Update to PixVerse

{
  "description": "Image generation: create or edit a still image with PixVerse, preserving requested references, model and format. Use for a direct image deliverable.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 253
    }
  ],
  "name": "pixverse-create-image",
  "skill_md_contents": "---\nname: pixverse-create-image\ndescription: \"Image generation: create or edit a still image with PixVerse, preserving requested references, model and format. Use for a direct image deliverable.\"\n---\n\n# Create Images\n\n## Installed Command\n\nBefore running helper commands, resolve the absolute plugin root from this `./SKILL.md` path: it is two directories above this skill directory and contains `.codex-plugin/plugin.json`. In every new shell session, set:\n\n```bash\nPVX=\"<absolute-plugin-root>/scripts/pvx\"\n```\n\nRun helper commands through `\"${PVX}\"`. Do not assume the user's current working directory is the plugin checkout, and do not bypass the installed wrapper with a module invocation.\n\n## CLI Execution\n\nApply `../../skills-shared/quality-policy.md` to all generated images/videos: Sunburst 2K/high,\nSeedance 2.5 1080p with automatic prompt enhancement, and an explicit upgrade/fallback\nchoice for Free/Basic or model-entitlement rejection.\n\nFor an explicitly selected Canvas project or node, read\n`../../skills-internal/pixverse-agent-canvas/SKILL.md` first and follow its Canvas\npreflight and delivery contract; the ordinary queue/local route below does not replace it.\n\nFor ordinary creation or editing, read `../../skills-shared/cli-workflow.md` before\nexecuting this workflow. It contains the existing account-aware routing, paid-work\nconfirmation, progress, preview and project-handoff rules. Studio and Production are\nnot prerequisites. The shared account, confirmation and direct-medium rules govern the\nexamples and defaults below. Read the gateway only when writing manual CLI commands or queue specs.\nCreation command examples below are queue-task fragments, not permission to submit paid\n`pixverse create` commands directly.\n\nUse image generation for standalone stills and as a control layer before video.\n\nFor a simple standalone image, use the shared contract's account-aware `route queue`\nfast path directly. Read `../../skills-shared/prompt-craft.md` for complex composition\nor prompt repair; read `../../skills-shared/model-routing.md` for a custom model,\nunfamiliar parameters or route comparison. The supported default needs neither lookup.\nRead `../../skills-shared/capability-priority.md` when the image is part of a video pipeline.\n\nFor reference roles, image edits and reusable product/brand inputs, read\n`../../skills-shared/extended-capabilities.md` before composing the request.\n\n## Common Outputs\n\n- visual territory boards\n- product hero stills\n- storyboard sheets\n- character sheets\n- item/prop references\n- locked logo/title/final-frame plates\n- posters, KVs, book covers, album covers\n- game/UI mock screens\n\n## Default Command\n\nUse the same high-quality default for final stills, previews and intermediate control art:\n\n```bash\npixverse create image --model gpt-image-2.5-sunburst --quality 1440p --detail-level high --aspect-ratio <ratio> --prompt \"...\"\n```\n\nHere `1440p` is the CLI's 2K tier, while `high` controls rendering detail. Do not reduce\ncontrol boards to 1080p/medium. Respect an explicit user override.\n\nFree/Basic or model-entitlement failure pauses for the subscription/fallback choice in\n`../../skills-shared/quality-policy.md`. Only after the user accepts fallback:\n\n```bash\npixverse create image --model gemini-3.1-flash-lite --quality 1080p --aspect-ratio <ratio> --prompt \"...\"\n```\n\nNano Banana 2 Lite does not accept GPT's detail-level flag. Other image families remain\navailable when explicitly selected; verify their own supported parameters. Read\n`../../skills-shared/pixverse-cli-1.4.4.md` for Flare/Sunburst's expanded detail/ratio\nchoices and Seedream's model-specific quality and reference limits. Use a manual\nqueue for explicit models outside the automatic route helper's image families.\n\nUse uploaded images with `--image` or `--images` when they define the subject, product, character, logo, or layout.\n\n## Image Before Video\n\nPrefer image-first when:\n\n- subject identity matters\n- product packaging matters\n- text/logo must land exactly enough to inspect\n- the user wants multiple concepts\n- video would be expensive to explore blindly\n- a storyboard frame, title card, final packshot, UI plate, or character sheet will control later video\n\n## Video Control Roles\n\nLabel stills by role before using them downstream:\n\n- identity/product anchor\n- storyboard opening frame\n- style reference\n- exact text/logo/UI plate\n- prop/wardrobe/vehicle sheet\n- negative example or rejected route\n\nDo not send an asset sheet as an I2V opening frame when a proper storyboard frame is needed; generate or choose the shot frame first.\n\n## QA When Requested\n\nStandalone images deliver directly after generation and download, with no automatic visual inspection or QA command. If the user requests review or a specialized workflow explicitly requires an anchor check, assess only the requested fit, crop, subject, text or logo constraints.\n"
}