Happy Horse 1.0 Video Edit is Alibaba's video editing model on Versely. This page is its structured prompting reference: the 5 parameters its schema actually exposes, the video-edit technique that applies to it, copy-ready templates.
Everything here is grounded in the same sources Versely's agent reads — the model's input schema. Where a line is general craft advice rather than a documented fact about Happy Horse 1.0 Video Edit, the page says so.
What Happy Horse 1.0 Video Edit wants
The exact input surface, from the same schema the Versely agent fetches with get_model_input_schema before every generation.
| Parameter | What it does | Values |
|---|---|---|
video_urlreq | Source video (3-60s, mp4/mov, ≤100MB) | string |
promptreq | Edit instruction (max 2500 chars; references @Image1...@Image5) | string (max 2500) |
image_urls | Up to 5 reference images. fal field is `image_urls`. | array (max 5) |
audio_setting | Audio handling: auto (model decides) or origin (preserve source) | auto · origindefault: auto |
resolution | Resolution | 720p · 1080pdefault: 1080p |
- — Verified against fal.ai/models/alibaba/happy-horse/video-edit
Technique that applies here
Video-to-video editing/restyle/segmentation: instruction-style prompts over an input video
- Every model in this family operates ON an existing video, but 'prompt' means four different things across the four pages: an edit instruction (Happy Horse 1.0 Video Edit, Wan 2.7 Video Edit), an object selector (SAM 3 Video Segment — its prompt's schema description is literally 'Text prompt selecting the object to segment'), an optional guiding note on a motion transfer (Wan 2.2 14B Move), or nothing at all (Lucy Restyle, whose only published creative control is a style enum: Realistic / Artistic / Anime at 720p). Identify which of the four you're writing before you write anything.
- For the instruction-style editors, write the CHANGE, not the scene. Happy Horse's prompt field is described as an 'Edit instruction (max 2500 chars)' and lets you anchor the edit to visual references with @Image1...@Image5 tokens tied to its image_urls array (up to 5). Wan 2.7 Video Edit gives you up to 5,000 characters of edit instruction — optional per its docs — plus a 500-character negative_prompt and an optional reference_image. Re-describing the entire frame from scratch is the classic failure here: general instruction-editing technique says name what changes and leave the rest implied by the source video.
- Source-video constraints are schema facts, not guidelines. Happy Horse's video_url takes 3-60 second mp4/mov files up to 100MB. Wan 2.7 Video Edit's duration parameter documents 0 = full source duration, with 2-10 to override. Check the clip against the input contract before you polish the instruction.
- Audio handling is an explicit enum on both instruction editors: audio_setting is auto ('model decides') or origin ('preserve source') on Happy Horse, and Wan 2.7's docs describe the same auto/origin pair. If the original soundtrack must survive the edit, set origin — leaving the default hands the decision to the model.
Copy-ready templates
Replace the bracketed slots; each template says when it's the right shape.
Change [ELEMENT TO EDIT — e.g. 'the jacket the presenter wears'] to match @Image1. Keep [WHAT MUST SURVIVE — framing, identity, background] unchanged. audio_setting: [auto / origin]
Use when: Happy Horse 1.0 Video Edit — an edit instruction (max 2,500 chars) anchored to up to 5 reference images via the schema's own @Image1...@Image5 tokens, on a 3-60s mp4/mov source under 100MB.
[ONE-SENTENCE EDIT INSTRUCTION — what changes], [STYLE KEYWORD]. negative_prompt: [what must not appear, ≤500 chars]. duration: [0 for full source / 2-10 to override] | audio_setting: [auto / origin]
Use when: Wan 2.7 Video Edit — plain instruction plus a style keyword is the register the Wan family tip rewards; the schema adds a real negative_prompt, an optional reference_image, and prompt_extend if you want the documented LLM rewrite to expand a minimal instruction.
How the Versely agent does this automatically
You can use this page by hand, or let the agent apply the same knowledge. Four real mechanisms — no more, no less:
get_model_input_schema— before generating, the agent looks up Happy Horse 1.0 Video Edit's exact input fields, required fields, allowed values, defaults, and min/max bounds. The parameter table above is that same surface.- The prompt enhancer's family rules — 12 per-family rewrite rules (this model's family isn't one of the 12, so only general enhancement applies) shape how a rough prompt gets rewritten.
- The per-provider speech guide — for TTS scripts, the agent follows a provider-specific tag scheme — not relevant to this model, but it's why voiceover scripts come out marked up correctly.
expand_movie_scene— in movie flows, brief scene ideas are rewritten into detailed cinematic descriptions before generation.
Mistakes that waste generations
- Writing a full scene description instead of an edit instruction. The source video already defines the scene — general instruction-editing technique is to state only the change ('replace the background with...', 'make the shirt match @Image1') and what must stay fixed.
- Feeding Happy Horse a source outside its input contract — the schema takes 3-60 second mp4/mov files up to 100MB via video_url; longer or heavier clips fail before any prompt quality matters.
- Expecting the original soundtrack to survive by default — audio_setting on both Happy Horse and Wan 2.7 Video Edit is an explicit auto/origin choice, and only origin is documented as preserving the source audio.
Frequently asked questions
How long can a Happy Horse 1.0 Video Edit prompt be?+
Happy Horse 1.0 Video Edit's schema caps the prompt at 2,500 characters. Spend them on the subject, motion, and the register its family rewards rather than restating parameters the schema already controls.
Does Happy Horse 1.0 Video Edit support negative prompts?+
No — Happy Horse 1.0 Video Edit's published schema has no negative_prompt parameter. Exclusions have to be phrased positively inside the main prompt, or dropped.
How does the Versely agent know Happy Horse 1.0 Video Edit's parameters?+
Before generating, the agent calls its get_model_input_schema tool, which looks up the exact input fields, required fields, allowed values, defaults, and min/max bounds for the model. Nothing on this page is guessed — it is the same schema surface those tools read.
Related prompting guides
Generate with Happy Horse 1.0 Video Edit
Happy Horse 1.0 Video Edit is live in Versely — paste a template above, or just describe what you want and let the agent map it onto the schema for you.