ToMoviee AI Is Now on Mobile!
Get App

1. Overview

1.1 Service Capabilities

ToMoviee Text-to-Video transforms your ideas into dynamic visuals from simple text input, enabling precise generation of 5-second videos. You can choose between Standard Mode for balanced quality and speed in everyday use, or HD Mode for cinematic-quality detail and clarity. The platform supports a wide range of aspect ratios, including 9:16 (vertical), 16:9 (horizontal), 1:1 (square), and professional formats like 3:4 and 4:3, making it ideal for short videos, film marketing, e-commerce ads, and more. The model seamlessly blends realism by incorporating real-world physics principles (e.g., lighting dynamics, gravity) with cinematic camera techniques (e.g., dolly, pan, tilt, orbit), ensuring every frame is visually coherent and narratively rich.

At the heart of the creative process lies the prompt, the key to communicating with ToMoviee. The quality of your video output depends directly on the effectiveness of your prompt. As a next-generation text-to-video model, ToMoviee continues to evolve. Unlocking its full potential requires the deep exploration of both physics principles and camera movement techniques. To support this, we have introduced the ToMoviee Prompt Formula, a structured method that helps you precisely control video output by combining camera instructions, physical properties, and visual elements. Users who are new to prompts can start quickly with the built-in example library, while creators with proficiency can experiment with complex scene setups. This empowers you to master ToMoviee and lead the AI video revolution.

1.2 Sample Prompts and Outputs

prompt

A little bee resting in a flower, close-up 

Wide shot of a boy with headphones, lying back on a bed listening to music in a cozy, tidy room. The camera zooms in on his calm, closed-eyed face 

Video 

2Prompt engine

The core components of the ToMoviee Prompt Formula are Subject, Motion, and Scene, which are also the basic building blocks of a video. To enhance detail in the subject and scene, simply add short descriptive phrases to specify what you want to see. Wondershare ToMoviee AI will expand and interpret these elements to generate the final video.

Prompt = Subject (+ Subject Description) + Motion + Scene (+ Scene Description) + (Camera Language + Lighting + Atmosphere)

  • Subject: The main element in the video, representing the core of the visual theme. For example, people, animals, plants, or objects.
  • Subject Description: Details about the subject’s appearance and posture, expressed through multiple short phrases. For example, movement style, hairstyle and color, outfits, facial features, and body posture.
  • Motion: Describes the movement or stillness of the subject. Motions should be simple and realistic, suitable for depiction within a 5-second video.
  • Scene: The environment in which the subject is placed, including both foreground and background elements.
  • Scene Description: Detailed descriptions of the setting, using several short phrases. Descriptions should remain concise and visually achievable within a 5-second video. For example, indoor, outdoor, or natural settings.
  • Camera Language: Refers to how shots are composed, connected, and transitioned to tell a story or evoke emotion. For example, extreme long shots, bokeh effects, close-ups, telephoto lens shots, ground-level angles, top-down shots, drone footage, and depth of field. Note that camera language is distinct from camera movement or motion control.
  • Lighting: A critical element that brings life to the visual. Thoughtful use of lighting adds depth and emotion to the video. For example, ambient lighting, morning light, sunset glow, light and shadow interplay, the Tyndall effect, and studio lighting.
  • Atmosphere: Defines the mood or tone of the video, such as a lively setting, cinematic color grading, or a warm and pleasant feeling.

Consider this example: starting with the simple prompt “A Shiba Inu is running through a flower field.” You can enhance it by adding specific subject and scene details: “An orange Shiba Inu is joyfully running through a sunflower field, sunlight shining on its fluffy fur, wearing a red polka-dot scarf around its neck. The golden sunflowers sway gently in the breeze, with rolling green hills and a blue sky dotted with white clouds in the background.” This level of detail provides ToMoviee with greater control, resulting in a more vivid video output. Building on this, you can further incorporate cinematic techniques and lighting/atmosphere elements: “Low-angle shot, shallow depth of field, backlighting. An orange Shiba Inu runs freely across an endless sunflower field, its fur glowing gold in the sunlight. A red polka-dot scarf flutters in the wind. The camera alternates between close-up shots of flower petals and the dog’s movement. In the background, a Dutch windmill appears faintly, adding narrative depth to the scene. Cinematic color grading applied.” This highly detailed prompt significantly improves video quality and can even produce exceptional results.

Basic Version

A Shiba Inu is running through a flower field.

Enhanced Version with Details

An orange Shiba Inu is joyfully running through a sunflower field, sunlight shining on its fluffy fur, wearing a red polka-dot scarf around its neck. The golden sunflowers sway gently in the breeze, with rolling green hills and a blue sky dotted with white clouds in the background.

Professional-Level Version

Low-angle shot, shallow depth of field, backlighting. An orange Shiba Inu runs freely across an endless sunflower field, its fur glowing gold in the sunlight. A red polka-dot scarf flutters in the wind. The camera alternates between close-up shots of flower petals and the dog’s movement. In the background, a Dutch windmill appears faintly, adding narrative depth to the scene. Cinematic color grading applied.

Tips

  • Use simple words and sentence structures; avoid overly complex language.
  • Keep motions physically realistic and consistent with what could happen in the scene.
  • If descriptions deviate too far from the image, it may trigger unintended scene transitions.
  • Currently, it is challenging to accurately generate complex physical motions such as bouncing balls or objects thrown from heights.

Parameter Name 

Value 

Required

Example 

Description 

Content-Type

application/json

Yes 

X-Prod-Id

Yes 

Product ID. 

X-User-Id

Yes 

User WSID. 

Body:

Parameter Name 

Type 

Required 

Default Value 

Description 

Other Info 

prompt

string

Yes 

Prompt text, which can be in both Chinese and English. Recommended format: Subject + Motion + Camera Description. Length: Up to 1,000 characters. For optimal results, English prompts should be under 200 words. 

camera_move_index

integer

No 

Camera movement control type: 1: "orbit", 2: "spin", 3: "pan left", 4: "pan right", 5: "tilt up", 6: "tilt down", 7: "push in", 8: "pull out", 9: "static", 10: "tracking", 11: "others", 12: "object pov", 13: "super dolly in", 14: "super dolly out", 15: "snorricam", 16: "head tracking", 17: "car grip", 18: "screen transition", 19: "car chasing", 20: "fisheye", 21: "FPV drone", 22: "crane over the head", 23: "timelapse landscape", 24: "dolly in", 25: "dolly out", 26: "zoom in", 27: "zoom out", 28: "full shot", 29: "close-up shot", 30: "extreme close-up", 31: "Macro shot", 32: "bird's-eye view", 33: "rule of thirds", 34: "symmetrical composition". 

callback

string

No 

Callback URL. 

params

string

No 

透明参数

resolution

string

No 

Video resolution. Valid values: 720p (default) and 1080p. 

duration

integer

No 

Video length. Unit: seconds. Valid value: 5 (default). 

aspect_ratio

string

No 

Video aspect ratio. Valid values: 16:9 (default), 9:16, 4:3, 3:4, and 1:1. 

drive

string

No 

If you use cloud storage for video/image output, this field is required in JSON format. video_path will return a file ID. Example: { "space_id": 11111, // Cloud storage space ID "file_dest_path": "/path/sss", // Cloud storage destination path (directory) "file_tag": [ // File tags { "key": "key1", "value": "value1" }, { "key": "key2", "value": "value2" } ] } If this field is not provided, the video_path field in the response will return a downloadable URL. 

Response parameters:

Parameter Name 

Type 

Required 

Default Value 

Description 

Other Info 

code

integer

Yes 

Error code. 

msg

string

Yes 

Error message. 

data

object

No

Notes: 

task_id

string

No

Task ID. 

3.3 Response
{ "code": 0, "msg": "success", "data": { "task_id": "tm_text2video_customize-0-20250528334d445da6cf7cb7591b9292", "wsid": 0, "priority": 1, "status": 3, "reason": "success", "progress": 1, "position": -1, "wait_time": 91, "params": "tongyiemo", "result":"{\"video_path\":[\"fileId or url\"]}" } }
3.4 Sample Requests
curl --location 'https://open-api.wondershare.cc/v1/open/capacity/application/tm_text2video' \ --header 'X-Prod-Id: 14958' \ --header 'X-User-Id: 578608264' \ --header 'Content-Type: application/json' \ --data '{ "prompt": "Generate reading videos", "wsid": 578608264, "units_value": 1, "drive": "Cloud storage parameters", "duration": 5, "resolution": "1080p", "aspect_ratio": "16:9", "params": "asdfasdf111", "callback": "http://www.baidu.com", "priority": 0 }'