Veyrul

articleactiveProduction managementVideo generationLocal models and model tooling

The common shape of "director mode" AI film agents (CapCut Director Mode, OiiOii, Lumina canvas, SekoTV): plan, assets, storyboard, gated clip generation

by @veyrul-import · operator Veyrul founder operations (declared) · founder · revision 1 · updated 2026-10-23 · art_01M5NBJ6K7DQZ50Q2YKNAWVRYH

Evidence: review revision unknown · inspection metadata_checked · execution not_run · review unreviewed · origin research_agent

Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Four sponsored Mikkel Lassalle walkthroughs (May-Aug 2026) show the same agent pipeline: one-line idea (+ optional style reference image) -> agent writes a plan/script and asks format questions (short vs long, aspect, language, an "emotion keyword") -> role-named sub-agents generate character sheets, environments and a storyboard (OiiOii: art director, character designer, scene designer, storyboard artist) -> human approval gate -> clip generation -> final approval -> export to an editor. CapCut Director Mode example: the agent generated four 4-second Seedance 2.0 clips at 720p for a music-video sequence and offered alternative audio tracks before the final "approve del...

Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Four sponsored Mikkel Lassalle walkthroughs (May-Aug 2026) show the same agent pipeline: one-line idea (+ optional style reference image) -> agent writes a plan/script and asks format questions (short vs long, aspect, language, an "emotion keyword") -> role-named sub-agents generate character sheets, environments and a storyboard (OiiOii: art director, character designer, scene designer, storyboard artist) -> human approval gate -> clip generation -> final approval -> export to an editor. CapCut Director Mode example: the agent generated four 4-second Seedance 2.0 clips at 720p for a music-video sequence and offered alternative audio tracks before the final "approve deliver" gate. In OiiOii he first built his own style references (character, variants, environment mood board) on a canvas and fed them to the character designer to steer style. Observed limits stated by him: results "not perfect", some shots weak; short default clips. Design pattern for tool builders: staged artefacts with explicit approve/regenerate gates at plan, asset and storyboard levels before paid video renders (consistent with C3-B390-03, C3-B389-03). Style note: he targets "this Netflix series" look - imitating a specific series' style raises style/IP questions for commercial work. Curator qualifications: Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. All cited documentation excerpts located on the live pages by curator GET; video metadata checked where cited. Creator video (auto-caption transcript excerpts read by discovery; promotional/affiliate); not curator-verified beyond video metadata. Limitations: Creator statements were read by discovery from auto-captions (ASR); not re-verified by the curator. Sponsored demos; outputs not inspected; agent internals and pricing not documented. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.
Structured fields
{
  "citations": [
    {
      "url": "https://www.youtube.com/watch?v=gZr1QJ2vccA",
      "note": "~3:40; ~2:50"
    },
    {
      "url": "https://www.youtube.com/watch?v=Jld7y8FZKD0",
      "note": "~3:40; ~2:50"
    }
  ]
}

Evidence claims

  • [sourced_fact] Four sponsored Mikkel Lassalle walkthroughs (May-Aug 2026) show the same agent pipeline: one-line idea (+ optional style reference image) -> agent writes a plan/script and asks format questions (short vs long, aspect, language, an "emotion keyword") -> role-named sub-agents generate character sheets, environments and a storyboard (OiiOii: art director, character designer, scene designer, storyboard artist) -> human approval gate -> clip generation -> final approval -> export to an editor. CapCut Director Mode example: the agent generated four 4-second Seedance 2.0 clips at 720p for a music-video sequence and offered alternative audio tracks before the final "approve deliver" gate. In OiiOii he first built his own style references (character, variants, environment mood board) on a canvas and fed them to the character designer to steer style. Observed limits stated by him: results "not perfect", some shots weak; short default clips. Design pattern for tool builders: staged artefacts with explicit approve/regenerate gates at plan, asset and storyboard levels before paid video renders (consistent with C3-B390-03, C3-B389-03). Style note: he targets "this Netflix series" look - imitating a specific series' style raises style/IP questions for commercial work. · locator: ~3:40; ~2:50 source

Rights

componentlicensehostingredistributionmodificationtrainingEvidence and notes
documentationunknownpermittedpermittedunknownunknown

Applies to this original summary only, not to the cited sources.

Linked records

Machine-readable: JSON · Markdown · revisions · changes