# Wan 3.0 prompt guide

URL: https://dreambench.ai/guides/wan-3-0-prompt-guide

To write a Wan 3.0 prompt, follow Alibaba’s order: one overall line for the theme and mood, then each shot with its seconds (subject, scene, motion, camera), then the dialogue as Name says: “…”, the sound effects and music, the style, and last a short list of what must not appear. Skip any part you don’t need.

Written and reviewed by the DreamBench team. Published 2026-11-01; updated 2026-11-01.

## Wan 3.0 prompts at a glance

- **The formula:** Overall description, references, timed shots, dialogue, effects and music, style and mood, negative list.
- **One generation:** 2 to 30 seconds on Alibaba’s platform; clips of 3 to 12 seconds in a DreamBench film.
- **Shots:** Numbered with their seconds, 2 to 5 seconds each, or “one continuous shot”.
- **Sound:** Dialogue, effects and music made with the picture; always on at DreamBench.
- **On DreamBench:** Film Studio, 1:1, 16:9, 9:16 or 4:3, 720p or 1080p; every clip starts from an opening frame.

The formula is from Alibaba’s [Wan 3.0 prompt guide](https://www.alibabacloud.com/help/en/model-studio/wan3-video-generation-prompt-guide). For the model, see the [Wan 3.0 page](https://dreambench.ai/models/wan-3.0).

## The Wan 3.0 prompt formula

Alibaba says one sentence is enough for Wan 3.0, and the more precise the description, the closer the result. Its full formula has seven parts, in one paragraph; leave out any you don’t need.

**Overall description → references → shots → dialogue → sound → style → negatives**

|  | What it does | Strong | Weak |
|---|---|---|---|
| Overall description | Theme, point of view and pacing in a line. | A quiet family drama, 15 seconds, pacing from tense to warm. | A nice video. |
| References | Which upload is what. | The grandmother’s look follows Image 1. | Use my pictures. |
| Shots | Each moment with its seconds. | Shot 1 (00:00-00:05): medium shot, she opens the letter, hands trembling. | She reads a letter and reacts. |
| Dialogue | Who speaks, how, and the words. | The grandmother whispers: “He wrote back.” | She says something emotional. |
| Effects and music | What is heard besides speech. | Paper rustling, a clock ticking; no background music. | Good sound. |
| Style and mood | Art style, color tone and mood. | 35mm film look, warm amber tones, tender and hopeful. | Cinematic, 8K, masterpiece. |
| Negative list | Only what must not appear. | No subtitles, no watermark. | No bad quality, no ugly, no blur, no errors. |

1. Open with one line on the theme, the point of view, the length and the pacing.
2. If you upload pictures, say what each is for: “the girl in Image 1 stands in the room of Image 2”.
3. Write each shot with its seconds: the subject, the scene, the motion and the camera.
4. Add the dialogue as Name says: “…”, then the sound effects and the music, or “No background music”.
5. Finish with the art style, color tone and mood, then a short negative list.

## One continuous shot or timed shots in Wan 3.0

Wan 3.0 can tell a story in several shots inside one clip. Alibaba’s format is a number, the seconds and the content: “Shot 1 [0-3s] …”. The shots meet end to end, with no gaps or overlaps, at 2 to 5 seconds each; its API guide suggests 4 to 6.

**What to write for each kind of shot**

|  | Write |
|---|---|
| One shot, no split | “One continuous shot” on the first line. |
| A still camera | “Fixed shot, camera static, position unchanged.” |
| A cut between shots | “Hard cut” or “dissolve” at the end of a shot. |
| A shot that runs on | “Continue from the last frame of the previous segment.” |
| Pacing | In the overall line: “brisk build-up, sudden conflict, warm ending”. |

> On DreamBench, a Wan 3.0 clip doesn’t cut to a new setting partway through: each clip is written as one continuous shot, and a change of place comes at the next clip.

## Wan 3.0 camera and lens prompts

Alibaba asks for camera moves in plain words and allows a lens and depth of field. Put the move inside the shot it belongs to.

**Camera words for Wan 3.0, and how to write them**

|  | What it does | How to write it |
|---|---|---|
| Fixed | Holds still; the action carries the shot. | Fixed shot, camera static. |
| Push in | Moves closer. | The camera pushes in very slowly to her eyes. |
| Pull out | Moves back to reveal the place. | The camera pulls back and rises over the harbor. |
| Orbit | Circles the subject. | The camera orbits 120 degrees around him. |
| Handheld follow | Walks with the subject, with a slight sway. | Handheld follow behind her through the crowd. |
| Telephoto | A close, flattened view, soft background. | 85mm telephoto, shallow depth of field. |
| Wide-angle | A broad view, everything sharp. | 24mm wide-angle, deep focus, low angle. |
| Slow motion | Stretches a fast moment. | High-speed photography, 1000fps slow motion. |

Alibaba warns against actions faster than the model can control, such as “shaking head 3 times per second”. Give a motion a pace a person could act.

## How to write dialogue, sound effects and music for Wan 3.0

Wan 3.0 makes speech, effects and music in the same pass as the picture. See [native audio](https://dreambench.ai/glossary/native-audio).

*Diagram: Picture and sound come from one generation: the prompt’s lines, effects and music are made with the frames.*

- Dialogue: the character, a speaking verb, a colon and the line in quotes: she whispers: “Not yet.”
- Several speakers: one line each, in order, each with its speaker.
- Narration: Voiceover: “Every morning starts here.”
- Silence: write “No dialogue”, or the model decides by itself whether anyone speaks.
- Effects: describe what makes the sound, such as rain on a tin roof or boots in a puddle, and Wan adds it; or give an effect its own sentence and time: “From the 8th second, a church bell.”

**Alibaba’s three levels of music control**

|  | What to write | What happens |
|---|---|---|
| Leave it open | Nothing about music. | The model chooses. |
| Ask for it | “A soft cello enters slowly under the last line.” | That music, in that place. |
| None | “No background music.” | Only ambience and the sounds of the action. |

Alibaba’s Wan 3.0 pages list no dialogue languages; its examples speak English and Chinese. Name the language before a line, and check each take. See [lip sync](https://dreambench.ai/glossary/lip-sync).

## Style, mood and the Wan 3.0 negative list

Alibaba groups the look into three parts, art style, color tone and mood, said at the start or the end: “clay animation, high-saturation warm yellow, light and healing”.

- List only what you don’t want, and leave the list empty if there is nothing.
- Don’t pad it or repeat what the prompt already says.
- Typical lines: no subtitles, no watermark, no extra fingers, no face distortion, no frequent shot cuts.
- For an animated style, rule out the other look: “no photorealistic live-action”.

## What fits in a Wan 3.0 clip: 5, 15 and 30 seconds

Alibaba’s platform takes 2 to 30 seconds, or a smart length the model picks. Write as much as the seconds hold:

**How much a Wan 3.0 clip holds**

|  | What fits | Prompt length |
|---|---|---|
| 2 to 6 seconds | One action and its result, or one short line. | 30 to 80 words |
| 7 to 15 seconds | Two or three shots, or a short exchange. | 80 to 200 words |
| 16 to 30 seconds | Five to eight shots, a scene with a turn and an ending. | 200 to 450 words |

In a DreamBench film each Wan 3.0 clip runs 3 to 12 seconds, as long as its action takes, and DreamBench writes its prompt to fit.

## Wan 3.0 image to video: first and last frames

Wan 3.0 can start from a first frame, or run between a first and a last frame. Alibaba says the picture already fixes the subject, the scene and the style, so the prompt describes the motion, the plot, the dialogue and the camera. See [first and last frame](https://dreambench.ai/glossary/first-and-last-frame).

1. Give the picture as the first frame, or the first and the last.
2. Describe what happens next, shot by shot with times if there are several, without repeating what the picture shows.
3. Add the lines and the sound; for a last frame, describe the change that leads to it.

On Alibaba’s platform, first and last frames can’t be mixed with reference pictures in one request. On DreamBench, every Wan 3.0 clip starts from an opening frame made from your references. See [image to video](https://dreambench.ai/glossary/image-to-video).

## Keeping characters the same in Wan 3.0

On Alibaba’s platform, uploads are numbered in order, with images, videos and audio counted separately: Image 1, Video 1 and Audio 1 can all exist. Alibaba’s advice is to give each a purpose, so features don’t bleed between people.

- Lock each subject to one upload: “the little girl is Image 2, the shop is Image 1”.
- Describe each character in the same words in every shot and every clip.
- Keep the clothes, the props and the light from shot to shot.

On DreamBench, each character, place and prop is drawn once as a sheet, and every clip’s opening frame is made from the sheets it needs. See [character consistency](https://dreambench.ai/glossary/character-consistency) and [reference to video](https://dreambench.ai/glossary/reference-to-video).

## From one idea to a Wan 3.0 film

On Alibaba’s platform one Wan 3.0 clip can hold eight timed shots. On DreamBench, a film is several clips, each one continuous shot from its own opening frame, joined at hard cuts, so any one can be redone.

*Diagram: One idea, several clips: a scene plan, each clip its own generation, hard cuts at the joins, one clip redone while the rest are kept.*

**One idea, planned as Wan 3.0 clips**

|  | What the clip shows | Length | What carries over |
|---|---|---|---|
| Clip 1 | A fisherman unties his boat in a harbor at dawn | 8 s | His orange oilskin, the gray light |
| Clip 2 | Out at sea, he hauls in an empty net and sighs | 10 s | The oilskin, the boat |
| Clip 3 | Back on the quay, his daughter hands him a flask; he laughs | 10 s | The boat behind them, the light now warmer |

[Describe the film](https://dreambench.ai/) on DreamBench and it writes every clip’s prompt, draws the cast and has Wan 3.0 animate each clip. See [multi-shot video](https://dreambench.ai/glossary/multi-shot-video).

## Wan 3.0 prompt examples to copy

Each follows Alibaba’s order. Paste one into Alibaba’s platform, or use it as a DreamBench brief; change the subject, keep the shape.

#### One continuous shot: the harbor at dawn

One continuous shot. A fishing harbor at dawn, calm and quiet, 10 seconds. The camera glides low over the water toward a red boat as a fisherman in an orange oilskin coils a rope and looks up at the sky. Gulls, water lapping at the hull, a distant engine. No dialogue. No background music. Documentary realism, cool blue tones warming to gold, peaceful.

#### A three-shot drama

A short drama about forgiveness, 12 seconds, pacing from tense to warm. Shot 1 (00:00-00:04): medium shot, fixed camera; a young man stands at a farmhouse door, holding a cake box. Shot 2 (00:04-00:08): hard cut, close-up, 85mm telephoto; his father opens the door, unsmiling. Shot 3 (00:08-00:12): the father steps aside and says: “Your mother kept your seat.” Wind, a dog barking far off. 35mm film look, muted greens, tender. No subtitles.

#### Two speakers in a lift

One continuous shot, 8 seconds, light office comedy. Inside a mirrored lift, a woman in a navy suit and a courier with a tall stack of boxes. Fixed shot, camera static. The courier says: “Which floor?” She glances at the boxes and replies: “All of them, apparently.” The lift hums and pings. No background music. Bright, clean light, natural color.

#### A product with a voiceover

A product film for a steel water bottle, 10 seconds, calm and confident. Shot 1 (00:00-00:05): the bottle on wet rock by a waterfall, mist drifting, the camera orbiting slowly. Shot 2 (00:05-00:10): a hand fills it from the stream and closes the cap with a click. Voiceover: “Cold for a day. Built for a lifetime.” Rushing water, the cap’s click. Soft acoustic guitar under the voice. Clean commercial look, cool greens.

#### Sport with no dialogue

One continuous shot, 8 seconds. A sprinter in a white tank top bursts out of the blocks on a wet track under floodlights and runs toward the camera. Handheld follow at running pace, low angle. Spikes on the track, her breathing, rain. No dialogue. No background music. Realistic sports-broadcast look. No slow motion.

#### A music cue: rooftop violinist

One continuous shot, 15 seconds, dreamy and romantic. A violinist in a long gray coat plays on a Paris rooftop at dusk, chimneys and the city behind her. The camera pulls back and rises slowly. A slow solo violin melody that builds as the lights of the city come on. Wind in her hair. No dialogue. Warm pink and blue dusk tones.

#### Clay animation

Clay animation, high-saturation warm yellow, light and healing, 10 seconds. Shot 1 (00:00-00:05): a small clay bear in a striped scarf waters a single sunflower on a windowsill. Shot 2 (00:05-00:10): the flower blooms in three soft bounces and the bear claps. Squelchy clay footsteps, a happy chime. No dialogue. No photorealistic live-action, no extra limbs.

#### From a first frame

Continue the market scene from the first frame, 8 seconds, one continuous shot. The spice seller lifts a scoop of saffron, lets it fall back into the sack and smiles at a customer, who says: “Two hundred grams, please.” The camera pushes in slowly. Market chatter, a scale clicking. No subtitles.

#### First and last frame: a sketch that comes to life

One continuous shot, 10 seconds, from a pencil sketch of a horse (first frame) to a real horse galloping in a field (last frame). The pencil lines thicken, color floods in from the edges, and the horse breaks into a gallop as the paper becomes grass. The camera pulls back slowly. Pencil scratching, then hooves and wind. No background music.

#### Two references

A warm bakery morning, 10 seconds. The baker’s look follows Image 1; the bakery follows Image 2. Shot 1 (00:00-00:05): fixed shot, she pulls a tray of croissants from the oven. Shot 2 (00:05-00:10): close-up, she breaks one open and steam rises; she says: “Perfect.” Crackling pastry, the oven door. No background music. Golden morning light. No extra people, no costume changes.

#### A 30-second story

A comic short about a lost umbrella, 30 seconds, brisk build-up and a warm ending. Shot 1 (00:00-00:05): wide shot, rain on a city square; a man’s umbrella blows away. Shot 2 (00:05-00:10): handheld follow as he chases it past a café. Shot 3 (00:10-00:15): it lands at the feet of a girl in a yellow raincoat. Shot 4 (00:15-00:20): she holds it out and says: “Is this yours?” Shot 5 (00:20-00:25): he nods, soaked. Shot 6 (00:25-00:30): they share it; the camera pulls back and rises. Rain, wind, a light jazz piano. Bright, saturated color. No subtitles, no watermark.

## Weak Wan 3.0 prompts, rewritten

Most weak Wan prompts leave a part to chance: the seconds, the speaker or the sound.

**Three weak prompts and their strong versions**

|  | Weak | Strong | What changed |
|---|---|---|---|
| A story | A cat running on the grass. | A playful short, 8 seconds. Shot 1 (00:00-00:04): low angle, a ginger cat sprints across a meadow. Shot 2 (00:04-00:08): it pounces on a butterfly and misses. Grass rustling. No dialogue. Bright spring light. | An overall line, timed shots, sound and a look. |
| A line | Two people talk about the weather. | One continuous shot. At a bus stop, an old man says: “Rain again.” The young woman beside him smiles and replies: “It suits the city.” Rain on the shelter. No background music. | Speakers and their words, in Alibaba’s pattern. |
| A list | Epic, 8K, masterpiece, no bad hands, no blur, no ugly, no errors. | 35mm film look, cold blue tones, tense. No extra fingers. | Quality tags became a style; the negative list kept one real risk. |

## Common Wan 3.0 prompt mistakes and how to fix them

**Wan 3.0 prompt mistakes and fixes**

|  | What goes wrong | Fix |
|---|---|---|
| Shots with gaps | “0-3s”, then “5-8s”: the timing slips. | Make each shot start where the last one ends. |
| Unwanted speech | Someone talks in a clip meant to be quiet. | Write “No dialogue”. |
| Unwanted music | A score you didn’t ask for. | Write “No background music”. |
| Too-fast actions | “Shaking head 3 times per second” breaks. | Give a pace a person could act. |
| A padded negative list | The list repeats the prompt or adds noise. | List only real risks. |
| Describing the first frame | The words repeat the picture. | Describe motion, plot, lines and camera. |
| Long on-screen text | Alibaba says text is still improving. | Keep words on screen short, and check them. |

## What a Wan 3.0 prompt can’t fix

- One prompt run twice gives two clips.
- Alibaba says Wan 3.0’s audio texture and the accuracy of on-screen text are still improving.
- One generation stops at 30 seconds.
- A real person or product can’t be known from words; it takes a picture you have the right to use.
- On DreamBench, Wan 3.0 always makes sound, and its clips don’t cut to a new setting mid-clip.

## Wan 3.0 prompts on DreamBench

- A film: [describe it](https://dreambench.ai/), add up to 8 reference pictures and pick Wan 3.0. DreamBench writes each clip’s prompt, makes its opening frame, has Wan 3.0 animate it with sound and joins the clips; redo any one with a note.
- Settings: 1:1, 16:9, 9:16 or 4:3, 720p or 1080p, on every plan.
- Not offered: the Video page, which takes models that start from words alone; Alibaba’s numbered references, documents, editing and extension; a silent clip.

The [AI video prompt generator](https://dreambench.ai/tools/ai-video-prompt-generator) writes a prompt in this order for any model. The price in credits shows before you generate; the first time, create a free account and choose a plan. For a prompt sent as typed, see the [Seedance 2.5](https://dreambench.ai/guides/seedance-2-5-prompt-guide) or [Kling 4.0](https://dreambench.ai/guides/kling-4-0-prompt-guide) guides; for prompts from words alone, [text to video](https://dreambench.ai/glossary/text-to-video).

## Questions

- **How do you write a prompt for Wan 3.0?** To write a Wan 3.0 prompt, follow Alibaba’s order: an overall line for the theme and mood, each shot with its seconds, the dialogue as Name says: “…”, the effects and music, the style, then a short negative list. Skip the parts you don’t need; one sentence also works.
- **What is a good Wan 3.0 prompt example?** One continuous shot. A fishing harbor at dawn, 10 seconds. The camera glides low over the water toward a red boat as a fisherman coils a rope. Gulls, water lapping. No dialogue. No background music. Documentary realism, cool blue tones. It has a shot, an action, sound and a look.
- **How do I write multiple shots in a Wan 3.0 prompt?** Number each shot and give it its seconds: Shot 1 (00:00-00:03), Shot 2 (00:03-00:06). Alibaba says the shots should meet end to end, with no gaps or overlaps, at 2 to 5 seconds each. Write “hard cut” or “dissolve” where shots join.
- **How do I make Wan 3.0 do one continuous shot?** Write “One continuous shot” on the first line of the prompt, as Alibaba’s guide says, keep one place and one camera move, and leave out shot numbers. On DreamBench, every Wan 3.0 clip is written as one continuous shot.
- **How do I write dialogue for Wan 3.0?** Write the speaker, a speaking verb, a colon and the line in quotes: she whispers: “Not yet.” For several people, give each line its own speaker, in order. For narration, write Voiceover: “…”. For silence, write “No dialogue”, or the model may add speech.
- **Does Wan 3.0 have a negative prompt?** Alibaba’s formula ends with a negative prompt list written inside the prompt. Keep it to what you don’t want, such as no subtitles, no watermark or no extra fingers, and don’t repeat what the prompt already says. Leave it out if there is nothing.
- **How do I add or remove music in Wan 3.0?** Write nothing and Wan 3.0 chooses the music; describe it, such as “a soft cello under the last line”, to ask for it; or write “No background music” for only ambience and action sounds. These are Alibaba’s three levels of music control.
- **How long can a Wan 3.0 video be?** Wan 3.0 makes 2 to 30 seconds in one generation on Alibaba’s platform. In a DreamBench film, each Wan 3.0 clip runs 3 to 12 seconds, and the clips are joined into one video.
- **How do I write a Wan 3.0 image-to-video prompt?** From a first frame, describe the motion, the plot, the dialogue and the camera, not what the picture already shows. Alibaba says the picture fixes the subject, the scene and the style. With a last frame too, describe the change that leads to it.
- **How do I keep a character the same in Wan 3.0?** On Alibaba’s platform, upload a picture of the character and tie it to them: “the girl is Image 2”. Describe each character in the same words in every shot. On DreamBench, each character is drawn once as a sheet, and every clip starts from it.
- **Can I use Wan 3.0 on DreamBench?** Yes, in Film Studio. Describe the video and add reference pictures: DreamBench plans the clips, makes an opening frame for each and has Wan 3.0 animate it with sound, at 720p or 1080p. It isn’t on the Video page, because on DreamBench Wan 3.0 starts every clip from a picture.

## Sources

- [Alibaba Cloud Model Studio: wan3.0 Video Generation Prompt Guide](https://www.alibabacloud.com/help/en/model-studio/wan3-video-generation-prompt-guide), Alibaba Cloud: read 2026-11-01
- [Alibaba Cloud Model Studio: wan3.0 video generation](https://www.alibabacloud.com/help/en/model-studio/wan3-video-generation-guide), Alibaba Cloud: read 2026-11-01
- [Alibaba Cloud: Wan3.0, 30-second AI video generation from any input](https://www.alibabacloud.com/blog/wan3-0-30-second-ai-video-generation-from-any-input_603452), Alibaba Cloud: read 2026-11-01

DreamBench is an independent platform and isn’t affiliated with or endorsed by the companies named on this page.