ModelsVideo modelsHappyHorseHappyHorse 1.0 AI Video Generator
HAPPYHORSE 1.0 VIDEO MODEL

HappyHorse 1.0 AI Video Generator

Turn a written scene or a still image into a short video with HappyHorse 1.0, Alibaba’s AI video model. Create character animation, moving scenes and cinematic shots with 3–15 second duration options on WeShop AI.

HappyHorse_10
HAPPYHORSE 1.0 EXAMPLES

HappyHorse 1.0 Video Examples

See a tree grow, an anime character react and a camera follow a motorcycle. Open each example to compare the full prompt with the finished clip and, where used, its input image.

From Seedling to Fruit

A lemon tree grows leaves, blossoms and yellow fruit in a time-lapse sequence. The prompt asks for its life cycle from germination to ripe fruit.

Generate a continuous time-lapse video showcasing the complete life cycle of a lemon tree, from seed germination to fruit ripening. The video should feature realistic natural lighting and detailed visuals.
Use This Prompt

Anime Conversation and Comic Reaction

A sunset conversation turns into an exaggerated reaction with flames and the punchline “NOT FUNNY!”. The prompt combines dialogue, expression and visual effects.

Visual: Vibrant sunset lighting, sharp line art. Action: A girl with a depressed expression says: "Life is so lame, I can't even smile!" The boy's glasses flash with white light: "In that case, you need Western medicine." Girl: "Why?" Boy: "Because Western medicine SMILES!" Suddenly, the background explodes with fire FX. The girl transforms into a "Chibi" angry face and delivers an exaggerated punch/slap with motion blur. Text on screen: "NOT FUNNY!"
Use This Prompt
Reference 1

Follow a Motorcycle Through a Neon Street

One rider image and a short instruction become a moving street scene. The motorcycle travels forward while the camera follows.

The motorcycle sped forward, and the camera followed it.
Use This Prompt
WHAT IS HAPPYHORSE 1.0?

What Can You Create with HappyHorse 1.0?

HappyHorse 1.0 generates video from text and images, with support for cinematic composition, multi-shot storytelling and sound. Use it to develop short story scenes, animated characters, advertising concepts and social clips.

Bring a Scene into Motion

Create a visible change over time or build a shot around a moving subject. The lemon-tree clip shows a growth sequence; the motorcycle clip follows a rider through a street. These are two ways to develop a short visual story.

Give Characters Something to Do

Build a scene around a character’s expression, gesture or reaction. The anime clips show both small facial movements and a larger comic performance—useful starting points for character animation and short narrative scenes.

WORKFLOWS

Create from Text or Animate an Image

Start with the material you have: a written idea for a new scene, or an image you want to animate.

Animate an Image

Upload the image, then describe what should move and how the shot should unfold. In the motorcycle example, the image supplies the rider and street; the prompt asks the motorcycle to move forward and the camera to follow.

Create a Scene from Text

Describe who or what is in the scene, where it takes place and what happens. Add the visual style, dialogue or camera direction your scene needs. The tree-growth and anime-conversation examples both start from text alone.

PROMPT GUIDE

How These HappyHorse 1.0 Prompts Work

Study five original prompts alongside their results. Each example focuses on a different part of a video brief: setting, expression, action sequence, scene objects or camera movement.

Establish the Setting and Action

The rooftop prompt introduces the doll and New York setting, then describes a cane dance as the building lights come on. Use it to see how location and action fit into one scene description.

The Cruella de Milo 3D doll stands atop a New York skyscraper. As the lights in the middle of the building illuminate, the Cruella de Milo 3D doll begins to dance, holding a cane, overlooking the entire city. The camera movement is required to be natural and fluid.

Describe the Expression as Movement

This close-up prompt asks for blinking, a smile and a small head tilt, along with swaying hair. It shows how to describe a character performance through specific visible movements.

Anime style, close-up. The character slowly blinks and gives a soft, charming smile. Head tilts slightly towards the camera. Long teal hair sways gracefully. The background is a soft bokeh of magical light. Focus on maintaining the intricate details of the gemstone crown and clothing. High fidelity, fluid motion, professional anime animation.
Reference 1

Describe What Happens Next

The puppy drinks its cola, then turns back to the computer game. The prompt gives the actions an order rather than listing them as separate scene details.

After finishing his cola, the puppy turned around and started playing games.
Reference 1

Name the Objects That Define the Scene

The oversized cup, eye motifs, laptop and studio backdrop establish this scene. Compare those details with the result and the supplied character image.

{ "image_settings": { "aspect_ratio": "4:5", "resolution": "780/975" }, "prompt": { "scene_and_composition": { "visual_hook": "A surreal juxtaposition of a professional person in a corduroy suit sitting inside a giant, oversized ceramic teacup adorned with realistic human eyes.", "camera_angle": "Eye-level, straight-on studio shot, formal composition.", "framing_and_depth": "Centered medium shot with a shallow depth of field that keeps the subject and the teacup in sharp focus against a flat, smooth, solid blue studio backdrop.", "medium_physics": "Clean, crisp commercial digital photography, high-resolution textures, no motion blur, consistent studio lighting." }, "subject_content": { "identity_features": "Fair-skinned person, lean facial structure, narrow nose, soft jawline, blonde hair styled in a sleek, tight middle-part bun.", "overall_pose": "Sitting upright in a giant cup, legs dangling down, laptop balanced on lap, hands typing.", "limb_articulation": "Arms bent at the elbow resting on the laptop, legs hanging off the edge of the cup, feet wearing clean white sneakers.", "pose_dynamics": "Formal and rigid posture, focus directed forward, conveying a sense of corporate-surrealism.", "makeup_look": "Minimalist, 'no-makeup' makeup, clean skin texture, natural soft brows.", "emotional_vibe": "Detached, surreal, calm, professional, eccentric.", "main_object/apparel": "Muted sage-green corduroy blazer and matching trousers, crisp white button-up shirt, pale pink tie, pearl-bead circular spectacles.", "hair_and_styling": "Hair tightly pulled back, sleek finish, no flyaways.", "interaction_with_environment": "Subject is physically nested inside the giant ceramic teacup, surrounded by small green foliage and delicate pink floral sprigs tucked into the cup edge." }, "environment": { "visual_depth_stack": "Foreground: 1 giant ceramic teacup with 8 realistic human eyes painted on the exterior surface. Midground: 1 professional person sitting, holding a silver laptop, small 5-10 clusters of green leaves and flowers. Background: 1 seamless, solid light-blue studio wall.", "lighting_atmosphere": "Key: Even, diffused softbox lighting from the front; Ambient: Subtle, low-contrast shadows around the base of the cup; Interaction: Soft highlight on the ceramic texture of the cup and a slight sheen on the corduroy fabric." }, "realism_rules": [ "Surreal editorial photography style", "High-fashion conceptual aesthetic", "Studio lighting with no harsh shadows", "Sharp focus on eye details of the teacup", "Matte fabric textures for clothing", "Glossy ceramic finish for the cup" ] }, "negative_prompt": [ "3D render", "cartoon", "painting", "distorted anatomy", "over-saturated colors", "cluttered background", "blurry subjects", "low resolution", "floating limbs", "inconsistent studio lighting", "obvious AI artifacting", "stiff posing" ] }
Reference 1

Give the Camera Its Own Directions

The dance prompt describes the couple’s jive steps, then adds orbit, zoom, pan and low-angle cues. Read the character actions and camera instructions separately when adapting it.

A football-loving couple celebrating a World Cup victory inside a packed sports pub. They burst into an energetic British Jive dance, performing synchronized kicks, spins, side steps, partner turns, rhythmic footwork, playful interactions, and joyful dance moves. Orbit camera, dynamic zoom, whip pan transitions, low-angle hero shots, immersive crowd movement, strong motion parallax, cinematic motion blur.ultra-realistic motion, high-energy festival atmosphere.
HOW TO USE

How to Use HappyHorse 1.0 on WeShop AI

Use the generator at the top of this page to create your clip.

  1. Describe Your Video

    Write the scene and action in the prompt box. Add an image if you want to animate an existing subject or setting; an image is optional.

  2. Set the Length and Frame

    Choose a duration from 3 to 15 seconds, select an aspect ratio and set the quantity. Check the points estimate before submitting.

  3. Generate, Watch and Download

    Watch the result for motion, character details and any text or speech. Download the original video to check the finished clip and its file dimensions.

MODEL SELECTION

HappyHorse 1.0 vs. 1.1: Which Should You Choose?

Both versions create short videos from text or images. HappyHorse 1.1 builds on 1.0 with improvements to movement, instruction following and audiovisual synchronization; the WeShop duration and aspect-ratio choices are the same.

DimensionHappyHorse 1.0HappyHorse 1.1
Model focusCinematic scenes, character animation and audiovisual generationAn upgraded version with improved motion continuity, instruction following and audiovisual synchronization
Input on WeShopText prompt; optional imageText prompt; optional image
Settings on WeShop3–15 seconds; 9:16, 16:9, 3:4, 4:3 or 1:13–15 seconds; 9:16, 16:9, 3:4, 4:3 or 1:1
Model focus
HappyHorse 1.0
Cinematic scenes, character animation and audiovisual generation
HappyHorse 1.1
An upgraded version with improved motion continuity, instruction following and audiovisual synchronization
Input on WeShop
HappyHorse 1.0
Text prompt; optional image
HappyHorse 1.1
Text prompt; optional image
Settings on WeShop
HappyHorse 1.0
3–15 seconds; 9:16, 16:9, 3:4, 4:3 or 1:1
HappyHorse 1.1
3–15 seconds; 9:16, 16:9, 3:4, 4:3 or 1:1

HappyHorse 1.0: Animate Images and Create Short Scenes

HappyHorse 1.1: Complex Motion and Audiovisual Scenes

Consider HappyHorse 1.1 when a scene depends on complex character actions, close adherence to detailed instructions or speech and sound matching the picture. Its upgrades focus on motion continuity, instruction following and audiovisual synchronization.

HappyHorse 1.1: Complex Motion and Audiovisual Scenes
MORE VIDEO MODELS

Explore More AI Video Models

Compare other models that create video from text and images, including Kling 3.0 Omni and Seedance 2.5.

FAQ

HappyHorse 1.0 FAQ

Find answers about inputs, output settings, audio and usage.

What is HappyHorse 1.0?

HappyHorse 1.0 is Alibaba’s AI video generation model. It turns text or images into scenes and supports cinematic composition, multi-shot storytelling and audiovisual generation. On this page, you can start with a text prompt or upload an image.

Do I need to upload an image?

No. Enter a prompt on its own to create a new scene, or upload an image to guide the subject and setting. For example, the lemon-tree clip uses text alone, while the motorcycle clip starts from one image.

How long can the videos be, and which aspect ratios are available?

On WeShop, you can choose a duration from 3 to 15 seconds and an aspect ratio of 9:16, 16:9, 3:4, 4:3 or 1:1.

Can I select 1080P or another resolution?

There is no separate resolution selector in this generator. Download the original video and check its pixel dimensions for the actual output size. The video embedded on this page is a smaller preview.

Can the video include dialogue and sound?

Yes. HappyHorse 1.0 supports generating audio with video, including dialogue and ambient sound. Describe the words or sounds you want in the prompt, then review the voice, sound and lip movements in the result. This form has no separate audio on/off switch.

Should I choose HappyHorse 1.0 or 1.1?

For a new project with no version requirement, start by considering 1.1, especially for complex movement, detailed instructions or audiovisual synchronization. HappyHorse 1.0 also supports text-to-video and image animation, including the short scenes shown here. Both versions offer the same duration and aspect-ratio choices on WeShop.

How is video generation charged?

The generator shows a points estimate for your selected settings and quantity. Review that estimate before submitting, and check the Pricing page for your plan’s model access and allowances.

How do I use an example’s prompt?

Click Copy Prompt to get the complete original English prompt, then paste it into the generator. Change the subject, setting or action for your own scene. For an image-based example, also add the image you want to animate.

Will the result preserve every detail of my image?

An image guides the scene, but faces, clothing, objects and other details can change as the video develops. Review those details along with motion, hands, on-screen text and any dialogue before sharing the result.