Visual Pipeline

Status: Approved initial pipeline

Production flow

  1. Lock the episode’s cast, guest, location, style, and audio intent.
  2. Write a 12-panel board using the coverage rules in Little Lanterns Format.
  3. Compile each structured image record through the Anima model adapter.
  4. Generate Anima storyboard candidates locally in ComfyUI.
  5. Review character recognition, location continuity, shot diversity, story clarity, and the motion opportunity in every frame.
  6. Approve one Anima frame per shot. That image becomes the first frame and visual continuity contract for image-to-video.
  7. Write a motion prompt that describes only what changes after the approved first frame.
  8. Animate each approved frame through the local Wan 2.2 14B image-to-video workflow.
  9. Generate the episode’s music, character voices, spoken narration, spoken-word tags, and emotional performance through Suno.
  10. Send the selected Wan video shots and Suno audio to Palmier.
  11. Assemble, time, revise, and finalize all episode media in Palmier.
  12. Store review assets in SmartGallery and record the Palmier project, timeline, final outputs, links, and provenance here.

Handoff contracts

Anima → Wan 2.2 14B

Every approved storyboard shot hands off:

shot_handoff:
  shot_id: S01E__-SH__
  approved_first_frame: ""
  anima_prompt_record: ""
  anima_workflow_version: ""
  seed: ""
  dimensions: 864x1152
  visible_characters: []
  continuity_anchors: []
  intended_action: ""
  camera_motion: ""
  environmental_motion: ""
  wan_motion_prompt: ""
  wan_workflow_version: ""

The first-frame image owns appearance, framing, wardrobe, location, props, and starting pose. The Wan motion prompt owns change over time. It must not redesign the frame.

Suno → Palmier

Every approved audio handoff records:

audio_handoff:
  episode: S01E__
  suno_prompt_record: ""
  music_output: ""
  narration_output: ""
  selected_version: ""
  emotional_arc: ""
  spoken_word_tags: []
  edit_notes: ""

Music and narration may be generated as one integrated performance or as separate approved outputs, but the selected structure must be known before Palmier finishing.

Wan and Suno → Palmier

Palmier is the approved finishing environment for all media for now. Each episode hands off:

palmier_handoff:
  episode: S01E__
  palmier_project: ""
  timeline_version: ""
  selected_wan_shots: []
  selected_suno_music: ""
  selected_suno_narration: ""
  edit_order: []
  timing_notes: ""
  revisions: []
  final_output: ""
  final_status: Draft

Palmier owns assembly, editorial timing, shot trimming, audio placement, revision tracking, and the finalized media output. It does not replace the source-generation records for Anima, Wan, or Suno.

Current image baseline

Field Candidate
Orientation Portrait video
Aspect ratio 3:4
Working dimensions 864 × 1152
Board size 12 panels
Storyboard / first-frame model Anima
Image-to-video model Wan 2.2 14B
Music and narration Suno
Finishing environment Palmier (approved interim destination)
Character strategy Distinctive visible anchors + structured prompt inheritance
Review strategy Contact sheet first, individual frames second

Visual acceptance checklist

  • Lumi and Pip are recognizable without relying on labels.
  • Close-ups are genuinely close; the face occupies most of the frame.
  • The sequence includes wide, medium, close-up, ECU, two-shot, OTS, and reverse coverage.
  • Camera position, subject scale, and composition meaningfully change between panels.
  • Style phrasing remains unchanged across the sequence.
  • Location anchors recur without forcing identical backgrounds.
  • Hands, gaze, props, and screen direction support the intended edit.
  • No unexplained duplicate character or wardrobe mutation appears.
  • Every approved frame has a specific, achievable motion plan.
  • Wan preserves the approved first-frame identity, composition, and location.
  • Music and narration support the same emotional beats used by the storyboard.
  • The Palmier timeline references the selected Wan and Suno versions.
  • The final Palmier output can be traced back to every source-generation record.

Known lesson

Model quality alone does not produce a storyboard. Shot type must be expressed as camera geometry and subject scale, and each panel must have a distinct editorial job.