Question 1

What is Happy Horse Video Edit?

Accepted Answer

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.

Question 2

How much does Happy Horse Video Edit cost on Runflow?

Accepted Answer

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

Question 3

What source videos are supported?

Accepted Answer

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.

Question 4

How long does an edit take?

Accepted Answer

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.

Question 5

Can I use Happy Horse output commercially?

Accepted Answer

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

Question 6

Do I need to manage GPUs or infrastructure?

Accepted Answer

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.

Parameter	Type	Required	Description
prompt	string	required	Text prompt describing the desired edit. Reference any supplied reference images using @Image1, @Image2, ... up to @Image5. Max 2500 characters.
video_url	video	required	URL of the source video to edit. Formats: MP4, MOV (H.264 recommended). Duration: 3-60 s. Longer side ≤ 2160 px, shorter side ≥ 320 px. Aspect ratio between 1:2.5 and 2.5:1. Frame rate > 8 fps. Max 100 MB. The output video preserves the source aspect ratio. Output duration matches the input video, capped at 15 s (longer inputs are truncated to the first 15 s).
audio_setting	string	optional	Audio handling. 'auto': model decides whether to regenerate audio. 'origin': preserve the original audio from the input video.
enable_safety_checker	boolean	optional	Enable content moderation for input and output.
reference_image_urls	image_list	optional	Optional reference images used to guide the edit (up to 5). Formats: JPEG, JPG, PNG, WEBP. Dimensions must be at least 300px. Aspect ratio between 1:2.5 and 2.5:1. Max 10 MB each.
resolution	string	optional	Output video resolution tier.
seed	integer	optional	Random seed for reproducibility (0-2147483647).

Field	Type	Description
outputs	json	Unified output array — one entry per generated artifact with url/type/width/height/duration/etc.
seed	json	Deterministic seed used for generation, or null if the provider doesn't return one.
timing	json	Provider timing info (inference_ms etc.), or null.
nsfw_detected	json	true if the provider flagged output as NSFW, false if cleared, null if not checked.

alibaba/happy-horse/video-edit

Install

Run the model

Input schema

Output schema

Related models

Start generating with Happy Horse Video Edit