HeyGen Edit Look: retouching an AI avatar, and the Sume route
HeyGen's Edit Look retouches an existing avatar in place. Sume's docs show no such edit, so the route is a new avatar from a retouched photo and a new handle.
Sume's avatar docs do not describe a retouch step for an existing avatar. To change how an avatar looks, retouch your reference photo and create a new avatar from it with a new avatar_handle, then use that handle on later videos. HeyGen's Edit Look does this in place, per its August 2026 update.
What does HeyGen's Edit Look do?
HeyGen describes it as "Post-hoc retouching for existing avatars: clear blemishes, even out skin, soften fine lines, enhance makeup", and says Edit Look "applies at the avatar level, so every video you generate from that avatar inherits the fix". All of this is from HeyGen's own page.
Can I retouch an existing Sume avatar?
The avatar docs show three creation inputs (prompt, props traits and photo) and read routes for listing and fetching avatars. They show no edit or update route for an avatar that already exists, so this post does not claim one.
| Need | HeyGen | Sume |
|---|---|---|
| Retouch an existing avatar | Edit Look, at avatar level | No edit route documented |
| Start from a new look | Not covered here | New avatar from a photo input |
| Reuse across videos | Videos inherit the fix | Reference avatar_handle per video |
How do I make a retouched version?
Retouch the photo in whatever editor you use, host it at a public HTTPS URL, and create a second avatar. Localhost, private-network, non-HTTPS and non-image URLs are rejected before generation.
curl -X POST https://api.sume.com/v1/avatar-1.0/generate \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: avatar-retouched-001" \
-d '{
"avatar_handle": "presenter_retouched",
"input": {
"type": "photo",
"image_url": "https://example.com/presenter-retouched.png"
}
}'What changes for my old videos?
Nothing: finished videos stay as they were, and future ones use whichever avatar_handle you pass.
Sources
Related posts
More in Sume Avatar 1.0
- Shortest video an AI dub or face swap accepts: 5 s vs 4 s
Synthesia's dubbing page says a video must be at least 5 seconds. Sume's Beta face swap plans for about 4-15 seconds and avatar videos take 4-60. Side by side.
- Does a face-swapped video need a YouTube AI disclosure?
YouTube asks for disclosure when content makes a real person appear to say or do something they didn't. What that means for a Sume Beta face-swap output.
- Introducing Sume Avatar 1.0
Sume Avatar 1.0 is a multi-agent orchestration system as a single avatar model.
- Avatar Face Swap API (Beta): apply an avatar face to a video
Avatar Face Swap 1.0 is a Beta Sume endpoint that applies a ready avatar's face to a short public source video. Required fields, limits, and polling.
Written by Sume