Explore short scene and character clips with HappyHorse 1.0, Alibaba’s earlier HappyHorse model. Start with the written or image-led input offered in WeShop.
Explore the tasks shown by these actual HappyHorse 1.0 results. Copy a prompt to try in the generator, or open the linked case for its saved setup. Supply your own images or clips when the request uses references.
Compress a lemon tree’s development into a continuous time-lapse request, using changing growth stages to structure the clip.
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.
Develop an illustrated character scene around a couple and a sunset setting, keeping the anime treatment as part of the visual brief.
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!"
Follow a moving motorcycle with the camera, linking the subject’s forward motion to the shot’s direction.
The motorcycle sped forward, and the camera followed it.
HappyHorse 1.0 is Alibaba’s earlier HappyHorse video model. The page keeps its saved WeShop examples and current settings separate from the later 1.1 release.
The original release establishes HappyHorse 1.0 as an Alibaba video model. This page keeps its own examples separate from later 1.1 output.
WeShop lists text and reference-image starting options for this entry. They support different ways of establishing the scene before describing its motion.
Use the HappyHorse 1.0 input mode that matches the material you have.
Describe the scene and add reference media through the available controls. Identify what each input supplies, such as the subject, setting, motion, or sound.
Describe the subject, setting, action, and camera for a new scene. Match the amount of action to the duration selected in the form.
Learn from the actual instructions behind these results. Each example keeps its complete original prompt and available inputs. For a new request, replace its subject and reference assignments with your own.
Name the camera movement and the part of the subject or environment it should reveal. In this case: “The camera movement is required to be natural and fluid.”
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.
Name the expression or small movement to perform rather than describing appearance alone. In this case: “The character slowly blinks and gives a soft, charming smile.”
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.
Describe what happens first and how the next action or reveal follows it. In this case: “After finishing his cola, the puppy turned around and started playing games.”
After finishing his cola, the puppy turned around and started playing games.
Identify the environmental element that moves while the composition remains recognizable. In this case: “Background: 1 seamless, solid light-blue studio wall.",”
{ "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" ] }
Specify the camera’s route around the subject, rather than leaving the viewpoint implicit. In this case: “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.”
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.
Start in the generator on this page. To reuse an example, click Copy Prompt, return to the description field, and adapt the prompt to your own inputs.
Write your brief and add the reference media required by the selected mode. Explain the role of each supplied input.
Choose an offered duration, aspect ratio, and other available output options. Check the form’s displayed points before submitting.
Click Generate and review the resulting video. Check movement, framing, continuity, and any delivered audio. Adjust your prompt or references for the next attempt.
Compare the documented model roles and the inputs and options currently listed in WeShop. Model names or matching settings do not by themselves establish equal output quality or a fixed generation-time difference.
| Dimension | HappyHorse 1.0 | HappyHorse 1.1 |
|---|---|---|
| Model role | Earlier Alibaba HappyHorse model; no 1.1-only claims | Later model with text-, image-, and reference-led vendor variants |
| Inputs listed for the page | Direct a Scene with References; Build a Scene from Text | Direct a Scene with References; Build a Scene from Text |
| Current WeShop options | Duration: 3–15 seconds | Duration: 3–15 seconds |
Consider 1.0 when its existing case style and input workflow fit your task. Check 1.1 separately for its documented later capabilities.
Open a related model page to review its capabilities, examples, and current generation options.
Answers about this version, its inputs, and how to get started.
HappyHorse 1.0 is Alibaba’s earlier HappyHorse video model. The page keeps its saved WeShop examples and current settings separate from the later 1.1 release.
Consider 1.0 when its existing case style and input workflow fit your task. Check 1.1 separately for its documented later capabilities.
Direct a Scene with References. Describe the scene and add reference media through the available controls. Identify what each input supplies, such as the subject, setting, motion, or sound. Build a Scene from Text. Describe the subject, setting, action, and camera for a new scene. Match the amount of action to the duration selected in the form.
Duration: 3–15 seconds
Click Copy Prompt, return to the generator, and paste it into the description field. Add your own required references and update their roles. Linked case previews and Use This Prompt open the saved case; they do not automatically fill this page’s form.
Detailed original-version documentation is limited. Later 1.1 reference limits or improvement claims are not specifications for 1.0.