happyhorse-1.1-t2v is the text-to-video model in the HappyHorse 1.1 series, designed for creating from scripts, scene concepts, and shot descriptions. It focuses on cinematic lighting, natural motion, and camera movement, and can be used for advertising concept films, e-commerce mood assets, and social short videos. On this platform, enter a text prompt to submit a generation task, then obtain a video link for previewing, selection, and editing.
Submit requests to the public API at api.acedata.cloud using the documented parameters, then use the results in your application.
Input parameters and result formats vary by service. Use the public API for this model and follow its guide for generation, task retrieval and editing operations.
HappyHorse 1.1's public creative positioning and this endpoint's calling specifications are described separately. The durations, aspect ratios, and default values above apply to calls on this platform.
Write subjects, environments, actions, lighting, and camera movements into prompts to build dynamic scenes directly from text. It is suitable for describing single-shot concepts such as a slow push-in in morning light or a person walking down a street, allowing storyboards to first become watchable clips before assessing whether composition and pacing meet expectations.
HappyHorse 1.1 emphasizes cinematic lighting and stable camera movement, making it suitable for short videos that require atmosphere, spatial changes, and subject motion. You can adjust action or lighting descriptions around the same scene to compare visual approaches; complex interactions should still be reviewed shot by shot, and stylistic positioning should not be treated as a guarantee of every result.
Generation tasks can be submitted asynchronously. Applications can save the task_id and query status, or set callback_url to receive completed results. After success, obtain the video_url, duration, and resolution, making it easy to integrate generation, previewing, user selection, and downloading into a single creative workflow.
Enter a shot from an advertising script, specifying the product environment, subject actions, lighting direction, and camera movement to generate a dynamic previsualization for team discussion. It is suitable for validating the opening mood and shot pacing before deciding on filming or post-production plans; when accurate product appearance requires stronger image constraints, use an image creation model instead.
Write scene descriptions around travel, lifestyle, or holiday themes, choose a 9:16 aspect ratio to generate short videos, then add captions, music, and brand information. Each task focuses on presenting one clear action or visual change, making it easier to select assets and combine them into complete social content during editing.
Break a script into individual shots, describe character behavior, scene atmosphere, and camera movement for each segment, and generate concept clips to support discussion. It is suitable for exploring visual directions rather than completing an entire short drama at once; when consistent characters or costumes are needed across shots, shift the task to the reference-image-to-video model in the same series.
When visual assets have not yet been defined and you want to explore visuals directly from text, choose happyhorse-1.1-t2v. If you already have product or character images and want to use one as the first frame, choose happyhorse-1.1-i2v; if you need to use multiple images to constrain characters, props, or style, choose happyhorse-1.1-r2v. The three correspond to different creative starting points, so do not mix up actions and models.
happyhorse-1.1-t2v is the default text-to-video model and is suitable as the starting point for new projects. If you already have prompts and approved sample videos based on happyhorse-1.0-t2v, it is recommended to test them side by side using the same scenes before deciding whether to switch, without assuming a fixed degree of improvement. If the goal is to modify an existing video, choose happyhorse-1.0-video-edit rather than a text-to-video model.
Use prompt to define the subject, action, environment, and shot; this is a text-to-video model and does not automatically switch operations after an image is submitted.
Set model=happyhorse-1.1-t2v and action=generate for /happyhorse/videos. Choose an integer duration of 3–15 seconds and 720P or 1080P; text and reference-image generation can set ratio.
Use async or callback_url to integrate background tasks, save task_id and query /happyhorse/tasks; wait for succeeded before reading video_url, then check characters, actions, and audio.
In a warm kitchen, a person places bread on a plate. The camera slowly pulls back from a close-up to a medium shot, sunlight streams through the window, and the atmosphere feels natural.
Use generate, 720P/1080P, and a clearly specified integer duration. Start with a single scene; check the actions, hands, and sound.
Provide a prompt to start text-to-video generation, using action=generate and model=happyhorse-1.1-t2v. The prompt should clearly describe the subject, environment, action, and camera direction; resolution, aspect ratio, and duration can be set separately according to delivery requirements, and no image needs to be prepared beforehand.
Yes. This entry point supports 16:9, 9:16, 1:1, 4:3, and 3:4, with 16:9 as the default. Choose 9:16 for social short videos and 16:9 for landscape previews; it is best to determine the target aspect ratio before generation to reduce the impact of later cropping on subject placement and composition.
The requested duration can be set to 3–15 seconds, with 5 seconds as the default; supported resolutions are 720P and 1080P, with 1080P as the default. During exploration, you can first use shorter clips to validate motion and composition, then choose the resolution based on presentation needs after the visual direction is confirmed, avoiding stacking too many events into a single clip.
If you only want to explore the environment and advertising atmosphere around the product, T2V is still suitable. If the product appearance and first-frame composition must follow an existing image, prioritize happyhorse-1.1-i2v; when multiple character, prop, or style images jointly participate as constraints, consider happyhorse-1.1-r2v.
You can set async=true, save the returned task_id, and query it through /happyhorse/tasks; you can also provide callback_url to receive completion notifications. Task statuses include pending, succeeded, and error. After success, read video_url to download the video; obtaining a task ID should not be treated as generation completion.
Choose a development approach or application suited to this model and follow its setup guide.
↗Python SDK Integration Guide
SDK installation, authentication and examples↗TypeScript SDK Integration Guide
SDK installation, authentication and examples
↗This is only a basic call example. See the full docs for more parameters and advanced usage.
View Docs