Chinese AI video prompt builder using Alibaba's Wan prompt guide: text to video, image to video and multi-shot, with its lighting and camera terms.
Chinese AI Video Prompt Builder
Write a Chinese video prompt to the formulas in the official Wan prompt guide: text to video, image to video or multi-shot.
How to write a video prompt here
Pick the kind of video
Text to video asks for subject, scene and motion. Image to video asks only for motion and camera movement, because the picture already fixes the subject, scene and style. Multi-shot asks for one overall line, then each shot in order with its length in seconds.
Tap the visual terms
Lighting, shot size, composition, camera angle, colour tone, camera movement and style are buttons, and every term comes from the official prompt guide for Alibaba's Wan video models. They join your description in the order the guide uses.
Add sound if you want it
A line of dialogue is written as 说：“…”, which the guide says the model keeps word for word. You can also tick no dialogue, no background music, or one continuous shot.
Copy each box to its own field
The prompt and the exclusions copy separately. Put exclusions only in your tool's negative-prompt field, never in the prompt itself.
Why it follows the guide's formulas
This page writes prompts to Alibaba Cloud Model Studio's video prompt guide for its Wan models. The guide gives a formula for each job: text to video is subject (with its description) + scene + motion + aesthetic control + style; image to video is only motion + camera movement, because the picture has already decided the subject, scene and style; multi-shot is an overall description, then each shot with its number and timestamp.
The page used to join its fields under Markdown "##" headings, so the heading text was pasted into the model along with the scene, and it wrote "no …" inside the prompt, while the guide defines the prompt as the positive prompt. The prompt is now one continuous description, and exclusions sit in their own box. Every lighting, shot-size, composition, angle, tone, camera-movement and style term on the buttons comes from the guide's term tables.
Other vendors' official guides are not cited on this page, so it does not claim the same wording works equally well in Kling, Jimeng or Hailuo.
Frequently Asked Questions
From Alibaba Cloud Model Studio's video prompt guide for its Wan models: text to video is subject + scene + motion + aesthetic control + style; image to video is motion + camera movement; multi-shot is an overall description, then a numbered, timestamped description of each shot. Every term on the buttons is taken from the guide's term tables.
You can paste it into any of them, but the formulas and terms here are the ones Alibaba documents for Wan. Other vendors' guides are not cited on this page, so check the tool you use.
The guide defines the prompt as the positive prompt: a description of what should be in the video. Things you do not want go in your tool's negative-prompt field instead.
From the seconds you give each shot, added up in order: shot 1 [0-3 seconds], shot 2 [3-6 seconds], the form the guide uses. The total length shows under the list.
No. The prompt is put together in your browser. No model is called and nothing is sent anywhere.
Method & sources
How it computes
In the browser, by a tested kernel. Text to video joins subject, scene, motion, the chosen lighting, shot, camera and style terms, then sound, into one description; image to video gives motion and camera movement only; multi-shot gives an overall line, then 第n个镜头[a-b秒] per shot. All follow Alibaba Cloud's 万相 (Wan) prompt guide. Exclusions come back separately as a negative prompt. No model is called.
What this tool implements
- Corrected 2026-10-19: the page said most Chinese video models render about 5-10 seconds per clip. Current flagships allow 15 to 30 seconds: Kling 3.0, Hailuo 3.0 and Wan 2.7 up to 15 s, Vidu Q3 Pro 16 s, Seedance 2.5 30 s, per RECATOOLS' AI video model specs dataset, where each figure carries the vendor documentation it came from (checked 20-21 August 2026). The advice to keep one action per shot is kept, worded as practice rather than a limit.
- Rebuilt 2026-11-03 in all three languages. The page joined its fields under Markdown "##" headings, so each heading was pasted into the model with the scene, and it wrote the exclusions into the prompt as "不要…", while the 万相 guide defines the prompt as the positive prompt. The prompt is now one description in the guide's order, exclusions come back in a separate negative-prompt box, and image-to-video and multi-shot forms follow the guide's own formulas.
- The clip-length paragraph and the AI video model specs citation were removed with the copy they supported: the page no longer states durations. Other vendors' guides are not cited, and the page says so rather than claiming the wording works equally in Kling, Jimeng or Hailuo.
- Merged 2026-11-03: /chinese-image-to-video-prompt-builder/ now redirects here, to this page's image-to-video mode, which writes the 万相 guide's 运动 + 运镜 formula. The retired page held no list or data to port.
Sources
- Alibaba Cloud Model Studio. 视频生成Prompt指南 (万相): the text-to-video, image-to-video and multi-shot formulas, the fixed phrases 无台词, 无背景音乐 and 生成单镜头, and the term tables every button is taken from. https://help.aliyun.com/zh/model-studio/text-to-video-prompt — read 2026-11-03.
Pick up where you left off
Stored only in this browser — never sent to our servers.