← FXI StudioCONTENT HISTORY

Update to FXI Studio

Snapshot Oct 24, 2026 · 13:35 UTC · version 1.1.0

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save FXI Studio and check future changes in Following.

Up to 10 plugins free · no card required.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "description": "Use when the user wants a short film, multi-shot scene, or sequence of clips with continuous motion through FXI Studio. Teaches the stills-first, frame-chained workflow instead of generating disconnected one-off video clips.",
  "included_files": [],
  "name": "direct-a-film",
  "skill_md_contents": "---\nname: direct-a-film\ndescription: Use when the user wants a short film, multi-shot scene, or sequence of clips with continuous motion through FXI Studio. Teaches the stills-first, frame-chained workflow instead of generating disconnected one-off video clips.\n---\n\nUse this skill whenever the request implies more than one shot: \"short film\",\n\"scene\", \"sequence\", \"chain these shots\", \"continuous motion\", or when a single\ngenerate_video result would not satisfy what the user described.\n\n1. Break the request into 2 to 8 shot descriptions before calling any generation\n   tool. Confirm the shot count and the aspect ratio with the user in the first\n   turn if neither is stated — do not default silently to 16:9 when the user\n   describes a short vertical film, reel, or story.\n2. Generate an opening still for shot 1 with `generate_image` (optionally with a\n   reference image uploaded via `upload_from_url` / `upload_media_data` /\n   `create_upload_url` + `confirm_upload`) to lock composition, character identity,\n   and wardrobe before any video call.\n3. For every shot after the first, generate a keyframe still for where the next\n   shot should end, using the previous still as the reference image. Pass\n   continuity details explicitly in the prompt (costume, armor, hair, framing) —\n   do not let the video model invent or change them.\n4. Call `frame_chain` with each scene's `target_frame_uri` set to the matching\n   keyframe still, or `compose_scene` when the user wants a scene built from their\n   saved characters (look them up first with `list_characters`).\n5. Poll `get_task` until the task finishes, then show the result inline. Do not\n   report success before the task is actually complete.\n6. If continuity drifts between shots (face, costume, or environment changes\n   without being asked for), say so plainly and offer to regenerate the keyframe\n   that drifted rather than presenting a broken chain as finished.\n\nDo not skip straight to a multi-shot `frame_chain` without keyframe stills when\nthe user needs a specific character, costume, or environment to stay consistent\nacross shots — unkeyframed chains are the most common cause of identity and\ncostume drift.\n"
}

SHA-256 of public snapshot: 92d621425b4a66614f8fc541b0ed51b2f81650e2e791309bde81d5f9ab482d25