HappyHorse 1.0 Video-Edit
- HappyHorse 1.0 video edit, takes 1 source video and text instructions to perform style transfer, local replacement, etc.
- Optionally accepts 0–5 reference images for style / subject guidance
- Does not support
duration: output video duration =min(input video duration, 15), determined by the model - Does not support
aspect_ratio: output aspect ratio matches the source video - Special billing rule:
(input video duration + output video duration) × resolution unit price; the model truncates inputs longer than 15 seconds to 15 seconds - Asynchronous processing mode, use the returned task ID to query status
- Generated video links are valid for 24 hours, please save them promptly
Authorizations
##All endpoints require Bearer Token authentication##
Get API Key:
Visit the API Key Management Page to obtain your API Key
Add to request header:
Authorization: Bearer YOUR_API_KEYBody
Video generation model name
happyhorse-1.0-video-edit "happyhorse-1.0-video-edit"
Edit instruction text, required
Length limits:
- Chinese: up to
2500characters - Non-Chinese: up to
5000characters - Excess content is automatically truncated
Prompt tips:
- Use editing instructions instead of creative descriptions
- Examples:
Replace the protagonist's clothes with the striped sweater in the image,Replace the video background with snowy mountains
"Have the character in the video wear the striped sweater from the image"
Source video URL to edit, required, only 1 (the first item of the array is taken)
Video requirements:
- Supported formats: MP4, MOV (H.264 encoding recommended)
- Duration:
3~60seconds - The model automatically truncates inputs longer than
15seconds to the first15seconds - Resolution: long edge ≤
2160px, short edge ≥320px - Aspect ratio:
1:2.5~2.5:1 - File size: ≤
100MB - Frame rate: >
8fps - Video URL must be publicly accessible (HTTP or HTTPS); private OSS, intranet, or authenticated links are not supported
Compatible fields: video_url / video are also accepted (lower priority than video_urls)
1 element["https://cdn.example.com/source.mp4"]Reference image URL array, optional, 0 ~ 5 images
Used for style / subject guidance.
Image requirements:
- Supported formats: JPEG, JPG, PNG, WEBP
- Resolution: width and height ≥
300px - Aspect ratio:
1:2.5~2.5:1 - File size: ≤
10MB - Image URLs must be publicly accessible (HTTP or HTTPS)
5["https://cdn.example.com/sweater.jpg"]Whether to keep the original audio of the input video, defaults to false
Options:
true: Keep the original audio of the input videofalse: Discard the original audio; the model generates new audio
false
Video resolution tier, defaults to 720p
Options:
720p: Standard clarity, this is the default1080p: HD clarity
Billing note: Resolution tier directly affects billing
720p, 1080p "720p"
Random seed, default is random
Details:
- Range:
1~2147483647 - A fixed seed reduces parameter-induced variation when iterating on prompts and improves reproducibility
1 <= x <= 214748364742
HTTPS callback URL for task completion
Callback timing:
- Triggered when the task is completed, failed, or cancelled
- Sent after billing confirmation is complete
Security restrictions:
- Only HTTPS protocol is supported
- Callbacks to private IP addresses are prohibited (127.0.0.1, 10.x.x.x, 172.16-31.x.x, 192.168.x.x, etc.)
- URL length must not exceed
2048characters
Callback mechanism:
- Timeout:
10seconds - Up to
3retries after failure (at1/2/4seconds after failure respectively) - Callback response body format is consistent with the task query endpoint response format
- A 2xx status code is considered successful; other status codes trigger retries
"https://your-domain.com/webhooks/video-task-completed"
Response
Video generation task created successfully
Task creation timestamp
1761313744
Task ID
"task-unified-1761313744-h1edgh12"
Actual model name used
"happyhorse-1.0-video-edit"
Specific type of the task
video.generation.task Task progress percentage (0-100)
0 <= x <= 1000
Task status
pending, processing, completed, failed, cancelled "pending"
Video task details
Output type of the task
text, image, audio, video "video"
Usage and billing information