 -5
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/runninghub-provider.md +0 -33
- package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/starrouter-provider.md +0 -53
- package/skills/using-vvicat-ai-short-studio-cli/references/video-model-routing.md +0 -10
- package/skills/using-vvicat-ai-short-studio-cli/references/video-prompt-spec.md +0 -32
- /package/skills/using-vvicat-ai-short-studio-cli/references/{short-drama/assets/modules/humanizer → humanizer}/LICENSE +0 -0
- /package/skills/using-vvicat-ai-short-studio-cli/references/{hypit/playbooks/craft → short-drama/prompt}/examples/h3-base-prompt-writing.md +0 -0
- /package/skills/using-vvicat-ai-short-studio-cli/references/{hypit/playbooks/craft → short-drama/prompt}/examples/h3-reference-prompt-writing.md +0 -0
package/skills/using-vvicat-ai-short-studio-cli/references/hypit/production/video-downloads.md
DELETED
|
@@ -1,47 +0,0 @@
|
|
|
1
|
-
# Downloading a video from a link
|
|
2
|
-
|
|
3
|
-
Read this when a reference or source clip lives on a video page. `hypit media fetch` saves the
|
|
4
|
-
video as a project file through yt-dlp. For a website's interface, scroll or interaction, use
|
|
5
|
-
[browser capture](browser-capture.md).
|
|
6
|
-
|
|
7
|
-
## Save the source video
|
|
8
|
-
|
|
9
|
-
```bash
|
|
10
|
-
hypit media fetch "https://example.com/watch?v=VIDEO_ID" \
|
|
11
|
-
--to references/ad/source.mp4
|
|
12
|
-
```
|
|
13
|
-
|
|
14
|
-
Replace the example URL with the actual video link. Quote it so URL punctuation stays part of the
|
|
15
|
-
argument. The destination is relative to the current directory; the CLI creates parent directories
|
|
16
|
-
and requires a new output path. `--json` reports the saved path, source URL, duration, dimensions,
|
|
17
|
-
frame rate and audio presence.
|
|
18
|
-
|
|
19
|
-
The command fetches one video, including its audio when available, even when the link also belongs
|
|
20
|
-
to a playlist. It prefers H.264 and a resolution near 1080p; the source's available formats determine
|
|
21
|
-
the result. Destinations can use `.mp4`, `.mkv`, `.webm` or `.mov`. Downloading retains source timing;
|
|
22
|
-
it is separate from preparing material for a production's frame clock.
|
|
23
|
-
|
|
24
|
-
## Prepare the downloader
|
|
25
|
-
|
|
26
|
-
Run `hypit media prepare-fetch` explicitly before the first fetch. It uses uv to prepare the
|
|
27
|
-
Distribution's locked downloader and JavaScript solver, then reports the executable path. Reuse that
|
|
28
|
-
environment for subsequent downloads. `media fetch` never installs dependencies, updates tools or
|
|
29
|
-
acquires remote components; a missing environment reports the preparation command. `ffmpeg` merges separate picture and sound streams, and `ffprobe` reads the
|
|
30
|
-
saved file. [Local tools](../environment/local-tools.md#supply-host-executables-at-machine-scope)
|
|
31
|
-
covers these executables on macOS, Windows and Linux. The command runs directly, without a Runtime
|
|
32
|
-
Profile, model credential or Build.
|
|
33
|
-
|
|
34
|
-
Supported sites and access requirements depend on yt-dlp and the source site. A failed download
|
|
35
|
-
includes the downloader's error. When a site needs additional download options, the installed
|
|
36
|
-
`services/yt-dlp/README.md` explains direct use of the packaged tool; the site's own download or
|
|
37
|
-
export can also supply the same local file.
|
|
38
|
-
|
|
39
|
-
## Continue from the saved file
|
|
40
|
-
|
|
41
|
-
Keep the source URL and local path in the reference notes. Use the file for
|
|
42
|
-
[reference understanding](../creation/reference-video.md): transcription, timed frames and grids all
|
|
43
|
-
refer to that same source clock. Reuse the saved file when returning to the reference.
|
|
44
|
-
|
|
45
|
-
When the downloaded clip becomes material in the new video, declare it as `media:Video` and follow
|
|
46
|
-
[media preparation](media.md). The composition then places the prepared material against the
|
|
47
|
-
target's events.
|
|
@@ -1,119 +0,0 @@
|
|
|
1
|
-
# Choosing and extending author vocabulary
|
|
2
|
-
|
|
3
|
-
Read this when deciding which installed Surface should express a Treatment role, or whether the
|
|
4
|
-
production needs a new project Author Package.
|
|
5
|
-
|
|
6
|
-
## Search from the role
|
|
7
|
-
|
|
8
|
-
Name what the element must do in the work before choosing its implementation. Useful questions are:
|
|
9
|
-
|
|
10
|
-
- What does the viewer perceive, and why is it present?
|
|
11
|
-
- Is it Caption, independent Typography, A-roll, B-roll, MG, UI, Effect, Audio, or a new role?
|
|
12
|
-
- What does it consume and publish?
|
|
13
|
-
- Does it follow a Script Selection, a Moment, an explicit time span, or another component state?
|
|
14
|
-
- What changes over time, and what stays visually persistent?
|
|
15
|
-
- Which choices need author inputs, and which design can stay specific to this piece?
|
|
16
|
-
|
|
17
|
-
Query the likely package owners:
|
|
18
|
-
|
|
19
|
-
```bash
|
|
20
|
-
hypit vocabulary
|
|
21
|
-
hypit vocabulary @hypit/caption-fine
|
|
22
|
-
hypit vocabulary @hypit/media-pipeline --tag StillVideo
|
|
23
|
-
hypit vocabulary --visual text
|
|
24
|
-
```
|
|
25
|
-
|
|
26
|
-
Use a focused package and tag query before the first use of an unfamiliar Surface in the current
|
|
27
|
-
production. Query it again when the selected package or Distribution changes, or when `hypit check`
|
|
28
|
-
shows that an assumed declaration is not the installed one. Once the declaration is established in
|
|
29
|
-
the current context, ordinary edits do not require repeating the same query.
|
|
30
|
-
|
|
31
|
-
With no package argument, the command lists every package visible to the current Distribution and
|
|
32
|
-
project together with its tags and models. Use that inventory when the role is clear but the owner is
|
|
33
|
-
not. A focused package query then reports Surface attributes, children, ports, examples, and designed
|
|
34
|
-
previews, including the logical Module import when one physical package contributes several Modules.
|
|
35
|
-
The package README supplies exact behavior that is local to that installed implementation.
|
|
36
|
-
When the question requires more detail, inspect the relevant implementation and exported API. An
|
|
37
|
-
existing component can also provide a useful implementation example for a new project package.
|
|
38
|
-
|
|
39
|
-
Run Fragment libraries have a separate interface. A package can provide
|
|
40
|
-
Candidates while declaring no Markup Surfaces. Read [Runs](runs.md) and the library's
|
|
41
|
-
package-local Fragment documentation for those inputs and exports.
|
|
42
|
-
|
|
43
|
-
## Connect model references as typed inputs
|
|
44
|
-
|
|
45
|
-
Read the model Surface's reference roles and per-input metadata as well as its prompt parameters.
|
|
46
|
-
The prompt gives direction; the actual edges supply media and the declared facts needed to use it.
|
|
47
|
-
Seedance requires `person-reference="true|false"` on every image/video reference: true if the supplied
|
|
48
|
-
material contains a person, false otherwise. Audio must omit it. Its installed README owns the required
|
|
49
|
-
first/last-frame forms. The
|
|
50
|
-
[Provider](../environment/model-and-provider.md) translates these facts into the selected service's
|
|
51
|
-
media preparation without adding service instructions to the creative prompt.
|
|
52
|
-
|
|
53
|
-
## Choose a component for its behavior
|
|
54
|
-
|
|
55
|
-
An installed Surface fits when its semantic role, inputs and outputs, temporal behavior, composition
|
|
56
|
-
ownership, and visual range match the intended work. Parameter differences such as words, colors,
|
|
57
|
-
spacing, or ordinary media inputs belong to authored configuration when the Surface already exposes
|
|
58
|
-
them.
|
|
59
|
-
|
|
60
|
-
A catalogue preview helps identify the component's visual role. Its declared inputs and behavior
|
|
61
|
-
show what can be adapted; its configured appearance in Studio shows how it serves this production.
|
|
62
|
-
|
|
63
|
-
Record the creative role in Treatment and express the implementation choice through Source imports
|
|
64
|
-
and elements. Those two places contain the useful reason and the exact choice.
|
|
65
|
-
|
|
66
|
-
## Create a project component as normal production work
|
|
67
|
-
|
|
68
|
-
When the work introduces a new visual role, structure, state change, interaction, or crafted behavior,
|
|
69
|
-
create a project Author Package under the project's `packages/`. This is a normal part of making a
|
|
70
|
-
video. Do not patch Hypit Core, the CLI, or an installed Distribution package to implement one video's
|
|
71
|
-
component. Author the behavior in the video's project package and select it through normal imports.
|
|
72
|
-
|
|
73
|
-
Keep the boundary useful:
|
|
74
|
-
|
|
75
|
-
- the package owns rendering behavior, fixed design, input shapes, defaults and the vocabulary that
|
|
76
|
-
explains them, whether used once or reused;
|
|
77
|
-
- Source and Recipe connect supplied content, assets and semantic timing, and own the choices exposed
|
|
78
|
-
by the component;
|
|
79
|
-
- Runtime Profiles own external execution and credentials;
|
|
80
|
-
- Provider packages implement media tools and external services.
|
|
81
|
-
|
|
82
|
-
Read the installed `@hypit/hypit/author-kit` README for the public package boundary and a relevant component
|
|
83
|
-
for an implementation example. Give the new package its own Module identity and use the project
|
|
84
|
-
owner's scope; the selected Distribution owns the reserved `@hypit/*` namespace.
|
|
85
|
-
|
|
86
|
-
TypeScript imports use public SDK paths such as `@hypit/hypit/author-kit`, `@hypit/hypit/composition`,
|
|
87
|
-
`@hypit/hypit/text`, `@hypit/hypit/caption` or `@hypit/hypit/studio-adapter`. Source imports instead name logical Modules,
|
|
88
|
-
such as `@hypit/caption@1`. When learning from installed official source, translate its internal
|
|
89
|
-
workspace imports to the corresponding public SDK paths in the project package.
|
|
90
|
-
|
|
91
|
-
Describe the Surface's role, attributes and outputs with a small valid example so a future author
|
|
92
|
-
can select it. A visual preview makes its appearance recognizable; Studio shows the actual
|
|
93
|
-
configuration used in a production.
|
|
94
|
-
|
|
95
|
-
For existing Track composition, read [Tracks](tracks.md). For a new Track,
|
|
96
|
-
[Component design](component-design.md) shapes its visual idea, semantic behavior and useful controls.
|
|
97
|
-
[Track authoring](track-authoring.md) explains temporal inputs, spatial ownership, persistent
|
|
98
|
-
state, preset content and peer visual/audio outputs. [Caption authoring](caption-authoring.md) covers
|
|
99
|
-
a new speech-text family without rebuilding its transcript or timing.
|
|
100
|
-
|
|
101
|
-
[Studio and Companions](studio.md) covers timeline presentation and Inspector editing for the new
|
|
102
|
-
component.
|
|
103
|
-
|
|
104
|
-
[Component visuals](component-visuals.md) explains the actual Track and element representation,
|
|
105
|
-
with a drawing example. [System relationships](system.md) places it in the complete production.
|
|
106
|
-
|
|
107
|
-
## Let ordinary package management own distribution
|
|
108
|
-
|
|
109
|
-
The project's package manager installs and versions components. Hypit loads only packages selected
|
|
110
|
-
by Source or Run imports and their declared dependencies. Project packages resolve from the project;
|
|
111
|
-
reserved `@hypit/*` packages come from the selected Distribution. It does not scan the dependency
|
|
112
|
-
tree for possible components.
|
|
113
|
-
|
|
114
|
-
Keep a new component project-local while it serves this work. If its owner later wants to use it
|
|
115
|
-
across projects, send a versioned tarball or publish an npm/private-registry release and pin it in the
|
|
116
|
-
consumer project's `package.json` and lockfile. Sharing changes where the same package is installed;
|
|
117
|
-
it does not change the component model or require a Hypit-specific registry.
|
|
118
|
-
|
|
119
|
-
[Sharing a project package](component-sharing.md) owns the packaging, identity and upgrade details.
|
|
@@ -1,11 +0,0 @@
|
|
|
1
|
-
# 可扩展画风
|
|
2
|
-
|
|
3
|
-
`art-styles.json` 是 Dashboard 的内置画风目录。每个数组元素都是一个画风对象,至少需要包含:
|
|
4
|
-
|
|
5
|
-
- `id`、`name`、`description`、`prompt`
|
|
6
|
-
- `visualBible.version`(必须为 `1`)
|
|
7
|
-
- `visualBible.palette`、`baseline`、`lighting`、`narrative_arc`、`motion_language`、`negative_constraints`
|
|
8
|
-
|
|
9
|
-
复制一个现有对象修改即可新增画风。保存后重启 Dashboard,新的画风会出现在「生成配置」中;画风内容会原样写入项目的 `creative.art_style`。
|
|
10
|
-
|
|
11
|
-
通过插件生成并确认的自定义画风,会自动追加到统一工作区根目录下的 `art-styles.custom.json`,下次启动自动与系统画风合并。也可用环境变量 `SHORT_DRAMA_CUSTOM_ART_STYLES_FILE` 指定自定义库路径。
|
|
@@ -1,12 +0,0 @@
|
|
|
1
|
-
# Comfly Provider 合同
|
|
2
|
-
|
|
3
|
-
> 历史合同,仅用于读取旧任务与审计证据。短剧插件当前禁止直连 Comfly;需要 1194/1776 预处理时使用原生 Hypit 的 StarRouter 路线。以下凭据、接口和 Litterbox 步骤不得用于新制作。
|
|
4
|
-
|
|
5
|
-
插件迁移现项目的 Comfly MiniMax H3 视频适配器,使用 `COMFLY_TOKEN`、可选 `COMFLY_BASE_URL`(默认 `https://vvicat-comfly-prod.vvicat.dev`)和可选非负整数 `COMFLY_APP_ID`。
|
|
6
|
-
|
|
7
|
-
- 模型固定为 `minimax-h3`,`prompt_profile=h3`、`input_mode=Ref2VA`,时长为 5–15 秒整数;不静默钳制或取整。
|
|
8
|
-
- 图片输入为 1–3 张:无自定义尺寸时对应工作流 1518/1519/1520;指定 `720p|1K|2K` 与 `16:9|9:16` 时对应 1540/1541/1542。
|
|
9
|
-
- 视频输入最多 1 段,对应工作流 1521;视频与图片互斥,不支持参考音频。
|
|
10
|
-
- 提交路径为 `/internal/comfly/tasks?model=comfyui&type=<workflow>`,查询路径为 `/internal/comfly/tasks/<task-id>`。
|
|
11
|
-
|
|
12
|
-
Comfly 当前合同只接受可公开读取的 HTTPS 参考地址,不直接读取本地文件。上传参考素材会改变外部状态;可路由 `publish-drama-references` 使用用户确认的 Litterbox 临时公开图,也可使用用户指定的其他存储。必须确认权利、公开风险、用途许可和到期时间后再传 URL;成片输出仍须立即下载到本地资产账本。不得把 `COMFLY_TOKEN` 写入项目、请求快照或 provenance。
|
|
@@ -1,23 +0,0 @@
|
|
|
1
|
-
# Seedance 社区 Skill 参考
|
|
2
|
-
|
|
3
|
-
参考 [Emily2040/seedance-2.0 的 skills 目录](https://github.com/Emily2040/seedance-2.0/tree/main/skills)(查看提交 `4668457e560eee06e95d7fcfdf441c8c0bba802e`)。这些是社区编写经验,不是本项目接入模型的能力声明;实际素材数量、时间语法、时长和提示词上限以当前模型路由与 Provider 能力为准。
|
|
4
|
-
|
|
5
|
-
## Agent 逐镜写入时采用的检查
|
|
6
|
-
|
|
7
|
-
1. 从已选分镜、参考图、审核和声音版本确定**本镜**任务。多人镜先用内部镜头表写出机位一侧、站位/朝向、视线、主动作、其他人的持续行为、持物手、光线和镜尾状态;缺项先核实,不把表格原样塞入成品。参考 [prompt](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-prompt/SKILL.md)、[characters](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-characters/SKILL.md)。
|
|
8
|
-
2. 为每个实际上传的素材标明用途:人物身份、当前画面/分镜、首帧、运动、音频节拍等。`@` 编号必须与提交顺序一致;不要让一张图同时无条件控制身份、动作和场景,也不要编造素材。参考 [prompt](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-prompt/SKILL.md)。
|
|
9
|
-
3. 主动作写成起势、接触或变化、物理后果、收势;道具写清哪只手及交接后的归属。听者和其他可见人物在同一时间段有由主动作触发的注意与反应,幅度服从景别和角色,避免轮流冻结或无理由同步运动。参考 [motion](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-motion/SKILL.md)、[characters](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-characters/SKILL.md)。
|
|
10
|
-
4. 镜头运动写起点、方向和终点;对白写说话人及逐字台词,核对脸部可见性、听者反应与声音策略。若原生口型重要,避免同一句里同时要求大幅转头和复杂运镜。参考 [camera](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-camera/SKILL.md)、[audio](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-audio/SKILL.md)。
|
|
11
|
-
5. 只编译当前镜头的身份、素材用途、动作、声音、连续性和镜尾;删除重复画质词及参考图已经表达的静态背景。Seedance 不套社区经验字数阈值;H3 仍按本项目最终提交文本 7000 字符限制校验。参考 [antislop](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-antislop/SKILL.md)、[prompt-short](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-prompt-short/SKILL.md)。
|
|
12
|
-
6. 返工时先记录画面中实际失败的动作、口型、道具或连续性,再改一个主要变量;续镜以**已验收视频的实际镜尾**为准,不能把计划镜尾当成已发生事实。参考 [troubleshoot](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-troubleshoot/SKILL.md)、[continuation](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-continuation/SKILL.md)。
|
|
13
|
-
|
|
14
|
-
## 按问题查阅上游 Skill
|
|
15
|
-
|
|
16
|
-
| 问题 | 社区 Skill |
|
|
17
|
-
| --- | --- |
|
|
18
|
-
| 剧情与多镜规划 | [interview](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-interview/SKILL.md)、[interview-short](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-interview-short/SKILL.md)、[sequence](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-sequence/SKILL.md)、[recipes](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-recipes/SKILL.md) |
|
|
19
|
-
| 画面与运动 | [style](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-style/SKILL.md)、[lighting](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-lighting/SKILL.md)、[vfx](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-vfx/SKILL.md) |
|
|
20
|
-
| 平台、交付与问题定位 | [pipeline](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-pipeline/SKILL.md)、[troubleshoot](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-troubleshoot/SKILL.md)、[filter](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-filter/SKILL.md)、[copyright](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-copyright/SKILL.md) |
|
|
21
|
-
| 中文范例与用词 | [examples-zh](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-examples-zh/SKILL.md)、[vocab-zh](https://github.com/Emily2040/seedance-2.0/blob/main/skills/seedance-vocab-zh/SKILL.md);其他语言参见上游目录中的 `examples-ja/ko` 与 `vocab-en/es/ja/ko/ru` |
|
|
22
|
-
|
|
23
|
-
采用上游的检查方法时,以本项目的已选素材、审核、Provider 能力和提示词选版为准。社区 Skill 提到的具体镜头数量、绝对时间标记或平台参数不能直接写成本项目硬规则。
|
|
@@ -1,5 +0,0 @@
|
|
|
1
|
-
# 临时发布短剧参考素材
|
|
2
|
-
|
|
3
|
-
此旧路径保留供已有 Skill 引用;当前唯一支持的临时托管服务是 TempFile.org。只发布项目内当前 selected 且未失效的图片、视频或音频版本,发布前确认素材权利、公开暴露、使用范围和服务条款。默认有效期为 24 小时,先查询并复用同一资产版本的有效收据;强制重传需要重新确认。
|
|
4
|
-
|
|
5
|
-
临时 URL 只用于 StarRouter 所需的公网参考,不是最终交付资产。项目账本保留素材哈希、资产版本、服务名称、URL 和到期时间,不写入凭据。旧 Litterbox 收据不能用于新请求,过期或服务不匹配时重新走 TempFile.org 发布门禁。
|
package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/runninghub-provider.md
DELETED
|
@@ -1,33 +0,0 @@
|
|
|
1
|
-
# RunningHub Provider 合同
|
|
2
|
-
|
|
3
|
-
> 历史合同,仅用于读取旧任务与审计证据。短剧插件当前禁止 RunningHub 提交;下述工作流、环境变量、冒烟命令和确认步骤不得用于新制作。
|
|
4
|
-
|
|
5
|
-
RunningHub 既支持用户自己的通用工作流,也内置迁移自现项目的 Krea2 图片、MiniMax H3 视频和 SeedVR2.5 视频超分工作流:
|
|
6
|
-
|
|
7
|
-
- 环境变量:`RUNNINGHUB_API_KEY`、可选 `RUNNINGHUB_BASE_URL`,以及通用工作流的 `RUNNINGHUB_IMAGE_WORKFLOW_ID`、`RUNNINGHUB_VIDEO_WORKFLOW_ID`、`RUNNINGHUB_AUDIO_WORKFLOW_ID`。Krea2 默认工作流 ID 为 `2096515700701929473`,可用 `RUNNINGHUB_KREA2_WORKFLOW_ID` 覆盖;H3 默认平台工作流 ID 为 `2086743729407733762`,可用 `RUNNINGHUB_H3_WORKFLOW_ID` 覆盖。
|
|
8
|
-
- 本地参考素材先上传到 `/openapi/v2/media/upload/binary`。
|
|
9
|
-
- 任务提交到 `/task/openapi/create`,查询使用 `/openapi/v2/query`。
|
|
10
|
-
- 同一 API Key 的图片、视频和音频提交共用 2 个并发槽位;超出的请求在适配器内等待,任务查询不占用提交槽位。
|
|
11
|
-
- `node_info_list` 由工作流定义决定;字段值可使用 `@prompt` 和 `@asset:0`、`@asset:1` 等占位,提交前由适配器替换。
|
|
12
|
-
|
|
13
|
-
内置视频超分使用 `operation=video-upscale`、`model=seedvr2.5-video-upscale`,工作流固定为 `2099866760106491906`,不接受环境变量替换或手写 `node_info_list`。仓库映射来自 RunningHub 官方 `getJsonApiFormat` 导出,输入固定为节点 `25` 的 `video` 字段,输出固定为节点 `27` 的 `VHS_VideoCombine`;适配器只上传当前 selected 视频并覆盖这一项,禁止空节点试错或借用其他 SeedVR 工作流。该命名能力只列入 transform 目录,不列入普通视频生成模型。
|
|
14
|
-
|
|
15
|
-
超分完成后先保留 Provider 原始输出,再检查时长和帧率是否与来源一致;工作流映射未声明会改变这两项,因此漂移会被拒绝。若来源有音轨而 Provider 输出缺失,回写器以视频流复制和源音频 AAC 封装生成最终候选,并在 provenance 中同时记录原始输出版本/哈希和源音轨版本/哈希。候选仍不自动选中:必须做结构化 QC、完整观看并覆盖 `resolution,duration_fps,audio_preservation,faces_hands_text,motion_artifacts,color_crop` 六项专项观察。
|
|
16
|
-
|
|
17
|
-
真实冒烟先运行不带 `--confirmed` 的摘要命令:
|
|
18
|
-
|
|
19
|
-
```bash
|
|
20
|
-
node scripts/generation/live-smoke-test.mjs runninghub seedvr2.5-video-upscale "$SEEDVR25_PROJECT_ROOT" "$SEEDVR25_ASSET_KEY" "$SEEDVR25_VERSION_ID"
|
|
21
|
-
```
|
|
22
|
-
|
|
23
|
-
摘要会列出 selected 资产、SHA-256、时长、分辨率、帧率、音轨、上传事实、固定工作流和节点覆盖,不计算具体价格。只有用户针对这份制作计划再次确认后才追加 `--confirmed`,随后轮询同一个任务 ID,禁止失败后静默重提。
|
|
24
|
-
|
|
25
|
-
内置 H3 使用 `model=minimax-h3-reference-to-video`,不要求 `node_info_list`。本地 `reference_image_paths`、`reference_video_paths`、`reference_audio_paths` 会依次上传并注入内置 ComfyUI workflow;图片 0–9 张、视频 0–2 段、音频 0–2 段,纯文本零媒体也可用。Hypit 原生 Runtime 的有效时长不得低于 5 秒,画幅为 `16:9|9:16`,模型分辨率严格使用 `768P|2K`,不得把旧 MCP 的 `480p|720p|1K` 配置静默折算。工作流同时生成视频与原生音频。
|
|
26
|
-
|
|
27
|
-
内置图片使用 `model=krea2-normal-v1`,不要求 `node_info_list`。适配器把 prompt 注入节点 5,并按 `resolution=1K|2K` 与 `aspect_ratio=1:1|16:9|9:16|3:4|4:3|2:3|3:2` 设置节点 8;当前普通工作流不接受参考图。
|
|
28
|
-
|
|
29
|
-
选择 RunningHub 前,用户必须确认工作流 ID、覆盖节点、参考文件、请求数量和输出模态;门禁不计算具体价格。视频还必须传入已选 `prompt_version`、prompt_profile、input_mode 和 reference_manifest;MiniMax H3 工作流必须使用 `h3` 及其真实 T2VA/I2VA/FL2VA/L2VA/Ref2VA 模式。T2VA 不带素材,I2VA/FL2VA/L2VA 分别绑定首帧、首尾帧、尾帧,Ref2VA 使用与类型一致的 `reference_image/reference_video/reference_audio`;适配器会在上传前核对数量、顺序和角色。插件不猜测节点 ID,也不把某个工作流的 schema 当成通用协议。查询任务时显式传 `media_type`,返回统一 `outputs[]`;全部远程输出仍必须下载进本地资产库。
|
|
30
|
-
|
|
31
|
-
通用图片工作流使用 `reference_paths` 时还必须提交等长 `reference_manifest`,逐项绑定本地 selected 图片版本和用途;清单只用于本地审计,不注入 RunningHub 节点。
|
|
32
|
-
|
|
33
|
-
通用对口型工作流若没有独立的时间范围节点,`submit_media_operation` 只从 selected 源镜头抽取台词前后约半秒的上下文窗口,避免 1080p 长镜头在 PainterAV2V 采样阶段耗尽显存。窗口扩展到 4 帧栅格,并额外补一个克隆尾帧,使工作流丢弃尾帧后的帧数可被 4 整除;插件只在 `.short-drama/provider-input` 创建 CFR 派生副本,不覆盖账本源资产。已审核 selected 配音以前导静音对齐窗口内台词起点并补尾到 Provider 输入时长。远端返回后,回写器校验分辨率、帧率和最小帧数,按精确帧号把窗口拼回完整 selected 源镜头并保留源音轨;Provider 原始窗口与最终整镜候选分别留证。请求快照和输出 provenance 必须记录 `provider_video_preparation`、`provider_audio_preparation` 与 `output_processing`,专项审核仍要完整观看范围内外、口腔伪影、身份和时长。
|
package/skills/using-vvicat-ai-short-studio-cli/references/short-drama/starrouter-provider.md
DELETED
|
@@ -1,53 +0,0 @@
|
|
|
1
|
-
# StarRouter Provider 合同
|
|
2
|
-
|
|
3
|
-
短剧插件的新制作统一使用 Hypit Runtime 的 StarRouter 配置与 Credential Store;以下适配器细节保留作兼容实现说明,不应单独配置另一套厂商路由。
|
|
4
|
-
|
|
5
|
-
插件通过独立适配器直接访问 StarRouter,不导入任何业务应用代码:
|
|
6
|
-
|
|
7
|
-
- 图片:`/v1/images/generations`;有本地参考图时使用 multipart `/v1/images/edits`。支持 `1K/2K/4K + aspect_ratio` 尺寸推导和常用输出参数。
|
|
8
|
-
- 视频:Seedance 使用 `/volcengine/doubao/contents/generations/tasks`;MiniMax H3/H3-Max 使用 OpenAI 兼容 `/v1/videos`,并通过 `/v1/videos/{task_id}` 查询。适配器按模型选择协议。
|
|
9
|
-
- 语音:同步 `POST /v1/audio/speech`,支持 `speech-2.8-hd`、`speech-2.8-turbo`、Qwen3 TTS、PawSense 与 `tts-1`;通用模型的 `instructions` 和 `metadata` 原样转发,当前 MCP 不缓冲 SSE 流式结果。
|
|
10
|
-
- 语音识别:同步 multipart `POST /v1/audio/transcriptions` 或 `/v1/audio/translations`;默认使用已验证可用的 `whisper-1`。`qwen3-asr-flash` 已从默认目录移除并禁用,其 transcription/translation 实测均返回上游 404。词级或分段时间戳必须使用 `response_format=verbose_json`,`timestamp_granularities` 只接受 `word|segment` 并按 multipart 同名重复字段发送;未知粒度和其他响应格式在请求前拒绝。
|
|
11
|
-
- 音乐:`POST /suno/submit/MUSIC` 提交 `suno_music`,`GET /suno/fetch/{task_id}` 轮询;生成结果作为 audio 资产保存。
|
|
12
|
-
- 认证:优先使用 Hypit Runtime 指定的 Credential Store;旧适配器仍支持从 `STARROUTER_API_KEY` 读取 Bearer Token。
|
|
13
|
-
- 保底目录:图片 `gpt-image-2`,视频为适配器登记的 Seedance 系列及 `MiniMax-H3`、`MiniMax-H3-Max`,语音和 ASR 为上述模型,音乐为 `suno_music`。可分别用 `STARROUTER_IMAGE_MODELS`、`STARROUTER_VIDEO_MODELS`、`STARROUTER_AUDIO_MODELS`、`STARROUTER_ASR_MODELS`、`STARROUTER_MUSIC_MODELS` 和 `STARROUTER_MULTIMODAL_VIDEO_MODELS` 提供逗号分隔目录;自定义模型仍需补能力合同。
|
|
14
|
-
|
|
15
|
-
## Suno 音乐合同
|
|
16
|
-
|
|
17
|
-
`generate_music` 使用系统模型键 `starrouter::suno_music`。提交到 `POST /suno/submit/MUSIC` 的 JSON 为 `prompt`、可选 `title`、`tags`、`lyrics` 与 `make_instrumental`;StarRouter 当前不读取请求体的 `model`,由 `/MUSIC` 路径映射系统模型 `suno_music`。`prompt` 必填,`lyrics` 与 `make_instrumental: true` 不能同时提交。远端返回的公开 task id 会编码为本地 `SUNO:MUSIC:b64_<providerConfigId>:<task_id>`,查询使用 `GET /suno/fetch/{task_id}`,并由 externalId 中的 provider 配置找回账号和密钥;只提取 `audio_url`、`audioUrl`、`stream_audio_url` 或 `streamAudioUrl`,避免把封面、MV 视频或其他媒体误登记为音频。
|
|
18
|
-
|
|
19
|
-
## MiniMax H3/H3-Max 视频合同
|
|
20
|
-
|
|
21
|
-
两者固定使用 `prompt_profile=h3`,输入模式枚举为 `T2VA`、`I2VA`、`FL2VA`、`L2VA`、`Ref2VA`,画幅为 `21:9`、`16:9`、`4:3`、`1:1`、`3:4`、`9:16`。`MiniMax-H3` 支持 `768P/2K`、4–15 秒及参考图/视频/音频;`MiniMax-H3-Max` 支持 `480P/768P`、5–15 秒,不接受参考素材或 Ref2VA。
|
|
22
|
-
|
|
23
|
-
`images` 最多两张,依次是 `first_frame`、`last_frame`;`input_reference` 仅在 `images` 为空时作为首帧。参考内容使用 `metadata.content`,元素类型只能是 `text`、`image_url`、`video_url`、`audio_url`,素材角色只能是 `first_frame`、`last_frame`、`reference_image`、`reference_video`、`reference_audio`。每个请求至少含一个非空 text;Hypit Runtime 的 Ref2VA 可把一个 `first_frame` 连续性锚点与完整参考素材同时提交。
|
|
24
|
-
|
|
25
|
-
`metadata` 仅接受 `model`、`content`、`resolution`、`duration`、`ratio`、`callback_url`;适配器要求 `metadata.model` 与顶层模型一致,回调地址和所有素材必须是公网 HTTPS。公开任务状态 `queued/in_progress/completed/failed` 被统一归一化为 pending/completed/failed,完成地址从响应(包括 `metadata.url`)提取。
|
|
26
|
-
|
|
27
|
-
## 同步语音合同
|
|
28
|
-
|
|
29
|
-
`generate_audio` 对 StarRouter 使用 `model`、`input`、`voice`,可选 `instructions`、`speed`、`response_format` 和 `metadata`。`voice` 必须是用户已确认且有权使用的模型声音 ID;`speed` 为 0.5–2;格式支持 `mp3`、`pcm`、`flac`。
|
|
30
|
-
|
|
31
|
-
`speech-2.8-*` 继续严格校验 MiniMax 的 `voice_setting`、`audio_setting`、`pronunciation_dict`、`timbre_weights`、`language_boost`、`voice_modify`、`subtitle_enable`、`aigc_watermark`、`output_format`、`stream`、`stream_options`。其余 OpenAI 兼容模型原样转发 `instructions` 与 metadata。当前 MCP 返回完整文件,明确拒绝 `stream_format`,避免把 SSE 事件流误登记成音频。
|
|
32
|
-
|
|
33
|
-
上述字段透传能力不等于完整情感配音合同能力。当前已验证的 MiniMax `speech-2.8-*` 只能表达单一情绪枚举和部分声学参数,不能可靠承载意图、潜台词、情绪强度、重音、停连、呼吸及空间关系;`tts-1` 不支持 `instructions`。因此二者在 `compile_dubbing_request` 中都对完整逐句表演合同失败关闭,不会静默降级。旧 CosyVoice 与 RunningHub 工作流不能用于新制作;若当前 StarRouter 能力无法满足完整合同,应明确阻塞。
|
|
34
|
-
|
|
35
|
-
`emotion` 与 `language_boost` 按非空字符串透传:Skill 只列已验证常用值,不把上游可能扩展的值固化为封闭枚举;范围错误由 StarRouter/MiniMax 返回。
|
|
36
|
-
|
|
37
|
-
StarRouter 返回的二进制音频会统一转为 `outputs[0].b64_json` 数据 URI,并保留 `media_type=audio`、Content-Type 和格式。立即用 `asset-ledger.mjs decode` 保存到 `assets/audio/<asset-key>/v001.<ext>`;项目账本只保存生成来源和参数,不保存 Key。
|
|
38
|
-
|
|
39
|
-
附件同时描述了异步 `/v1/t2a_async_v2`,但其最终产物是 TAR 而非可直接剪辑的音频文件。本插件当前不把 TAR 暴露为音频资产;需要长文本异步合成时,应先增加安全解包、逐文件校验和音频版本登记,再开放该模式。
|
|
40
|
-
|
|
41
|
-
## 本地资产约束
|
|
42
|
-
|
|
43
|
-
所有生成工具要求 `confirmed: true`。本地参考文件必须已落入当前项目 `assets/`,插件会在请求前通过真实路径校验,拒绝项目外文件和符号链接逃逸。视频公网参考只接受已授权的 HTTPS 地址;仅当用户另外调用 `publish-drama-references` 并确认第三方公开上传时,插件才会把本地选版图片临时发布到 TempFile.org,生成调用本身不会隐式发布。
|
|
44
|
-
|
|
45
|
-
Seedance 2.0 视频必须同时提交 `prompt_profile=seedance2`、`input_mode`、本地 `prompt_version` 和 `reference_manifest`。清单按图片、视频、音频各自从 1 连续编号,并与 URL 数组及提示词中的 `@图片N/@视频N/@音频N` 同序;适配器在付费请求前校验 4–15 秒目标时长、图片最多 9 个、视频最多 3 个、音频最多 3 个、总参考最多 12 个、音视频参考总时长、用途和真实人物脸部禁用声明。
|
|
46
|
-
|
|
47
|
-
图片、视频或语音结果统一返回 `outputs[]`;每项包含 `media_type` 以及 `url` 或 `b64_json`。立即用 `asset-ledger.mjs fetch|decode` 下载并登记哈希;远程结果不视为资产,落盘前任务保持未完成。文本资产由 Codex 直接创作,不经过本适配器。
|
|
48
|
-
|
|
49
|
-
图片生成始终提交 `reference_manifest`;无参考图时为 `[]`,有参考图时必须与 `reference_paths` 等长,并按顺序记录 `type=image`、资产 key、selected 版本和用途。该清单只进入本地请求快照和 provenance,不发送给 StarRouter。
|
|
50
|
-
|
|
51
|
-
## 扩展规则
|
|
52
|
-
|
|
53
|
-
新制作的厂商与模型选择以 Hypit Runtime 为准;旧适配器注册表只用于保留兼容代码和历史证据读取,不能绕过 Runtime 审批门禁。
|
|
@@ -1,10 +0,0 @@
|
|
|
1
|
-
# 视频模型路由
|
|
2
|
-
|
|
3
|
-
1. 模型合同优先于 LibTV 风格偏好。
|
|
4
|
-
2. MiniMax H3 使用 H3 的 Ref2VA 六段字段、稳定主体标签、说话者 ID 和原生音频合同。
|
|
5
|
-
3. Seedance 使用 `seedance2_video` 的中文 `full-reference` 结构、真实素材顺序和实时素材限制。
|
|
6
|
-
4. 未确认模型协议时停止,不把通用文本冒充平台专用提示词。
|
|
7
|
-
|
|
8
|
-
音色绑定后,角色长期档案保留 `voice_identity`。模型支持参考音频时,把已选全局音色作为 `audio_reference`;H3 仍使用原生音频,不运行外部 TTS 覆盖。模型不支持参考音频时只写稳定声线描述,并在结果中保留能力限制。
|
|
9
|
-
|
|
10
|
-
H3 与 Seedance 不得混用字段或引用语法。最终编译前必须读取实时节点 schema、项目有效 `artStyle`、画幅、时长和音频能力。
|
|
@@ -1,32 +0,0 @@
|
|
|
1
|
-
# 项目通用视频提示词规范
|
|
2
|
-
|
|
3
|
-
LibTV 语料只用于提炼可执行的内容维度,不直接复制其占位符或平台字段。先写平台中立的镜头事实,再由 H3 或 Seedance 编译器生成最终提示词。
|
|
4
|
-
|
|
5
|
-
## 必写维度
|
|
6
|
-
|
|
7
|
-
- 主体身份和每个参考素材的用途;
|
|
8
|
-
- 起始状态、按时间排序的动作、结束状态;
|
|
9
|
-
- 人物之间的站位、视线、距离和屏幕方向;
|
|
10
|
-
- 景别、机位、构图、镜头方向和运镜;
|
|
11
|
-
- 表演、光影、材质和接触物理;
|
|
12
|
-
- 对白、旁白、环境声、动作声和音乐策略;
|
|
13
|
-
- 跨镜人物、服装、道具、伤口、光线和声音连续性;
|
|
14
|
-
- 最小必要的禁止项。
|
|
15
|
-
|
|
16
|
-
## 三档复杂度
|
|
17
|
-
|
|
18
|
-
- 单主体单动作:一个动作链、一个镜头、一个明确结果。
|
|
19
|
-
- 多主体互动:编号主体、空间关系、交接顺序、反应和镜头覆盖。
|
|
20
|
-
- 连续剧情或大场面:按镜头拆分,写时间点、运动结果、声音桥和首尾状态。
|
|
21
|
-
|
|
22
|
-
## 编译前清洗
|
|
23
|
-
|
|
24
|
-
- 解析 `{{Image N}}`、`{{Mixed N}}` 为真实资产版本和用途;未解析变量不得提交。
|
|
25
|
-
- 故事板、宫格和分镜板只作为构图与动作顺序参考,禁止生成成片中的格线、纸张、编号、字幕或 UI。
|
|
26
|
-
- 删除无法验证的质量词和互相冲突的正负约束。
|
|
27
|
-
- 一个镜头只保留一个叙事主动作;多人动作归属不清时先拆镜。
|
|
28
|
-
- `art_style` 必须来自项目当前完整画风合同,不能只传画风名称。
|
|
29
|
-
|
|
30
|
-
## 质量门禁
|
|
31
|
-
|
|
32
|
-
主体、素材用途、动作顺序、镜头可见性、空间关系、光线连续性、声音归属和平台 schema 任一缺失,都不得提交付费视频任务。
|
|
File without changes
|
|
File without changes
|