← HeyGenCONTENT HISTORY

Update to HeyGen

Snapshot Oct 28, 2026 · 12:07 UTC · version 4.3.0

Collection source: downloaded plugin package.

WHAT CHANGED

First saved snapshot

No earlier snapshot is available to establish a change.

Save HeyGen 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": "Create and confirm a four-view character identity sheet (face, front, side, back) for one consistent person before HeyGen video generation; the approved sheet becomes the identity reference for every clip. Use when a UGC format skill asks for a character reference sheet, or the user asks for one.",
  "included_files": [],
  "name": "character-reference",
  "skill_md_contents": "---\nname: character-reference\ndescription: Create and confirm a four-view character identity sheet (face, front, side, back) for one consistent person before HeyGen video generation; the approved sheet becomes the identity reference for every clip. Use when a UGC format skill asks for a character reference sheet, or the user asks for one.\n---\n\n# Character Reference\n\nCreate one approved identity sheet so the same person appears in every generated clip. The user sees and confirms the person before any video is generated; this reduces face, body, and wardrobe drift in the final video.\n\n## 1. Inputs\n\nUse the presenter the calling workflow resolved; UGC formats default to someone chosen automatically unless the user supplies or describes a person. Used on its own, ask only if it is missing: \"Who should present this: someone from a quick reference video, someone from a photo, a person you describe, or someone I choose automatically?\"\n\n| Source | Identity authority |\n| --- | --- |\n| Photo or quick reference video | The real adult in the supplied media. Import it once with `import_asset_from_chat` as the calling workflow describes; preserve their recognizable face and build. For a video, use a clear, front-facing frame as the image input and keep the video itself for `reference_videos`. The user must be that person or authorized to depict them; do not depict a public figure otherwise. |\n| Description | The requested adult appearance, clothing, and demeanor. Fill unstated details coherently. |\n| Automatic | A plausible adult suited to the product and audience. Do not add stereotypes, credentials, or a customer history. |\n\nA real person's reference is not voice-cloning or digital-twin consent. Generated people may be invented; products may not. One sheet depicts exactly one adult.\n\n## 2. Write the identity profile once\n\nBefore prompting, write a compact profile and reuse it verbatim in the sheet prompt, any revision, and every downstream video prompt:\n\n- Apparent age range, face shape, eye color, brows, nose, lips, and distinguishing marks.\n- Skin tone and texture, hair color, length, texture, and parting.\n- Height impression, build, and posture.\n- Wardrobe for the ad: each garment, color, fit, footwear, and accessories, including which side each accessory is on.\n\nChoose wardrobe that suits the format and setting. For Try-On, use a muted pre-wear outfit; the garment has its own product sheet. Do not invent logos or readable text on clothing.\n\n## 3. Generate the 4×1 sheet\n\nGenerate with the host's OpenAI image generation, preferring GPT Image 2.5 in its quality-oriented \"sunburst\" variant at high quality; if model or quality selection is not exposed, do not invent parameters or claim a setting was applied, and never stretch the result. Supply real images through the supported image input; a filename in a prompt conditions nothing. If a check fails, regenerate once with one targeted correction from the original inputs, never by editing a drifted output; if that still fails, show it and name the remaining issue. Show the actual sheet, never rejected drafts. When size is selectable, request a wide canvas of four 9:16 columns, such as 2880×1280; otherwise use the widest landscape size offered.\n\nRequest one image, four equal columns, left to right:\n\n1. **Face:** head-and-shoulders close-up, front-facing, neutral relaxed expression.\n2. **Front:** full body, front-facing, arms relaxed.\n3. **Side:** full body in profile. Pick left or right, state it, and keep it across regenerations.\n4. **Back:** full body from behind.\n\nPrompt rules:\n\n- State the sheet's purpose first: a character identity reference sheet, not an advertisement or scene.\n- With supplied media, number the inputs: \"Image 1 is the person to preserve. PRESERVE face shape, features, skin tone, hairline, and build exactly. Do not redesign the person.\" Without supplied media, describe the person entirely from the profile.\n- \"The exact same person, outfit, and hairstyle in every column.\"\n- Plain light-grey seamless background; even, soft, neutral light; shadow only under the feet. Light must not tint the base skin tone.\n- Whole figure inside each column with margin above the head and below the feet; thin plain gutters; nothing crosses a gutter.\n- Natural, healthy skin with an even tone and fine texture that reads only up close; no waxy, airbrushed, beauty-filtered, slimmed, or stretched faces, and no exaggerated pores, blotchy or grey patches, dirt, or freckles, spots, and wrinkles beyond the supplied photo or profile.\n- \"No text, labels, numbers, captions, logos, or watermarks.\" Name the views in your prompt only; never ask for visible panel labels.\n- No props, product, mirrors, or second person.\n\n## 4. Check, then show\n\nLook at the generated sheet before showing it. Check: four complete views in order; one consistent face, skin tone, hair, build, and outfit across columns; side profile in the stated direction; no clipped heads or feet; no text; no extra limbs or people; natural, healthy skin that is neither smoothed nor over-textured. With a supplied photo, compare the face against Image 1.\n\n## 5. Confirm with the user\n\nWhen called from a UGC format, show the sheet in that format's single approval message, beside the script and settings. Used on its own, ask: **\"Is this the person you want in the ad? Approve, or tell me what to change.\"**\n\nFor a change request, also restate the change and update the identity profile before regenerating.\n\n## 6. Hand off the approved sheet\n\n- Lock the approved sheet and profile for the whole production. Do not regenerate the person mid-run; a later identity change needs a new approval.\n- In UGC formats, the approved sheet is an input to each clip's storyboard image, which becomes that clip's only reference image. Paste the identity profile verbatim into every prompt that shows this person, and keep a supplied quick video in `reference_videos`.\n- Only when no storyboard can be used, transfer the approved sheet to HeyGen honestly: use a returned public HTTPS URL only if HeyGen can access it, `import_asset_from_chat` only when the host accepts the returned file object, or the genuine raw-upload workflow. Never treat an OpenAI file identifier as a HeyGen `asset_id`. Record the real `asset_id`; if no transfer path exists, tell the user and continue with the original photos and the identity profile. Send the sheet in `reference_images` (after any product images, and before any supplied photo of the real person) and state: \"Image N is an identity reference only. Show one person in a single full frame; never show panels, split views, grey backgrounds, or multiple copies of the person.\"\n- The sheet's outfit is the default wardrobe. When a shot calls for a different garment, such as Try-On wearing shots, say that the garment comes from the product reference and the sheet controls identity only.\n- Record in the production ledger: source type, profile, sheet version, `asset_id`, and approval.\n"
}

SHA-256 of public snapshot: 2ae60ed410c5b1ea941fb9ceef20461adcdf7bbb14ffdebf5186b38f4dfe4de2