← ImagineArtCONTENT HISTORY

Update to ImagineArt

Snapshot Sep 30, 2026 · 22:47 UTC · version 2.0.0

Collection source: not recorded for this historical snapshot.

WHAT CHANGED · RULE-BASED ANALYSIS

First saved snapshot

No earlier snapshot is available to establish a change.

Compare saved observations

Download comparison JSON
Full technical diff · 0 changed fields
Full snapshot data
{
  "name": "fashion",
  "description": "Fashion photoshoots and fashion motion — lookbooks, editorials, catalogue shoots, runway clips, and animating a look. Use for any request about clothing on models, collections, or campaign imagery. Not for putting a customer's own garment photo onto a person (use Try-On) and not for generic photo effects (use Effects).",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 480
    },
    {
      "relative_path": "assets/ATTRIBUTION.md",
      "size_in_bytes": 935
    },
    {
      "relative_path": "assets/icon.svg",
      "size_in_bytes": 399
    },
    {
      "relative_path": "references/errors.md",
      "size_in_bytes": 2325
    },
    {
      "relative_path": "references/flow.md",
      "size_in_bytes": 1537
    },
    {
      "relative_path": "references/models.md",
      "size_in_bytes": 3809
    },
    {
      "relative_path": "references/qa.md",
      "size_in_bytes": 842
    }
  ],
  "skill_md_contents": "---\nname: fashion\ndescription: Fashion photoshoots and fashion motion — lookbooks, editorials, catalogue shoots, runway clips, and animating a look. Use for any request about clothing on models, collections, or campaign imagery. Not for putting a customer's own garment photo onto a person (use Try-On) and not for generic photo effects (use Effects).\n---\n\n# Fashion\n\nStills and motion, one pipeline. Read `references/flow.md` for the picker sequence and\n`references/models.md` before any video call.\n\n## Tokens\n\n| Token | What it does |\n|---|---|\n| `/lookbook`, `/editorial` | Styled, atmospheric campaign stills — `shoot_type: editorial` |\n| `/catalogue` | Clean, consistent e-commerce stills — `shoot_type: catalogue` |\n| `/runway`, `/animate` | Motion from an existing shoot |\n| `/model`, `/wardrobe`, `/pose` | Jump to one picker on an existing project |\n\n## The one rule that breaks this skill\n\n**Advance exactly one `select_*` call per turn and wait for the answer.** Each picker\nrenders UI and the user's choice comes back as the next message. Chaining two pickers in a\nturn is the most common failure here — it produces a dead widget and a stalled flow.\n\n## Truth and safety gate — clear this before generating\n\nIf any item fails, do not generate and do not route around it.\n\n- **Subject authorization.** Use a generated adult, or a real person the user is authorized\n  to depict. A supplied photo is not permission to impersonate its subject. Decline public\n  figures, minors, and deceptive identity use. If third-party consent is unclear, ask once.\n- **No synthetic testimonials.** A generated person is a model or demonstrator, never a real\n  customer. Do not invent ownership, results, or lived experience.\n- **Transparent framing.** Output is a brand concept or demo, not organic customer content.\n\n## Decide the shoot type first, without asking\n\n`shoot_type` is `catalogue` or `editorial` and carries through every later step.\n\n- \"lookbook\", \"campaign\", \"editorial\", \"moody\" → **editorial**\n- \"catalogue\", \"product pages\", \"e-commerce\", \"consistent\" → **catalogue**\n\nInfer it, state which you picked in one short line, and move on. Don't open with a\nquestion — the pickers already ask plenty.\n\n## Stills\n\nFollow the sequence in `references/flow.md`. The pickers collect their own photos, URLs and\ndescriptions and call the underlying upload and create tools themselves — never call\n`request_image_upload` or `create_fashion_model` to feed a picker.\n\n## Motion\n\nThree paths, cheapest first:\n\n| Request | Tool |\n|---|---|\n| One still, simple movement | `animate_fashion_image` |\n| A named template or a specific runway style | `list_fashion_video_templates`, then generate |\n| A whole look or collection in motion | `fashion_video_shoot` |\n\nTake the cheapest path that answers the request, then offer the richer one.\n\n**Fashion motion is people.** Never open on `seedance-2.5` — it refuses human subjects,\nincluding illustrated ones. Default to `seedance-2.0` at 1080p; fall back to `ltx-2.3`\nat 6s/1080p. See `references/models.md`.\n\n## Second shoots\n\nOnce a project exists, do not rewalk the flow. Ask which single thing changes — pose,\nbackground, wardrobe — re-run that one picker, and generate. This is the most common real\nrequest and it should feel short.\n\n## Conventions\n\nIds returned by pickers are internal. Never print `org_id`, `folder_id`,\n`fashion_project_id`, or raw asset uuids.\n\n## When something fails\n\nRead `references/errors.md`. Identify the kind of failure before responding: pending jobs\nare waited on, technical errors retried at most twice, unsupported capabilities stated\nplainly, safety refusals never routed around, and every material change disclosed.\n\n## QA before delivery\n\nRun `references/qa.md` before calling this finished. Inspect the actual output — never\nclaim quality you have not observed, and say plainly what you could not verify.\n"
}

SHA-256: bef84c4029d18e3b1bc2824c305d75eee9528947271016c4c2a4fcc67b81b4c4