Faceless history video with AI: 3 shots, 2 stills, the exact prompts
Seedance 2.0 and Seedream 5.0 Pro prompt on Twistavo, an AI video studio for character swap: replace a person in a real video from 1 to 4 photos; plans from $3.99/month.
Updated
A faceless history short has no presenter on screen: a voiceover carries the story over wide shots of places and objects. On August 5, 2026 we built one about the desert trade routes of the medieval Islamic world. We generated 7 vertical stills with Seedream 5.0 Pro, then 12 vertical clips with Seedance 2.0 from text alone, in two passes, and two voiceover lines with a text-to-speech preset voice. This page shows three of the clips in the order of the story, two of the stills, and what went wrong in the takes we did not keep.
Make your own with Twistavo — 1 free imageSetup
- Model
- Seedance 2.0 and Seedream 5.0 Pro
- Settings
- Order of the short: an establishing shot of the caravan for the hook, the market, then the library, with the voiceover running over all of them. Each shot is a separate Seedance 2.0 text-to-video clip, 9:16, 720p. The first pass made 6 clips from short prompts at the duration shown under each example; the second pass made 6 shorter clips from longer prompts that add a camera move and a symbol for each scene. The clips came with Seedance native sound (wind, market noise, candle crackle) and every prompt ends with "no music", so no music track was used; the clips on this page are muted. The two voiceover lines are each a little shorter than one first-pass clip, in French, made with a preset text-to-speech voice and a style tag that ends with "starts speaking immediately". The stills were not used as start frames: they are separate images of the same scenes, useful as a thumbnail and as a fallback when a clip fails. To assemble: put the voiceover on the timeline first, cut each clip to the length of its sentence, and keep the native ambience under the voice at a low level.
- Models used
- Seedance 2.0, Seedream 5.0
1. Shot 1, the hook: a caravan on the dunes at dusk
- Seedance 2.0, text to video
- Aspect ratio 9:16
- Duration 10 s
- Resolution 720p
- Native audio on (muted on this page)
386 credits in Twistavo
Prompt
Cinematic vertical 9:16 establishing shot. A vast golden desert at dusk, a distant caravan of camels and merchants silhouetted on the dunes, no faces visible. Camera slowly pushes forward, warm amber light, long shadows, dust in the air. Audio: gentle desert wind, distant camel sounds, no music.
Tip: The first two seconds decide whether a viewer stays, and this shot carries almost no motion: the caravan stays a thin line on the horizon for the whole clip. The hook comes from the voiceover, which starts on the first frame. If you want the image to hook too, ask for a closer caravan and a stronger move; the shorter second-pass retake ("pushes forward and rises") brought the camels closer and the sun into frame.
2. Shot 2: the market from above
- Seedance 2.0, text to video
- Aspect ratio 9:16
- Duration 10 s
- Resolution 720p
- Native audio on (muted on this page)
386 credits in Twistavo
Prompt
Cinematic vertical 9:16 shot. A peaceful ancient Islamic souk at golden hour, merchants in robes trading spices and fabrics, seen from elevated angle, no faces visible, warm light. Camera slowly glides. Audio: soft market ambience, quiet voices distant, no music.
Tip: "No faces visible" is a request, not a guarantee: the crowd still has small faces in it. What keeps them unreadable is the elevated angle and the distance. For a faceless format, keep crowds far away and seen from above, and check every frame before you publish.
3. Shot 3: the library
- Seedance 2.0, text to video
- Aspect ratio 9:16
- Duration 10 s
- Resolution 720p
- Native audio on (muted on this page)
386 credits in Twistavo
Prompt
Cinematic vertical 9:16 shot. A grand ancient library with high arches and shelves of old books, warm light streaming through a window, empty, reverent. Camera slowly glides forward between shelves. Audio: soft ambient, faint page rustle, no music.
Tip: "A grand ancient library" came out as a European Gothic hall with pointed windows, in both passes. The model fills a vague place name with the most common picture it knows. Name the architecture and the period you want, for example horseshoe arches, carved wood and tiled floors, instead of "ancient".
4. Still: the same library as an image

- Seedream 5.0 Pro, text to image
- Aspect ratio 9:16
- Resolution 1k
11 credits in Twistavo
Prompt
Cinematic documentary still, 9:16 vertical. A grand ancient library with high arches, shelves of old books and manuscripts, warm light streaming through a window, reverent scholarly atmosphere, completely empty of people. No faces, no text, no watermark.
Tip: A still costs a small fraction of a clip, so we wrote the stills first to check the look of each scene. The still kept the same Gothic arches as the clip: when a still shows the wrong place, fix the words before you pay for the video.
5. Still: the market at golden hour

- Seedream 5.0 Pro, text to image
- Aspect ratio 9:16
- Resolution 1k
11 credits in Twistavo
Prompt
Cinematic documentary still, 9:16 vertical. A peaceful ancient Islamic city marketplace at golden hour, merchants and traders in modest robes trading goods, spices, books and wares, seen from elevated angle, figures in long robes, no faces visible, warm sunlight. Sense of exchange, culture and commerce. No text, no watermark.
Tip: The still has closer figures than the clip, and two merchants in the front are large enough to read. For a thumbnail that is fine; for a faceless channel, push the camera higher or crop.
Shot list
| Shot | Duration | Model | Prompt |
|---|---|---|---|
| Pass 1: Caravan on the dunes (hook) | 10 s | Seedance 2.0, text to video, 9:16, 720p | Cinematic vertical 9:16 establishing shot. A vast golden desert at dusk, a distant caravan of camels and merchants silhouetted on the dunes, no faces visible. Camera slowly pushes forward, warm amber light, long shadows, dust in the air. Audio: gentle desert wind, distant camel sounds, no music. |
| Pass 1: Market from above | 10 s | Seedance 2.0, text to video, 9:16, 720p | Cinematic vertical 9:16 shot. A peaceful ancient Islamic souk at golden hour, merchants in robes trading spices and fabrics, seen from elevated angle, no faces visible, warm light. Camera slowly glides. Audio: soft market ambience, quiet voices distant, no music. |
| Pass 1: Library | 10 s | Seedance 2.0, text to video, 9:16, 720p | Cinematic vertical 9:16 shot. A grand ancient library with high arches and shelves of old books, warm light streaming through a window, empty, reverent. Camera slowly glides forward between shelves. Audio: soft ambient, faint page rustle, no music. |
| Pass 1: Mosque at night | 10 s | Seedance 2.0, text to video, 9:16, 720p | Cinematic vertical 9:16 shot. A majestic mosque with a glowing dome and minaret at night under a starry sky, warm light from within, low angle. Camera slowly tilts up from the courtyard to the dome. Audio: gentle night wind, soft water fountain, no music. |
| Pass 1: Manuscript close-up | 10 s | Seedance 2.0, text to video, 9:16, 720p | Cinematic vertical 9:16 shot. Close-up of an old open Islamic manuscript with gold calligraphy and a quill and inkwell beside it, warm flickering candlelight, dark scholarly ambiance. Camera slowly dollies in. Audio: soft candle crackle, page rustle, no music. |
| Pass 1: Coins and scales | 10 s | Seedance 2.0, text to video, 9:16, 720p | Cinematic vertical 9:16 shot. Close-up of ancient golden coins and scales on a wooden table, warm candlelight, dark ambiance. Camera slowly dollies in toward the scales. Audio: soft coin clink, candle crackle, no music. |
| Pass 2: Caravan on the dunes, retake | 6 s | Seedance 2.0, text to video, 9:16, 720p | Cinematic vertical 9:16 shot. A vast golden desert at dusk, a long ancient caravan of camels and merchants walking over sand dunes seen from a distance, silhouettes only, no faces. Camera slowly pushes forward and rises, warm amber light, dust drifting, long shadows. Slow, majestic, reverent. Audio: gentle desert wind ambience, distant camel sounds, no music. |
| Pass 2: Coins, scales and ledger, retake | 6 s | Seedance 2.0, text to video, 9:16, 720p | Cinematic vertical 9:16 shot. Ancient golden coins, scales and a merchant ledger on a wooden table, warm candlelight, dark scholarly ambiance. Camera slowly dollies in toward the scales, candle flame flickers, light glints off the coins. Symbol of economy and trade. Audio: soft candle crackle, gentle ambient, no music. |
| Pass 2: Library, retake | 6 s | Seedance 2.0, text to video, 9:16, 720p | Cinematic vertical 9:16 shot. A grand ancient library with high arches and shelves of old books, warm light streaming through a window, dust in the air, completely empty. Camera slowly glides forward between the shelves, reverent and scholarly. Audio: soft ambient, no music. |
| Pass 2: Map and astrolabe (left out: modern map) | 6 s | Seedance 2.0, text to video, 9:16, 720p | Cinematic vertical 9:16 shot. An old world map and a brass astrolabe on a desk, warm light, dust motes drifting, dark rich ambiance. Camera slowly pans across the map, astrolabe gently reflecting candlelight. Symbol of knowledge and navigation in the golden age. Audio: quiet ambient, faint page rustle, no music. |
| Pass 2: Manuscript close-up, retake | 6 s | Seedance 2.0, text to video, 9:16, 720p | Cinematic vertical 9:16 shot. Close-up of an old open Islamic manuscript with ornate gold Arabic calligraphy and illumination, an ancient quill and inkwell beside it, warm flickering candlelight, dark ambiance. Camera slowly dollies in toward the page, candle flame gently flickering, dust motes in the light. Scholarly, reverent, timeless. Audio: soft crackling candle, quiet page turning, no music. |
| Pass 2: Mosque at night, retake | 6 s | Seedance 2.0, text to video, 9:16, 720p | Cinematic vertical 9:16 shot. A majestic mosque with a beautiful minaret and glowing dome at night under a starry sky, warm light from within, low dramatic angle. Camera slowly tilts up from the courtyard fountain to the dome and into the starry sky, stars twinkling, peaceful magical atmosphere. Audio: gentle night wind, soft water fountain, no music. |
Make it in Twistavo
- Write the voiceover first: one sentence per shot, and decide the order of the shots (here: caravan, market, library).
- Open the AI Studio in Twistavo, pick Seedream 5.0 Pro, set 9:16 and 1k, and make one still per scene with the still prompts above. Fix the words of any scene that shows the wrong place before you pay for video.
- Pick Seedance 2.0, leave the image slots empty (text to video), set 9:16, 720p, native audio on and the duration given in the shot list, and paste that shot's prompt.
- Check the credit quote before you run it, then repeat for each shot. For tighter cuts, use the shorter second-pass prompts.
- In your editor, put the voiceover on the timeline first, cut each clip to the length of its sentence and keep the native ambience low under the voice.
Variations to try
- Same seven scenes for another period, such as the Silk Road or the Hanseatic ports: change the place and period words, keep the camera and audio lines.
- Give Seedance 2.0 each Seedream still as the start frame, so the clip and the thumbnail match.
- Replace the map shot's prompt with "a hand-drawn medieval map of the Mediterranean and the Indian Ocean": the second-pass map came out as a modern world map.
- Name the architecture in the library prompt (horseshoe arches, carved wood, tiled floors): "a grand ancient library" came out as a Gothic hall in both passes.
Notes
What we would change: the map shot of the second pass (a0daa5d1) showed a modern world map with the Americas, which does not fit a medieval story, so we left it out; ask for "a hand-drawn medieval map of the Mediterranean and the Indian Ocean" instead. Variations to try: the same seven scenes for another period (Silk Road, Hanseatic ports), a shorter cut for each sentence, as in the second pass, or a start frame from each still so the clip and the thumbnail match. Every clip and image on this page was generated with AI on August 5, 2026 with the prompt and settings shown. Results change from run to run.