Rename segmented mode to studio; tokens are @imageN/@audioN (lowercase)
This commit is contained in:
parent
738b2e30e8
commit
0e4ab2db7c
12
README.md
12
README.md
@ -6,8 +6,8 @@ ready-to-run generation package:
|
|||||||
- `segments.txt` — N segment prompts, joined by `|`. The video creator node splits the
|
- `segments.txt` — N segment prompts, joined by `|`. The video creator node splits the
|
||||||
total length evenly across segments (`N = max(1, round(total_seconds / 10))`) and
|
total length evenly across segments (`N = max(1, round(total_seconds / 10))`) and
|
||||||
generates them one by one. Default format is full-reference (ref2va); FL2VA
|
generates them one by one. Default format is full-reference (ref2va); FL2VA
|
||||||
(first–last frame) and segmented (one `segment-N/segment.txt` file per segment with
|
(first–last frame) and studio (one `segment-N/segment.txt` file per segment with
|
||||||
`@PictureN`/`@AudioN` tokens) are opt-in alternatives.
|
`@imageN`/`@audioN` tokens) are opt-in alternatives.
|
||||||
- `Image-N.json` — one 16:9 character-sheet text-to-image prompt per character that
|
- `Image-N.json` — one 16:9 character-sheet text-to-image prompt per character that
|
||||||
has no user-provided image reference, consumed one at a time by a ComfyUI workflow.
|
has no user-provided image reference, consumed one at a time by a ComfyUI workflow.
|
||||||
- `Segment-img-N.json` — one 16:9 first-frame image prompt per segment, rendered by
|
- `Segment-img-N.json` — one 16:9 first-frame image prompt per segment, rendered by
|
||||||
@ -23,7 +23,7 @@ ready-to-run generation package:
|
|||||||
| `SKILL.md` | Skill entry point: triggers, mode selection, pipeline, output contract, validation checklist |
|
| `SKILL.md` | Skill entry point: triggers, mode selection, pipeline, output contract, validation checklist |
|
||||||
| `references/ref2va-segment-format.md` | Authoritative per-segment format for the default mode (sections, labels, shots, audio template) |
|
| `references/ref2va-segment-format.md` | Authoritative per-segment format for the default mode (sections, labels, shots, audio template) |
|
||||||
| `references/fl2va-segment-format.md` | The opt-in FL2VA first–last frame video prompt format |
|
| `references/fl2va-segment-format.md` | The opt-in FL2VA first–last frame video prompt format |
|
||||||
| `references/segmented-output-format.md` | The opt-in segmented layout: one `segment-N/segment.txt` per segment with `@PictureN`/`@AudioN` tokens, otherwise identical to ref2va |
|
| `references/studio-output-format.md` | The opt-in studio layout: one `segment-N/segment.txt` per segment with `@imageN`/`@audioN` tokens, otherwise identical to ref2va |
|
||||||
| `references/t2i-character-sheet.md` | Character-sheet caption rules (four-panel photorealistic turnaround) and the two-key JSON contract |
|
| `references/t2i-character-sheet.md` | Character-sheet caption rules (four-panel photorealistic turnaround) and the two-key JSON contract |
|
||||||
| `references/frame-image-prompts.md` | Per-segment first/last frame image prompt rules (`Segment-img-N.json`) |
|
| `references/frame-image-prompts.md` | Per-segment first/last frame image prompt rules (`Segment-img-N.json`) |
|
||||||
| `references/worked-example.md` | Complete end-to-end example, including the audio (singing) and FL2VA variants |
|
| `references/worked-example.md` | Complete end-to-end example, including the audio (singing) and FL2VA variants |
|
||||||
@ -36,12 +36,12 @@ ready-to-run generation package:
|
|||||||
2. Give the agent a vague scene prompt and the total video length in seconds, plus
|
2. Give the agent a vague scene prompt and the total video length in seconds, plus
|
||||||
optionally: song lyrics, an audio file mention (e.g. "use midnight.mp3"),
|
optionally: song lyrics, an audio file mention (e.g. "use midnight.mp3"),
|
||||||
per-character image references, style hints, and — only if wanted — an explicit
|
per-character image references, style hints, and — only if wanted — an explicit
|
||||||
request for FL2VA / first-last frame mode or segmented one-file-per-segment
|
request for FL2VA / first-last frame mode or studio one-file-per-segment
|
||||||
output with `@PictureN`/`@AudioN` references.
|
output with `@imageN`/`@audioN` references.
|
||||||
3. The agent writes `segments.txt`, `Image-N.json` for characters lacking references,
|
3. The agent writes `segments.txt`, `Image-N.json` for characters lacking references,
|
||||||
`Segment-img-N.json` (and `Segment-img-N-last.json` in FL2VA mode), and
|
`Segment-img-N.json` (and `Segment-img-N-last.json` in FL2VA mode), and
|
||||||
`image-map.txt` into the project folder.
|
`image-map.txt` into the project folder.
|
||||||
4. Verify before use: `python3 scripts/validate_outputs.py --segments segments.txt
|
4. Verify before use: `python3 scripts/validate_outputs.py --segments segments.txt
|
||||||
--expected-n <N> [--dir .] [--lyrics-file lyrics.txt]` — add
|
--expected-n <N> [--dir .] [--lyrics-file lyrics.txt]` — add
|
||||||
`--mode fl2va --total-seconds <seconds>` for FL2VA runs, or
|
`--mode fl2va --total-seconds <seconds>` for FL2VA runs, or
|
||||||
`--mode segmented --segments-dir <folder>` for segmented runs.
|
`--mode studio --segments-dir <folder>` for studio runs.
|
||||||
|
|||||||
34
SKILL.md
34
SKILL.md
@ -1,6 +1,6 @@
|
|||||||
---
|
---
|
||||||
name: mm-prompter
|
name: mm-prompter
|
||||||
description: Writes multi-segment ref2va video prompts plus T2I character-sheet prompts and per-segment first-frame image prompts from a vague scene idea and a total video length in seconds. Use when the user gives a rough video/scene concept (optionally with song lyrics or an audio file name) and wants numbered video-generation segments joined by "|", character sheets as Image-N.json for characters that lack an image reference, Segment-img-N.json frame prompts, and an image-map.txt manifest. Optional opt-in FL2VA mode adds last-frame prompts and first-last video prompts. Optional opt-in segmented mode writes one segment-N/segment.txt file per segment using @PictureN/@Audio1-style @-references instead of the joined file.
|
description: Writes multi-segment ref2va video prompts plus T2I character-sheet prompts and per-segment first-frame image prompts from a vague scene idea and a total video length in seconds. Use when the user gives a rough video/scene concept (optionally with song lyrics or an audio file name) and wants numbered video-generation segments joined by "|", character sheets as Image-N.json for characters that lack an image reference, Segment-img-N.json frame prompts, and an image-map.txt manifest. Optional opt-in FL2VA mode adds last-frame prompts and first-last video prompts. Optional opt-in studio mode writes one segment-N/segment.txt file per segment using @imageN/@audioN references instead of the joined file.
|
||||||
---
|
---
|
||||||
|
|
||||||
# MM Prompt Creator
|
# MM Prompt Creator
|
||||||
@ -10,8 +10,8 @@ generation package:
|
|||||||
|
|
||||||
1. `segments.txt` — N segment prompts, joined by `|`. The downstream video creator
|
1. `segments.txt` — N segment prompts, joined by `|`. The downstream video creator
|
||||||
node splits the total length evenly across segments and generates them one by one.
|
node splits the total length evenly across segments and generates them one by one.
|
||||||
Default format is full-reference (ref2va); FL2VA (first–last frame) and segmented
|
Default format is full-reference (ref2va); FL2VA (first–last frame) and studio
|
||||||
(one `segment-N/segment.txt` file per segment with `@PictureN`/`@AudioN` tokens)
|
(one `segment-N/segment.txt` file per segment with `@imageN`/`@audioN` tokens)
|
||||||
are opt-in alternatives (see Mode selection).
|
are opt-in alternatives (see Mode selection).
|
||||||
2. `Image-N.json` — one 16:9 character-sheet text-to-image prompt per character that has
|
2. `Image-N.json` — one 16:9 character-sheet text-to-image prompt per character that has
|
||||||
no user-provided image reference. Consumed one at a time by a ComfyUI workflow.
|
no user-provided image reference. Consumed one at a time by a ComfyUI workflow.
|
||||||
@ -37,12 +37,12 @@ example (including the audio and FL2VA variants) is in `references/worked-exampl
|
|||||||
character sheets. The sheets are still generated: they feed the image side, which
|
character sheets. The sheets are still generated: they feed the image side, which
|
||||||
renders the first/last frames with consistent characters. If the user's wording is
|
renders the first/last frames with consistent characters. If the user's wording is
|
||||||
ambiguous, stay in ref2va mode; never mix the two formats in one run.
|
ambiguous, stay in ref2va mode; never mix the two formats in one run.
|
||||||
- **Segmented (opt-in).** Switch when the user asks for each segment as its own
|
- **Studio (opt-in).** Switch when the user asks for studio mode, for each segment
|
||||||
`segment.txt` file or for `@Picture1` / `@Audio1`-style references. This is an
|
as its own `segment.txt` file, or for `@image1` / `@audio1`-style references. This
|
||||||
adaptation of ref2va defined in `references/segmented-output-format.md`: the
|
is an adaptation of ref2va defined in `references/studio-output-format.md`: the
|
||||||
segment content follows `references/ref2va-segment-format.md` unchanged, but each
|
segment content follows `references/ref2va-segment-format.md` unchanged, but each
|
||||||
segment is written to its own `segment-N/segment.txt` file (no `segments.txt`, no
|
segment is written to its own `segment-N/segment.txt` file (no `segments.txt`, no
|
||||||
`|` separators) and reference tokens are written as `@PictureN` / `@AudioN`;
|
`|` separators) and reference tokens are written as `@imageN` / `@audioN`;
|
||||||
`<Subject N>` stays unchanged. Never mix formats in one run.
|
`<Subject N>` stays unchanged. Never mix formats in one run.
|
||||||
|
|
||||||
## Inputs
|
## Inputs
|
||||||
@ -130,16 +130,16 @@ not subjects.
|
|||||||
**Step 9 — Assemble the segment outputs.** ref2va/FL2VA: strip each segment text and
|
**Step 9 — Assemble the segment outputs.** ref2va/FL2VA: strip each segment text and
|
||||||
join with a single `|` (no spaces added around it). Exactly n segments, exactly n−1
|
join with a single `|` (no spaces added around it). Exactly n segments, exactly n−1
|
||||||
`|` characters, no trailing separator, no extra headers or numbering; the `|`
|
`|` characters, no trailing separator, no extra headers or numbering; the `|`
|
||||||
character must never appear inside a segment's own text. Segmented: instead write
|
character must never appear inside a segment's own text. Studio: instead write
|
||||||
each segment to its own `segment-N/segment.txt` file per
|
each segment to its own `segment-N/segment.txt` file per
|
||||||
`references/segmented-output-format.md` — no joined file, no `|` anywhere, and
|
`references/studio-output-format.md` — no joined file, no `|` anywhere, and
|
||||||
`<Picture N>` / `<Audio N>` written as `@PictureN` / `@AudioN` (`<Subject N>`
|
`<Picture N>` / `<Audio N>` written as `@imageN` / `@audioN` (`<Subject N>`
|
||||||
unchanged).
|
unchanged).
|
||||||
|
|
||||||
**Step 10 — Validate** against the checklist below. When the environment can run Python,
|
**Step 10 — Validate** against the checklist below. When the environment can run Python,
|
||||||
also run `python scripts/validate_outputs.py --segments segments.txt --expected-n <n>`
|
also run `python scripts/validate_outputs.py --segments segments.txt --expected-n <n>`
|
||||||
(add `--mode fl2va --total-seconds <total>` in FL2VA mode; in segmented mode run
|
(add `--mode fl2va --total-seconds <total>` in FL2VA mode; in studio mode run
|
||||||
`python scripts/validate_outputs.py --mode segmented --segments-dir <folder> --expected-n <n>`).
|
`python scripts/validate_outputs.py --mode studio --segments-dir <folder> --expected-n <n>`).
|
||||||
|
|
||||||
## Output location
|
## Output location
|
||||||
|
|
||||||
@ -203,10 +203,10 @@ segment in FL2VA mode, and none in ref2va mode); each is two-key JSON with
|
|||||||
correct final shot index and two-decimal duration; then `integrated_multimodal_description:`,
|
correct final shot index and two-decimal duration; then `integrated_multimodal_description:`,
|
||||||
`overall_soundscape:`, `non_diegetic_music:` in order, and none of the six ref2va
|
`overall_soundscape:`, `non_diegetic_music:` in order, and none of the six ref2va
|
||||||
section labels appear.
|
section labels appear.
|
||||||
12. (Segmented mode) Exactly n `segment-N/segment.txt` files, folders numbered 1..n
|
12. (Studio mode) Exactly n `segment-N/segment.txt` files, folders numbered 1..n
|
||||||
with no gaps; each file is the ref2va single-segment format with `<Picture N>` /
|
with no gaps; each file is the ref2va single-segment format with `<Picture N>` /
|
||||||
`<Audio N>` written as `@PictureN` / `@AudioN`, `<Subject N>` unchanged, and no `|`
|
`<Audio N>` written as `@imageN` / `@audioN` (lowercase), `<Subject N>` unchanged,
|
||||||
character anywhere.
|
and no `|` character anywhere.
|
||||||
|
|
||||||
## References
|
## References
|
||||||
|
|
||||||
@ -214,8 +214,8 @@ character anywhere.
|
|||||||
default mode (sections, labels, shots, audio template, retention markers).
|
default mode (sections, labels, shots, audio template, retention markers).
|
||||||
- `references/fl2va-segment-format.md` — the opt-in FL2VA first–last frame prompt
|
- `references/fl2va-segment-format.md` — the opt-in FL2VA first–last frame prompt
|
||||||
format (instruction line, interpolation arc, dialogue and audio rules).
|
format (instruction line, interpolation arc, dialogue and audio rules).
|
||||||
- `references/segmented-output-format.md` — the opt-in segmented layout: one
|
- `references/studio-output-format.md` — the opt-in studio layout: one
|
||||||
`segment-N/segment.txt` file per segment with `@PictureN` / `@AudioN` reference
|
`segment-N/segment.txt` file per segment with `@imageN` / `@audioN` reference
|
||||||
tokens; otherwise identical to the ref2va format.
|
tokens; otherwise identical to the ref2va format.
|
||||||
- `references/t2i-character-sheet.md` — the four-panel photorealistic turnaround
|
- `references/t2i-character-sheet.md` — the four-panel photorealistic turnaround
|
||||||
sheet rules and the two-key JSON output contract.
|
sheet rules and the two-key JSON output contract.
|
||||||
|
|||||||
@ -1,20 +1,20 @@
|
|||||||
# Segmented Output Format (one segment.txt per segment, optional)
|
# Studio Output Format (one segment.txt per segment, optional)
|
||||||
|
|
||||||
An adaptation of the ref2va format (`references/ref2va-segment-format.md`) for tools
|
An adaptation of the ref2va format (`references/ref2va-segment-format.md`) for tools
|
||||||
that consume one prompt file per segment instead of one joined file. Opt in only when
|
that consume one prompt file per segment instead of one joined file. Opt in only when
|
||||||
the user asks for it (phrases like "each segment gets its own segment.txt", "one file
|
the user asks for studio mode (phrases like "studio", "each segment gets its own
|
||||||
per segment", "@Picture1", "@Audio1"). Everything not changed below is exactly the
|
segment.txt", "one file per segment", "@image1", "@audio1"). Everything not changed
|
||||||
ref2va format — same six sections, same summary prefixes, same audio template and
|
below is exactly the ref2va format — same six sections, same summary prefixes, same
|
||||||
lip-sync phrase, same shot rules, same sheets, frame prompts, and manifest. Never mix
|
audio template and lip-sync phrase, same shot rules, same sheets, frame prompts, and
|
||||||
formats in one run.
|
manifest. Never mix formats in one run.
|
||||||
|
|
||||||
## 1. What changes vs ref2va
|
## 1. What changes vs ref2va
|
||||||
|
|
||||||
| | ref2va (default) | segmented (opt-in) |
|
| | ref2va (default) | studio (opt-in) |
|
||||||
| --- | --- | --- |
|
| --- | --- | --- |
|
||||||
| Output files | one `segments.txt`, n segments joined by bare `\|` | n files: `segment-1/segment.txt`, `segment-2/segment.txt`, ... |
|
| Output files | one `segments.txt`, n segments joined by bare `\|` | n files: `segment-1/segment.txt`, `segment-2/segment.txt`, ... |
|
||||||
| `\|` separators | exactly n−1, bare | none — the `\|` character never appears in any segment file |
|
| `\|` separators | exactly n−1, bare | none — the `\|` character never appears in any segment file |
|
||||||
| Reference tokens | `<Picture 1>`, `<Audio 1>` | `@Picture1`, `@Audio1` |
|
| Reference tokens | `<Picture 1>`, `<Audio 1>` | `@image1`, `@audio1` |
|
||||||
| Subject tokens | `<Subject N>` | `<Subject N>` — unchanged |
|
| Subject tokens | `<Subject N>` | `<Subject N>` — unchanged |
|
||||||
| Segment content | ref2va single-segment format | identical, one document per file |
|
| Segment content | ref2va single-segment format | identical, one document per file |
|
||||||
|
|
||||||
@ -36,32 +36,34 @@ trailing whitespace. Folder numbers start at 1 with no gaps and no extra
|
|||||||
## 3. Reference token syntax
|
## 3. Reference token syntax
|
||||||
|
|
||||||
Convert every reference token to its @-form — same number, no space, no angle
|
Convert every reference token to its @-form — same number, no space, no angle
|
||||||
brackets:
|
brackets, all lowercase:
|
||||||
|
|
||||||
- `<Picture N>` → `@PictureN` (example: `<Picture 1>` → `@Picture1`)
|
- `<Picture N>` → `@imageN` (example: `<Picture 1>` → `@image1`)
|
||||||
- `<Audio N>` → `@AudioN` (example: `<Audio 1>` → `@Audio1`)
|
- `<Audio N>` → `@audioN` (example: `<Audio 1>` → `@audio1`)
|
||||||
|
|
||||||
The conversion applies everywhere the token appears: the `subject_definitions`
|
The conversion applies everywhere the token appears: the `subject_definitions`
|
||||||
citations and audio definition line, `summary`, `retention_analysis` (including the
|
citations and audio definition line, `summary`, `retention_analysis` (including the
|
||||||
`fully_copy` line), and the lip-sync phrase inside `detailed_description`. Examples:
|
`fully_copy` line), and the lip-sync phrase inside `detailed_description`. Examples:
|
||||||
|
|
||||||
- `<Audio 1> is the user-supplied song file "midnight.mp3", ...` →
|
- `<Audio 1> is the user-supplied song file "midnight.mp3", ...` →
|
||||||
`@Audio1 is the user-supplied song file "midnight.mp3", ...`
|
`@audio1 is the user-supplied song file "midnight.mp3", ...`
|
||||||
- `<Subject 1> lips are synced to the audio in <Audio 1>` →
|
- `<Subject 1> lips are synced to the audio in <Audio 1>` →
|
||||||
`<Subject 1> lips are synced to the audio in @Audio1`
|
`<Subject 1> lips are synced to the audio in @audio1`
|
||||||
- `<Audio 1>: fully_copy - <Audio 1> is reused 1:1 as the target video's complete
|
- `<Audio 1>: fully_copy - <Audio 1> is reused 1:1 as the target video's complete
|
||||||
final audio track.` → `@Audio1: fully_copy - @Audio1 is reused 1:1 as the target
|
final audio track.` → `@audio1: fully_copy - @audio1 is reused 1:1 as the target
|
||||||
video's complete final audio track.`
|
video's complete final audio track.`
|
||||||
|
|
||||||
`<Subject N>` is NOT converted: never write `@SubjectN`. The angle-bracket forms
|
`<Subject N>` is NOT converted: never write `@subjectN`. The angle-bracket forms
|
||||||
`<Picture ...>` and `<Audio ...>` must not appear anywhere in a segmented file.
|
`<Picture ...>` and `<Audio ...>` must not appear anywhere in a studio file, and
|
||||||
|
capitalized variants like `@Image1` or `@Audio1` are wrong — the tokens are exactly
|
||||||
|
`@imageN` and `@audioN`, lowercase.
|
||||||
|
|
||||||
## 4. Numbering
|
## 4. Numbering
|
||||||
|
|
||||||
Subject and Picture numbering stays global across the whole video (1..M, gapless when
|
Subject and Picture numbering stays global across the whole video (1..M, gapless when
|
||||||
all segment files are taken together), exactly as in ref2va; each file defines only
|
all segment files are taken together), exactly as in ref2va; each file defines only
|
||||||
the subjects that appear in it, using their global numbers. `Image-N.json` sheets and
|
the subjects that appear in it, using their global numbers. `Image-N.json` sheets and
|
||||||
`image-map.txt` are unchanged, and `@PictureN` still corresponds to the sheet mapped
|
`image-map.txt` are unchanged, and `@imageN` still corresponds to the sheet mapped
|
||||||
to Subject N.
|
to Subject N.
|
||||||
|
|
||||||
## 5. Worked micro-example
|
## 5. Worked micro-example
|
||||||
@ -72,11 +74,11 @@ tokens converted:
|
|||||||
|
|
||||||
```text
|
```text
|
||||||
subject_definitions:
|
subject_definitions:
|
||||||
<Subject 1> is the astronaut in @Picture1, a woman in her thirties with short black hair, wearing a matte-white EVA suit with orange stripe accents and a wrist-mounted scanner.
|
<Subject 1> is the astronaut in @image1, a woman in her thirties with short black hair, wearing a matte-white EVA suit with orange stripe accents and a wrist-mounted scanner.
|
||||||
<Subject 2> is the scout robot in @Picture2, a boxy machine on three wheels with a pale-grey shell and a single round blue lens eye.
|
<Subject 2> is the scout robot in @image2, a boxy machine on three wheels with a pale-grey shell and a single round blue lens eye.
|
||||||
|
|
||||||
summary:
|
summary:
|
||||||
[reference generation] The target video shows <Subject 1> and <Subject 2> cresting a red dune at dusk and stopping before a monolith of black glass. <Subject 1>'s appearance and suit come from @Picture1 and <Subject 2>'s shell and lens come from @Picture2.
|
[reference generation] The target video shows <Subject 1> and <Subject 2> cresting a red dune at dusk and stopping before a monolith of black glass. <Subject 1>'s appearance and suit come from @image1 and <Subject 2>'s shell and lens come from @image2.
|
||||||
|
|
||||||
retention_analysis:
|
retention_analysis:
|
||||||
<Subject 1> (appears in [Shot 1]): fully_preserved - the matte-white EVA suit with orange stripe accents, short black hair, and the wrist-mounted scanner are retained.
|
<Subject 1> (appears in [Shot 1]): fully_preserved - the matte-white EVA suit with orange stripe accents, short black hair, and the wrist-mounted scanner are retained.
|
||||||
@ -291,11 +291,11 @@ same story state as segment 1's last frame (the handoff), worded independently.
|
|||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
# Segmented variant (one segment.txt per segment, @-references)
|
# Studio variant (one segment.txt per segment, @-references)
|
||||||
|
|
||||||
The same desert run in the opt-in segmented layout
|
The same desert run in the opt-in studio layout
|
||||||
(`references/segmented-output-format.md`): an adaptation of ref2va where each segment
|
(`references/studio-output-format.md`): an adaptation of ref2va where each segment
|
||||||
is its own file and reference tokens are written `@PictureN` / `@AudioN`. The segment
|
is its own file and reference tokens are written `@imageN` / `@audioN`. The segment
|
||||||
texts are the Segment 1 / Segment 2 texts from the default run above with only the
|
texts are the Segment 1 / Segment 2 texts from the default run above with only the
|
||||||
token syntax converted — content, sections, prefixes, and numbering are unchanged.
|
token syntax converted — content, sections, prefixes, and numbering are unchanged.
|
||||||
Sheets, frame prompts, and `image-map.txt` are identical to the default run.
|
Sheets, frame prompts, and `image-map.txt` are identical to the default run.
|
||||||
@ -315,11 +315,11 @@ above):
|
|||||||
|
|
||||||
```text
|
```text
|
||||||
subject_definitions:
|
subject_definitions:
|
||||||
<Subject 1> is the astronaut in @Picture1, a woman in her thirties with short black hair and brown eyes, wearing a matte-white EVA suit with orange stripe accents, grey reinforced gloves, a clear dome helmet, and a wrist-mounted scanner on her left forearm.
|
<Subject 1> is the astronaut in @image1, a woman in her thirties with short black hair and brown eyes, wearing a matte-white EVA suit with orange stripe accents, grey reinforced gloves, a clear dome helmet, and a wrist-mounted scanner on her left forearm.
|
||||||
<Subject 2> is the scout robot in @Picture2, a boxy machine on three wheels with a pale-grey shell, a single round blue lens eye, and a short antenna.
|
<Subject 2> is the scout robot in @image2, a boxy machine on three wheels with a pale-grey shell, a single round blue lens eye, and a short antenna.
|
||||||
|
|
||||||
summary:
|
summary:
|
||||||
[reference generation] The target video shows <Subject 1> and <Subject 2> cresting a red dune at dusk and stopping before a monolith of black glass. <Subject 1>'s appearance and suit come from @Picture1 and <Subject 2>'s shell and lens come from @Picture2.
|
[reference generation] The target video shows <Subject 1> and <Subject 2> cresting a red dune at dusk and stopping before a monolith of black glass. <Subject 1>'s appearance and suit come from @image1 and <Subject 2>'s shell and lens come from @image2.
|
||||||
|
|
||||||
retention_analysis:
|
retention_analysis:
|
||||||
<Subject 1> (appears in [Shot 1]): fully_preserved - the matte-white EVA suit with orange stripe accents, grey reinforced gloves, short black hair, clear dome helmet, and the wrist-mounted scanner on her left forearm are retained.
|
<Subject 1> (appears in [Shot 1]): fully_preserved - the matte-white EVA suit with orange stripe accents, grey reinforced gloves, short black hair, clear dome helmet, and the wrist-mounted scanner on her left forearm are retained.
|
||||||
@ -337,8 +337,8 @@ N/A
|
|||||||
```
|
```
|
||||||
|
|
||||||
Note what did NOT change: `<Subject 1>` keeps its angle brackets (only `<Picture N>`
|
Note what did NOT change: `<Subject 1>` keeps its angle brackets (only `<Picture N>`
|
||||||
and `<Audio N>` become `@PictureN` / `@AudioN`), there is no `|` character anywhere,
|
and `<Audio N>` become `@imageN` / `@audioN`, lowercase), there is no `|` character
|
||||||
and no joined `segments.txt` is written. Validate with
|
anywhere, and no joined `segments.txt` is written. Validate with
|
||||||
`python3 scripts/validate_outputs.py --mode segmented --segments-dir <folder>
|
`python3 scripts/validate_outputs.py --mode studio --segments-dir <folder>
|
||||||
--expected-n 2`.
|
--expected-n 2`.
|
||||||
|
|
||||||
|
|||||||
@ -10,9 +10,10 @@ Checks the output contract described in SKILL.md:
|
|||||||
- fl2va mode (opt-in): exact instruction line (final shot index + two-decimal
|
- fl2va mode (opt-in): exact instruction line (final shot index + two-decimal
|
||||||
duration), the three fields in order, no reference labels, no ref2va
|
duration), the three fields in order, no reference labels, no ref2va
|
||||||
section labels, shot rules, fixed song sentences when a song is reused
|
section labels, shot rules, fixed song sentences when a song is reused
|
||||||
- segmented mode (opt-in, ref2va adaptation): n files segment-N/segment.txt, no
|
- studio mode (opt-in, ref2va adaptation): n files segment-N/segment.txt, no
|
||||||
'|' anywhere, @PictureN / @AudioN tokens (angle-bracket <Picture>/<Audio> and
|
'|' anywhere, @imageN / @audioN tokens (angle-bracket <Picture>/<Audio>,
|
||||||
@Subject are failures), otherwise the full ref2va per-segment checks
|
@subject, and capitalized @Image/@Audio variants are failures), otherwise
|
||||||
|
the full ref2va per-segment checks
|
||||||
- image-map.txt manifest covers every subject; Image-N.json valid (two keys,
|
- image-map.txt manifest covers every subject; Image-N.json valid (two keys,
|
||||||
16:9, four-panel photorealistic sheet language)
|
16:9, four-panel photorealistic sheet language)
|
||||||
- Segment-img-N.json per segment (both modes) and Segment-img-N-last.json
|
- Segment-img-N.json per segment (both modes) and Segment-img-N-last.json
|
||||||
@ -24,7 +25,7 @@ Usage:
|
|||||||
python3 scripts/validate_outputs.py --segments segments.txt [--expected-n 3] \
|
python3 scripts/validate_outputs.py --segments segments.txt [--expected-n 3] \
|
||||||
[--mode ref2va|fl2va] [--total-seconds 21] [--dir .] [--manifest image-map.txt] \
|
[--mode ref2va|fl2va] [--total-seconds 21] [--dir .] [--manifest image-map.txt] \
|
||||||
[--lyrics-file lyrics.txt] [--expect-audio]
|
[--lyrics-file lyrics.txt] [--expect-audio]
|
||||||
python3 scripts/validate_outputs.py --mode segmented --segments-dir <folder> \
|
python3 scripts/validate_outputs.py --mode studio --segments-dir <folder> \
|
||||||
[--expected-n 3] [shared options] # folder holds segment-1/segment.txt ...
|
[--expected-n 3] [shared options] # folder holds segment-1/segment.txt ...
|
||||||
|
|
||||||
Exit code 0 = all checks passed, 1 = failures listed.
|
Exit code 0 = all checks passed, 1 = failures listed.
|
||||||
@ -77,8 +78,9 @@ FL2VA_SONG_SENTENCE_RE = re.compile(
|
|||||||
)
|
)
|
||||||
FL2VA_LIPSYNC_RE = re.compile(r"\(S(\d+)\) lips stay synced to the song's vocals")
|
FL2VA_LIPSYNC_RE = re.compile(r"\(S(\d+)\) lips stay synced to the song's vocals")
|
||||||
|
|
||||||
SEGMENTED_PICTURE_RE = re.compile(r"@Picture(\d+)")
|
STUDIO_PICTURE_RE = re.compile(r"@image(\d+)")
|
||||||
SEGMENTED_AUDIO_RE = re.compile(r"@Audio(\d+)")
|
STUDIO_AUDIO_RE = re.compile(r"@audio(\d+)")
|
||||||
|
STUDIO_BAD_CASE_RE = re.compile(r"@(Image\d|Audio\d|IMAGE\d|AUDIO\d)")
|
||||||
|
|
||||||
BANNED_WORDS = ["cartoon", "anime", "manga", "illustration", "stylized",
|
BANNED_WORDS = ["cartoon", "anime", "manga", "illustration", "stylized",
|
||||||
"cgi", "3d render", "mascot", "avatar", "name tag",
|
"cgi", "3d render", "mascot", "avatar", "name tag",
|
||||||
@ -303,20 +305,24 @@ def check_segment_fl2va(seg_text, seg_no, errors, expected_duration=None):
|
|||||||
return has_song
|
return has_song
|
||||||
|
|
||||||
|
|
||||||
def check_segment_segmented(seg_text, seg_no, errors):
|
def check_segment_studio(seg_text, seg_no, errors):
|
||||||
"""Segmented mode: ref2va content with @-references, one file per segment."""
|
"""Studio mode: ref2va content with @imageN/@audioN references, one file per segment."""
|
||||||
if "|" in seg_text:
|
if "|" in seg_text:
|
||||||
fail(errors, seg_no, "segmented segment.txt must not contain the '|' "
|
fail(errors, seg_no, "studio segment.txt must not contain the '|' "
|
||||||
"separator (each segment is its own file)")
|
"separator (each segment is its own file)")
|
||||||
for bad, good in (("<Picture", "@PictureN"), ("<Audio", "@AudioN")):
|
for bad, good in (("<Picture", "@imageN"), ("<Audio", "@audioN")):
|
||||||
if bad in seg_text:
|
if bad in seg_text:
|
||||||
fail(errors, seg_no, f"segmented files use @-references: '{bad} N' must "
|
fail(errors, seg_no, f"studio files use @-references: '{bad} N' must "
|
||||||
f"be written as {good} (no space, no angle brackets)")
|
f"be written as {good} (no space, no angle brackets)")
|
||||||
if "@Subject" in seg_text:
|
if "@Subject" in seg_text or "@subject" in seg_text:
|
||||||
fail(errors, seg_no, "subject labels are not converted: keep '<Subject N>', "
|
fail(errors, seg_no, "subject labels are not converted: keep '<Subject N>', "
|
||||||
"never '@SubjectN'")
|
"never '@subjectN'")
|
||||||
normalized = SEGMENTED_PICTURE_RE.sub(r"<Picture \1>", seg_text)
|
bad_case = STUDIO_BAD_CASE_RE.findall(seg_text)
|
||||||
normalized = SEGMENTED_AUDIO_RE.sub(r"<Audio \1>", normalized)
|
if bad_case:
|
||||||
|
fail(errors, seg_no, f"reference tokens are lowercase: {bad_case} must be "
|
||||||
|
f"written as @imageN / @audioN")
|
||||||
|
normalized = STUDIO_PICTURE_RE.sub(r"<Picture \1>", seg_text)
|
||||||
|
normalized = STUDIO_AUDIO_RE.sub(r"<Audio \1>", normalized)
|
||||||
return check_segment_ref2va(normalized, seg_no, errors)
|
return check_segment_ref2va(normalized, seg_no, errors)
|
||||||
|
|
||||||
|
|
||||||
@ -366,11 +372,11 @@ def main():
|
|||||||
ap.add_argument("--segments", required=False, default=None,
|
ap.add_argument("--segments", required=False, default=None,
|
||||||
help="joined segments.txt (not used with --segments-dir)")
|
help="joined segments.txt (not used with --segments-dir)")
|
||||||
ap.add_argument("--segments-dir", default=None,
|
ap.add_argument("--segments-dir", default=None,
|
||||||
help="folder holding segment-1/segment.txt ... (segmented mode)")
|
help="folder holding segment-1/segment.txt ... (studio mode)")
|
||||||
ap.add_argument("--expected-n", type=int, default=None)
|
ap.add_argument("--expected-n", type=int, default=None)
|
||||||
ap.add_argument("--mode", choices=["ref2va", "fl2va", "segmented"],
|
ap.add_argument("--mode", choices=["ref2va", "fl2va", "studio"],
|
||||||
default="ref2va",
|
default="ref2va",
|
||||||
help="ref2va (default), fl2va first-last, or segmented "
|
help="ref2va (default), fl2va first-last, or studio "
|
||||||
"per-file layout")
|
"per-file layout")
|
||||||
ap.add_argument("--total-seconds", type=float, default=None,
|
ap.add_argument("--total-seconds", type=float, default=None,
|
||||||
help="total video length; enables the S.SS duration check in "
|
help="total video length; enables the S.SS duration check in "
|
||||||
@ -392,9 +398,9 @@ def main():
|
|||||||
|
|
||||||
if args.segments_dir:
|
if args.segments_dir:
|
||||||
if args.mode == "fl2va":
|
if args.mode == "fl2va":
|
||||||
print("FAIL: --segments-dir is the segmented layout; use --mode segmented")
|
print("FAIL: --segments-dir is the studio layout; use --mode studio")
|
||||||
return 1
|
return 1
|
||||||
args.mode = "segmented"
|
args.mode = "studio"
|
||||||
seg_dir = Path(args.segments_dir)
|
seg_dir = Path(args.segments_dir)
|
||||||
if not seg_dir.exists():
|
if not seg_dir.exists():
|
||||||
print(f"FAIL: {seg_dir} not found")
|
print(f"FAIL: {seg_dir} not found")
|
||||||
@ -448,8 +454,8 @@ def main():
|
|||||||
for i, part in enumerate(parts, 1):
|
for i, part in enumerate(parts, 1):
|
||||||
if args.mode == "fl2va":
|
if args.mode == "fl2va":
|
||||||
has_audio = check_segment_fl2va(part.strip(), i, errors, expected_duration)
|
has_audio = check_segment_fl2va(part.strip(), i, errors, expected_duration)
|
||||||
elif args.mode == "segmented":
|
elif args.mode == "studio":
|
||||||
defined, has_audio = check_segment_segmented(part.strip(), i, errors)
|
defined, has_audio = check_segment_studio(part.strip(), i, errors)
|
||||||
subjects |= defined
|
subjects |= defined
|
||||||
else:
|
else:
|
||||||
defined, has_audio = check_segment_ref2va(part.strip(), i, errors)
|
defined, has_audio = check_segment_ref2va(part.strip(), i, errors)
|
||||||
@ -461,7 +467,7 @@ def main():
|
|||||||
"video references")
|
"video references")
|
||||||
|
|
||||||
all_nums = set(int(x) for x in SUBJECT_RE.findall(raw))
|
all_nums = set(int(x) for x in SUBJECT_RE.findall(raw))
|
||||||
if args.mode in ("ref2va", "segmented") and all_nums and \
|
if args.mode in ("ref2va", "studio") and all_nums and \
|
||||||
all_nums != set(range(1, max(all_nums) + 1)):
|
all_nums != set(range(1, max(all_nums) + 1)):
|
||||||
errors.append(f"global Subject numbering must be gapless 1..{max(all_nums)} "
|
errors.append(f"global Subject numbering must be gapless 1..{max(all_nums)} "
|
||||||
f"(found {sorted(all_nums)})")
|
f"(found {sorted(all_nums)})")
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user