Happy Horse Video Edit

HappyHorse video editing supports advanced video editing through natural language instructions. It allows for local or global editing of video elements using up to 5 reference images.

By Alibaba

Pricing: $0.28 per second

Overview

Happy Horse Video Edit transforms an existing clip with **natural-language instructions** — no masks, no keyframes, no manual rotoscoping. Describe the change you want (recolor a sky, swap a season, restyle the whole scene); attach up to 5 reference images for visual anchoring; get back a re-rendered clip that preserves the source's motion and aspect ratio.

Key capabilities

• **Prompt-driven editing**: "recolor the sky to a deep purple sunset," "convert to film noir," "add cherry blossoms throughout" — global or local edits in one shot
• **Reference image support**: include up to 5 reference images and call them as `@Image1`-`@Image5` in your prompt for visual fidelity
• **Source-faithful**: aspect ratio is preserved; output duration matches input (longer-than-15s inputs truncate to the first 15s)
• **Audio control**: keep, replace, or strip the source audio via the `audio_setting` parameter
• **Wide input range**: MP4/MOV (H.264 recommended), 3-60s, ≤2160px long side, ≥320px short side, >8 fps, ≤100MB

Family

Part of the Happy Horse family — pair with the variants when you need a different starting modality:

| Variant | Input | Use it for |

|--------|-------|-----------|

| Text-to-Video | text prompt | one-shot clips from a brief |

| Image-to-Video | image + optional prompt | animating a still or hero shot |

| Video Edit | source video + edit prompt | transforming an existing clip (style, scene swap) |

| Reference-to-Video | text + 1-9 references | multi-character scenes, brand-consistent subjects |

Tech specs

• **Resolutions**: 720p, 1080p
• **Source video**: MP4/MOV, 3-60s, ≤2160px long side, ≥320px short side, >8 fps, ≤100MB
• **Output duration**: matches input, capped at 15s
• **References**: up to 5 images, callable as `@Image1`-`@Image5` in the prompt
• **Audio**: configurable via `audio_setting`
• **Latency**: 90-240s typical (longer than text-to-video due to source decode + re-render)
• **Pricing**: $0.28/s at 720p, $0.56/s at 1080p — input/output seconds are billed together, simple per-second billing

Examples

• Cosmic nebula (source: jellyfish-1080)
• Purple sunset (source: pexels-853874)
• Watercolor (source: pexels-2099568)
• Teal-and-orange (source: pexels-3015527)
• Anime stylize (source: pexels-1093659)
• Golden amber (source: jellyfish-1080)
• Film noir (source: pexels-853874)
• Cherry blossoms (source: pexels-3015527)
• Morning fog (source: pexels-1093659)
• Heavy snow (source: pexels-2099568)

Frequently asked questions

What is Happy Horse Video Edit?

Happy Horse Video Edit transforms an existing video using natural-language instructions — recolor a sky, swap a season, change the visual style — without masks or keyframes. You can attach up to 5 reference images and call them by index (`@Image1`-`@Image5`) inside the prompt to anchor the edit visually.

How much does Happy Horse Video Edit cost on Runflow?

$0.28 per second of output at 720p, and $0.56 per second at 1080p. Both input and output seconds are billed together, so the rate covers the full edit pipeline. A 5-second 720p edit costs $1.40.

What source videos are supported?

MP4 or MOV (H.264 strongly recommended), 3-60 seconds, longest side ≤2160px, shortest side ≥320px, frame rate >8 fps, file size ≤100MB. Output duration matches the input, capped at 15 seconds — longer inputs are truncated.

How long does an edit take?

Typical latency is 90-240 seconds, longer than text-to-video because the model decodes the source clip and re-renders frame by frame. Reference-image-heavy prompts can be slower. Runflow routes for fastest available capacity.

Can I use Happy Horse output commercially?

Yes. All output generated through Runflow is licensed for commercial use — ads, content, products, internal tools.

Do I need to manage GPUs or infrastructure?

No. Runflow runs the GPUs, queues the work, and handles failover. Submit an HTTP request, get a result. No GPU procurement, no AI team required.

Related models

• Happy Horse Reference-to-Video, Generate 1080p video with synchronized native audio from a text prompt and references. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.
• Happy Horse Image-to-Video, Alibaba's #1-ranked Happy Horse 1.0 — generate 1080p video with synchronized native audio and multilingual lip-sync from text prompts or images.
• Happy Horse Text-to-Video, Generate 1080p video with synchronized native audio from a text prompt. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.

Discoverable surfaces

• Dispatch endpoint: POST https://api.runflow.io/v1/models/happy-horse/video-edit/runs
• Per-model spec (markdown): https://app.runflow.io/models/happy-horse/video-edit/llms.txt
• Docs page: https://docs.runflow.io/models/happy-horse/video-edit
• Public OpenAPI spec: https://docs.runflow.io/api/openapi.public.json
• Agent skill (start here): https://www.runflow.io/.well-known/agent-skills/runflow/SKILL.md