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)
|
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.
3. API Requests
3.1 Request URL
https://open-api.wondershare.cc/v1/open/capacity/application/tm_text2video
3.2 Request Parameters
Headers:
|
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 }'