Pick a portrait built for motion
Use a front-facing image with even light, visible eyes and a relaxed expression. Leave a little space around the head and shoulders so the framing has room to move naturally.
A presenter-led clip usually needs a camera, a quiet room and several takes. DomoAI reduces that setup to one well-lit portrait plus a script or voice track, so a founder, teacher or creator can publish a clean talking video without booking a shoot.

Every DomoAI workflow starts from a prompt and an optional reference file. Nothing has to be rebuilt by hand.
Use a front-facing image with even light, visible eyes and a relaxed expression. Leave a little space around the head and shoulders so the framing has room to move naturally.
Keep sentences short and conversational. Where the workflow supports audio, use a clean recording with no background music; the avatar needs a clear voice signal to match mouth movement and timing.
Watch for unnatural jaw movement, frozen eyes or drift in the background. Generate another take if needed, then export the clip and add captions, B-roll or branded end cards in the editor.
DomoAI workflows differ by the material you already have. Pick the one that matches it.
| Workflow | What you provide | Good for |
|---|---|---|
| AI avatar video | One portrait plus a script or voice track | Presenter clips with a consistent face |
| AI spokesperson video | A brand presenter image and a product brief | Product explainers and sales messages |
| Talking avatar | A portrait with dialogue or audio | Short social messages and character voices |
| AI video lip sync | Existing footage plus a new audio track | Matching new dialogue to a clip you already shot |
Answers about inputs, limits, resolution, and how credits are used.
No. The workflow starts from a still portrait. A clear front-facing photo with even lighting is more useful than a low-resolution webcam frame.
Use a clean voice recording where the workflow accepts audio, or add narration in post. Keep the track free of music and room echo so the mouth movement has a clear signal to follow.
Extreme angles, hands near the face, heavy shadows and oversized accessories can confuse the animation. Start with a simple head-and-shoulders portrait and keep the first script short.
Yes, if you have the right to use the likeness and the message is presented honestly. Disclose synthetic presenters where required and keep the final claims accurate.
Every new account starts with 100 welcome credits, valid for 30 days, so you can test this workflow before choosing a plan.