Decision-Log.md
... ...
@@ -4,6 +4,7 @@ Use this page for decisions that change production canon. Newest entries go firs
4 4
5 5
| Date | Area | Decision | Status | Affected pages |
6 6
| --- | --- | --- | --- | --- |
7
+| 2026-07-26 | Shot timing | Import the finished Suno song into Palmier, transcribe it with Whisper, review the exact timecodes, and derive shot ranges before Anima storyboarding | Approved | [Music and Voices](/Music-and-Voices), [Visual Pipeline](/Visual-Pipeline), [Episode Template](/Episode-Template) |
7 8
| 2026-07-26 | Pipeline order | Suno is always the first media-generation stage; lock its selected audio and timing map before Anima storyboarding, then use Wan and finish in Palmier | Approved | [Music and Voices](/Music-and-Voices), [Visual Pipeline](/Visual-Pipeline), [Little Lanterns Format](/Little-Lanterns-Format) |
8 9
| 2026-07-26 | Series structure | Every Little Lanterns season contains 26 A–Z episodes; Alphabet Adventures is the recurring series format rather than a standalone generic season theme | Approved | [Little Lanterns](/Little-Lanterns), [Seasons](/Seasons) |
9 10
| 2026-07-26 | Season 01 slate | Adopt the supplied A–Z titles and loglines as the complete candidate episode slate for Alphabet Adventures | Candidate | [Season 01 — Alphabet Adventures](/Season-01---Alphabet-Adventures) |
Episode-Template.md
... ...
@@ -18,7 +18,7 @@ Lumi and Pip meet **[guest]**, help with **[problem]**, and discover **[meaning]
18 18
**Emotional idea:**
19 19
**Audience participation:**
20 20
21
-## Suno-first audio lock
21
+## Suno-first audio lock and transcription
22 22
23 23
**Two voice roles:**
24 24
**Spoken-word tags:**
... ...
@@ -30,9 +30,14 @@ Lumi and Pip meet **[guest]**, help with **[problem]**, and discover **[meaning]
30 30
**Locked audio duration:**
31 31
**Music output:**
32 32
**Narration output:**
33
-**Audio status:** Draft
34
-
35
-| Cue | Start | End | Lyric / narration | Story beat | Visual opportunity |
33
+**Palmier project:**
34
+**Palmier audio asset / track:**
35
+**Whisper model / workflow version:**
36
+**Whisper transcript:**
37
+**Transcript review status:** Draft
38
+**Timing-map status:** Draft
39
+
40
+| Cue | Start | End | Reviewed lyric / narration | Story beat | Visual opportunity |
36 41
| --- | ---: | ---: | --- | --- | --- |
37 42
| CUE-01 | | | | Find | |
38 43
| CUE-02 | | | | Meet | |
... ...
@@ -41,8 +46,8 @@ Lumi and Pip meet **[guest]**, help with **[problem]**, and discover **[meaning]
41 46
| CUE-05 | | | | Sing | |
42 47
| CUE-06 | | | | Shine | |
43 48
44
-No visual storyboard begins until the selected Suno version and this timing map
45
-are locked.
49
+No visual storyboard begins until the selected Suno song is in Palmier and the
50
+Whisper transcript and timing map are reviewed and locked.
46 51
47 52
## Beat sheet
48 53
... ...
@@ -83,7 +88,7 @@ are locked.
83 88
84 89
**Suno music output:**
85 90
**Suno narration output:**
86
-**Suno timing map version:**
91
+**Whisper transcript / timing-map version:**
87 92
**Anima model / checkpoint:**
88 93
**Anima workflow version:**
89 94
**Dimensions:** 864 × 1152 (3:4 portrait candidate)
Little-Lanterns-Format.md
... ...
@@ -10,19 +10,24 @@ The episode is designed as one coordinated audio-visual sequence:
10 10
1. **Suno music and narration** — generate and approve the musical structure,
11 11
two-character voices, spoken narration, spoken-word tags, and emotional
12 12
performance.
13
-2. **Audio lock and timing map** — mark the selected Suno version’s story beats,
14
- lyrics, narration, transitions, and shot opportunities.
15
-3. **Anima storyboard** — design and approve the first frame for every planned
13
+2. **Palmier audio ingest** — place the finished Suno song on the authoritative
14
+ episode timeline before visual generation.
15
+3. **Whisper transcription** — transcribe the song and produce exact timecodes
16
+ for lyrics, narration, pauses, transitions, and musical sections.
17
+4. **Shot timing map** — convert the reviewed Whisper transcript into story
18
+ beats and visual shot ranges.
19
+5. **Anima storyboard** — design and approve the first frame for every planned
16 20
shot against the locked Suno timing.
17
-4. **Wan 2.2 14B image-to-video** — animate each approved first frame to serve
21
+6. **Wan 2.2 14B image-to-video** — animate each approved first frame to serve
18 22
its assigned audio range.
19
-5. **Palmier finish** — assemble, time, revise, and finalize all selected Wan
23
+7. **Palmier finish** — assemble, time, revise, and finalize all selected Wan
20 24
shots and Suno audio in Palmier while preserving prompt and workflow
21 25
provenance.
22 26
23 27
The 12-panel storyboard is therefore not disposable concept art. Each approved
24 28
panel is the visual start frame and continuity contract for its corresponding
25
-video shot, and each panel must reference the Suno cue or time range it serves.
29
+video shot, and each panel must reference the reviewed Whisper cue or exact
30
+Palmier time range it serves.
26 31
27 32
## Story rhythm
28 33
Music-and-Voices.md
... ...
@@ -5,15 +5,17 @@
5 5
**Suno is always the first media-generation stage.** After the episode concept,
6 6
learning goal, and story/song brief are approved, Suno generates both **music
7 7
and narration**. No Anima storyboard or Wan shot production begins until a
8
-specific Suno version is selected and its timing map is recorded.
8
+specific Suno version is selected, imported into Palmier, transcribed with
9
+Whisper, and converted into a reviewed timing map.
9 10
10 11
The working pipeline is strongest when a piece is designed for two distinct
11 12
voices, uses explicit spoken-word tags, and describes the emotional movement of
12 13
each section.
13 14
14
-The selected Suno structure is the episode’s timing and emotional spine. The
15
-storyboard interprets that audio; the audio is not reshaped to justify an
16
-already-generated storyboard.
15
+The selected Suno audio on the Palmier timeline is the episode’s timing and
16
+emotional spine. Whisper provides the timecoded transcript used to place shot
17
+boundaries. The storyboard interprets that audio; the audio is not reshaped to
18
+justify an already-generated storyboard.
17 19
18 20
## Voice functions
19 21
... ...
@@ -55,7 +57,10 @@ song:
55 57
audio_lock:
56 58
selected_version: ""
57 59
duration: ""
58
- timing_map: ""
60
+ palmier_project: ""
61
+ palmier_audio_track: ""
62
+ whisper_transcript: ""
63
+ whisper_timing_map: ""
59 64
locked_on: YYYY-MM-DD
60 65
```
61 66
... ...
@@ -70,6 +75,10 @@ combined in Palmier.
70 75
* Let the chorus express the discovery, not merely repeat the letter.
71 76
* Write visual beats and song structure together.
72 77
* Preserve generation prompts and selected output links.
73
-* Lock the chosen Suno version and timing map before Anima storyboarding.
78
+* Import the chosen Suno version into Palmier before Anima storyboarding.
79
+* Run Whisper on the exact imported song and preserve the timecoded transcript.
80
+* Review Whisper’s words against the approved lyrics while retaining verified
81
+ timing; sung words can require text correction.
82
+* Lock the reviewed transcript and shot timing map before Anima storyboarding.
74 83
* Treat any later audio change as a dependency change that may invalidate the
75 84
storyboard, Wan shots, and Palmier timeline.
Season-01---Alphabet-Adventures.md
... ...
@@ -274,8 +274,8 @@ earlier adventures to find his way home.
274 274
275 275
Build an A–Z season contact board with one guest silhouette, palette, location
276 276
anchor, hero prop, and primary motion for each episode. Then select a simple,
277
-average, and difficult episode for full Suno → Anima → Wan → Palmier pipeline
278
-tests.
277
+average, and difficult episode for the full Suno → Palmier → Whisper → Anima →
278
+Wan → Palmier pipeline.
279 279
280 280
Create individual episode pages from the [Episode Template](/Episode-Template)
281 281
as each story enters development.
Visual-Pipeline.md
... ...
@@ -7,29 +7,34 @@
7 7
1. Approve the episode concept, learning goal, and Suno story/song brief.
8 8
2. Generate the episode’s music, two-character voices, spoken narration,
9 9
spoken-word tags, and emotional performance through **Suno**.
10
-3. Select and lock one Suno version. Record its duration and timing map.
11
-4. Lock the episode’s cast, guest, location, and style records.
12
-5. Write a 12-panel board against the locked Suno timing using the coverage
10
+3. Select and lock one finished Suno version.
11
+4. Import that exact song into **Palmier** as the authoritative episode audio.
12
+5. Run **Whisper** against the imported song to produce a timecoded transcript.
13
+6. Review the Whisper transcript against the approved lyrics and narration,
14
+ correct recognition errors, and preserve verified timecodes.
15
+7. Convert the reviewed transcript into the shot timing map.
16
+8. Lock the episode’s cast, guest, location, and style records.
17
+9. Write a 12-panel board against the Whisper/Palmier timing using the coverage
13 18
rules in [Little Lanterns Format](/Little-Lanterns-Format).
14
-6. Assign every panel a Suno cue or exact audio range.
15
-7. Compile each structured image record through the Anima model adapter.
16
-8. Generate Anima storyboard candidates locally in ComfyUI.
17
-9. Review character recognition, location continuity, shot diversity, story
19
+10. Assign every panel a transcript cue and exact Palmier audio range.
20
+11. Compile each structured image record through the Anima model adapter.
21
+12. Generate Anima storyboard candidates locally in ComfyUI.
22
+13. Review character recognition, location continuity, shot diversity, story
18 23
clarity, and the motion opportunity in every frame.
19
-10. Approve one Anima frame per shot. That image becomes the first frame and
24
+14. Approve one Anima frame per shot. That image becomes the first frame and
20 25
visual continuity contract for image-to-video.
21
-11. Write a motion prompt that describes only what changes after the approved
26
+15. Write a motion prompt that describes only what changes after the approved
22 27
first frame during its assigned audio range.
23
-12. Animate each approved frame through the local **Wan 2.2 14B
28
+16. Animate each approved frame through the local **Wan 2.2 14B
24 29
image-to-video** workflow.
25
-13. Send the selected Wan video shots and locked Suno audio to **Palmier**.
26
-14. Assemble, time, revise, and finalize all episode media in Palmier.
27
-15. Store review assets in SmartGallery and record the Palmier project,
30
+17. Return the selected Wan video shots to the existing Palmier project.
31
+18. Assemble, time, revise, and finalize all episode media in Palmier.
32
+19. Store review assets in SmartGallery and record the Palmier project,
28 33
timeline, final outputs, links, and provenance here.
29 34
30 35
## Handoff contracts
31 36
32
-### Suno → timed visual plan
37
+### Suno → Palmier → Whisper timing
33 38
34 39
Suno is always the first generated-media stage. Every locked audio version hands
35 40
off:
... ...
@@ -42,6 +47,13 @@ audio_handoff:
42 47
narration_output: ""
43 48
selected_version: ""
44 49
duration: ""
50
+ palmier_project: ""
51
+ palmier_audio_asset: ""
52
+ palmier_audio_track: ""
53
+ whisper_model: ""
54
+ whisper_workflow_version: ""
55
+ whisper_transcript: ""
56
+ transcript_review_status: Draft
45 57
emotional_arc: ""
46 58
spoken_word_tags: []
47 59
timing_map:
... ...
@@ -51,12 +63,15 @@ audio_handoff:
51 63
lyric_or_narration: ""
52 64
story_beat: ""
53 65
visual_opportunity: ""
66
+ transcript_source: whisper
54 67
locked_on: YYYY-MM-DD
55 68
```
56 69
57 70
Music and narration may be generated as one integrated performance or as
58
-separate approved outputs. In either case, their combined selected timing is
59
-locked before Anima storyboarding begins.
71
+separate approved outputs. In either case, the exact finished audio used in
72
+Palmier is the file Whisper must transcribe. The transcript text is reviewed
73
+against the approved lyrics and narration before its timecodes become the
74
+visual-production authority.
60 75
61 76
### Timed visual plan and Anima → Wan 2.2 14B
62 77
... ...
@@ -72,7 +87,7 @@ shot_handoff:
72 87
dimensions: 864x1152
73 88
visible_characters: []
74 89
continuity_anchors: []
75
- suno_cue_ids: []
90
+ whisper_cue_ids: []
76 91
audio_start: ""
77 92
audio_end: ""
78 93
intended_action: ""
... ...
@@ -137,8 +152,10 @@ source-generation records for Anima, Wan, or Suno.
137 152
* No unexplained duplicate character or wardrobe mutation appears.
138 153
* Every approved frame has a specific, achievable motion plan.
139 154
* Wan preserves the approved first-frame identity, composition, and location.
140
-* Every panel and Wan shot references its locked Suno cue or audio range.
155
+* Every panel and Wan shot references its reviewed Whisper cue and exact Palmier audio range.
141 156
* Music and narration establish the emotional beats interpreted by the storyboard.
157
+* The transcript was reviewed against the approved lyrics and narration.
158
+* The Whisper timing source is the exact Suno file imported into Palmier.
142 159
* The Palmier timeline references the selected Wan and Suno versions.
143 160
* The final Palmier output can be traced back to every source-generation record.
144 161
Workflow-Registry.md
... ...
@@ -5,10 +5,12 @@ review link whenever a workflow changes.
5 5
6 6
| Workflow | Purpose | Runtime | Version / path | Status |
7 7
| --- | --- | --- | --- | --- |
8
-| Music and narration | Create and lock the timing spine before visual generation | Suno workflow | Exact prompt version TBD | Approved first stage |
8
+| Music and narration | Create and select the finished episode song and narration | Suno workflow | Exact prompt version TBD | Approved first stage |
9
+| Audio timeline ingest | Place the selected Suno song on the authoritative episode timeline | Palmier | Exact project/template version TBD | Approved second stage |
10
+| Song transcription and timing | Produce and review the timecoded transcript used to define shots | Whisper | Exact model/workflow version TBD | Approved third stage |
9 11
| Character reference pack | Turnaround, expressions, pair scale | Local ComfyUI | TBD | Draft |
10
-| 12-panel first-frame storyboard | Interpret the locked Suno timing with consistent cast, location, varied coverage, and one approved first frame per shot | Local ComfyUI / Anima | Mary–Joseph V1 is the current learning reference | Approved second stage |
11
-| Image-to-video shot | Animate an approved Anima first frame to its assigned Suno cue without redesigning it | Local ComfyUI / Wan 2.2 14B | Exact workflow path and version TBD | Approved third stage |
12
+| 12-panel first-frame storyboard | Interpret the reviewed Whisper/Palmier timing with consistent cast, location, varied coverage, and one approved first frame per shot | Local ComfyUI / Anima | Mary–Joseph V1 is the current learning reference | Approved fourth stage |
13
+| Image-to-video shot | Animate an approved Anima first frame to its assigned Palmier time range without redesigning it | Local ComfyUI / Wan 2.2 14B | Exact workflow path and version TBD | Approved fifth stage |
12 14
| Episode finishing | Assemble, time, revise, and finalize every selected media element | Palmier | Exact project/template version TBD | Approved interim direction |
13 15
| Asset review | Contact sheets and approved output collections | SmartGallery | TBD | Candidate |
14 16