Happy Horse 1.0 Video Edit API

alibaba/happyhorse-1.0/video-edit

Happy Horse 1.0 Video Edit transforms existing source footage through natural-language prompts and optional reference images, supporting 3–60s input video, 720p or 1080p output, and flexible audio modes. It faithfully inherits underlying motion topology and camera trajectory while accurately rendering targeted wardrobe, material, and stylistic restyling.

Input

Prompt

249/2500

Source video

Drag and drop files, paste from clipboard, or provide a URL.

Reference images

Drag and drop files, paste from clipboard, or provide a URL.

Resolution

Audio setting

Seed

Safety checker

Output

Idle

Your generated video will appear here

Add your prompt and required media, review the settings, then click Run.

Continue with

Happy Horse 1.0 Text to Video Happy Horse 1.0 Image to Video Happy Horse 1.0 Reference to Video

Examples

Restore this archival greenhouse footage to match @Image1: repair the broken glass panes, clear the overgrowth, and let morning sunlight fill the structure while keeping the original camera move, no text, no logos, no watermark, no promotional marks

Make rain fall through the paper theater scene, tiny paper raindrops drifting past the layered buildings while the cool evening light deepens, keep the handcrafted paper texture, no text, no logos, no watermark, no promotional marks

Lift the fog gradually to reveal the harbor in warm golden hour light, boats becoming crisp as the sun breaks through, water reflections warming, keep the original camera drift, no text, no logos, no watermark, no promotional marks

REST API

Quick Start

Authenticate via API Key, submit source video and editing instructions, and retrieve video via task ID.

Connect to Vidgo API

Create an API Key, store it securely on your server, and set Authorization: Bearer VIDGO_API_KEY.

Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authentication: Authorization: Bearer VIDGO_API_KEY

Submit a Video Edit Task

Pass source video in video_url, describe modifications in prompt, and set model to alibaba/happyhorse-1.0/video-edit.

Submit Request

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "alibaba/happyhorse-1.0/video-edit",
  "input": {
    "prompt": "Restore this archival greenhouse footage to match @Image1: repair the broken glass panes, clear the overgrowth, and let morning sunlight fill the structure while keeping the original camera move, no text, no logos, no watermark, no promotional marks",
    "resolution": "1080p",
    "audio_setting": "auto",
    "video_url": "https://cdn.vidgo.ai/apis/models/alibaba/happyhorse-1.0/video-edit/v1/01/input-source.mp4",
    "reference_image_urls": [
      "https://cdn.vidgo.ai/apis/models/alibaba/happyhorse-1.0/video-edit/v1/01/input-01.png"
    ]
  }
}
JSON
)

RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

CODE=$(printf '%s' "$RESPONSE" | jq -r '.code // empty')
if [ "$CODE" != "0" ] && [ "$CODE" != "200" ]; then
  printf 'API error: %s
' "$RESPONSE" >&2
  exit 1
fi
printf '%s
' "$RESPONSE"

Await Results

Poll with task_id while status is not_started or running. Stop at finished or failed; read data.files[].file_url on success or data.error_message on failure.

Track Status

GET https://api.vidgo.ai/api/generate/status/{task_id}

Poll every 2 seconds, backing off for extended jobs. Continue only while not_started or running. Alternatively provide callback_url.

not_startedrunningfinishedfailed

Submit Response

{
  "code": 200,
  "data": {
    "task_id": "task-unified-...",
    "status": "running",
    "created_time": "2026-09-17T10:00:00Z"
  }
}

Completed Response

{
  "code": 200,
  "data": {
    "task_id": "task-unified-...",
    "status": "finished",
    "files": [
      {
        "file_url": "https://storage.vidgo.ai/generated/video.mp4",
        "file_type": "video"
      }
    ],
    "created_time": "2026-08-22T10:00:00Z",
    "progress": 100,
    "error_message": null
  }
}

Complete Runnable Example

Expand to inspect complete code including status checks, task_id validation, polling, and timeout boundaries.

Complete Runnable Example

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "alibaba/happyhorse-1.0/video-edit",
  "input": {
    "prompt": "Restore this archival greenhouse footage to match @Image1: repair the broken glass panes, clear the overgrowth, and let morning sunlight fill the structure while keeping the original camera move, no text, no logos, no watermark, no promotional marks",
    "resolution": "1080p",
    "audio_setting": "auto",
    "video_url": "https://cdn.vidgo.ai/apis/models/alibaba/happyhorse-1.0/video-edit/v1/01/input-source.mp4",
    "reference_image_urls": [
      "https://cdn.vidgo.ai/apis/models/alibaba/happyhorse-1.0/video-edit/v1/01/input-01.png"
    ]
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
BUSINESS_CODE=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.code // empty')
if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
  printf 'Submit failed:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

START_TIME=$(date +%s)
POLL_DELAY=2
while true; do
  if [ $(( $(date +%s) - START_TIME )) -ge 600 ]; then
    printf 'Timed out after 600 seconds
' >&2
    exit 1
  fi
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')
  BUSINESS_CODE=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.code // empty')
  if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
    printf 'Status request failed:
%s
' "$STATUS_RESPONSE" >&2
    exit 1
  fi

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep "$POLL_DELAY"
      if [ "$POLL_DELAY" -lt 10 ]; then POLL_DELAY=$((POLL_DELAY + 1)); fi
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Input Parameters

Available request parameters, data types, and default values. The top-level model field is also required.

Field	Type	Required	Default	Description
video_url	string	Yes	—	String. Publicly accessible source video URL. Supports 3–60 seconds duration.
prompt	string	Yes	—	Required, nonblank, and at most 2,500 characters. Describe the edits, optionally with reference images.
reference_image_urls	array	No	—	String array. Up to 5 reference image URLs, described in the prompt using natural language.
resolution	string	No	1080p	String. Output resolution. Supports 720p and 1080p.
audio_setting	string	No	auto	String. Audio policy: auto (regenerates audio) or origin (preserves source audio).
seed	integer	No	—	Integer. 0 to 2147483647 for reproducible generation foundations.
enable_safety_checker	boolean	No	—	Boolean. Enables content safety moderation for inputs and outputs.

Response Fields

Task submission returns a task_id; status queries yield lifecycle progress and video assets.

Field	Type	Description
code	integer	Business response code, 200 on success.
data.task_id	string	Unique task identifier used to track and poll progress.
data.status	string	Lifecycle state: not_started, running, finished, or failed.
data.progress	integer	Generation completion percentage (0–100).
data.files[].file_url	string	Public URL of the generated video asset.
data.files[].file_type	string	File type string, e.g., video.
data.error_message	string \| null	Failure details when status equals failed.

Task Lifecycle

Continue polling while in not_started or running. Conclude when finished or failed is reached.

not_started
Task is accepted in the queue and awaiting execution.
running
Generation is actively in progress. Continue polling.
finished
Task completed successfully. Read video from data.files[].file_url.
failed
Generation failed. Read data.error_message and stop polling.

Polling & Error Handling

AuthenticationIf HTTP 401 is returned, verify the Bearer API key in the Authorization header.
ValidationIf HTTP 400 is returned, verify required parameters, valid value ranges, and available credits.
Network & TimeoutIf status polling encounters a network timeout, retain the task_id and retry the query.
Polling FrequencyPoll every 2 seconds initially, gradually backing off for longer generations.
Terminal StatesOnly continue polling on not_started or running. Halt on finished or failed.
Callback SupportProvide callback_url in the request payload to receive final task payloads via webhook.

Endpoint Specifications

Specification	Value	Details
Input Mode	Source Video + Prompt (+ Optional Images)	Supply source video, text prompt, and up to 5 optional reference images.
Source Video Duration	3 to 60 seconds	Source videos support 3–60 seconds. Credits equal min(detected seconds, 15) × the resolution rate, normalized to six decimal places.
Reference Image Syntax	Natural-language references	Cited in prompt corresponding to reference_image_urls array.
Audio Policy	auto / origin	auto regenerates audio, origin preserves original source soundtrack.
Output Format	MP4 Video	Asynchronous response returns task_id; final result provides downloadable video URL.
Resolution	720p / 1080p	Default preselected to 1080p.
Billing	Per-second rate (15s Cap)	720p at 32 credits/s, 1080p at 64 credits/s.

View Happy Horse 1.0 Video Edit API docs

Happy Horse 1.0 Video Edit

Happy Horse 1.0 Video Edit is an advanced video-to-video diffusion and restyling engine. By taking a 3–60s source video alongside text instructions and up to 5 optional reference images (described in the prompt), it transforms visual appearance while strictly adhering to underlying motion trajectories, framing momentum, and timeline pacing. It supports original audio passthrough or smart regeneration, with built-in 15-second maximum billable cap protection.

Key Capabilities & Advantages

Seamless Motion Topology & Kinematic PreservationFlawlessly mirrors subject velocities, limb articulation, and camera momentum from source footage without pacing distortion.
Dual-Mode Local Replacement & Global Style TransferSupports targeted edits to attire, hair, or sky backgrounds as well as global anime, sci-fi, and fine art stylistic overhauls.
Up to 5 Visual Reference ImagesPass assets in reference_image_urls and describe their relevant features in the prompt to inject precise texture and character styling.
Flexible Audio Handling (auto / origin)Use audio_setting to either let the model synthesize fresh synced sound (auto) or seamlessly pass through the original audio track (origin).
15-Second Billing Cap ProtectionSource videos support 3–60 seconds. Credits equal min(detected seconds, 15) × the resolution rate, normalized to six decimal places.
720p Iteration & 1080p Crisp Delivery720p (32 credits/s) enables rapid turnaround during creative review, while 1080p (64 credits/s) provides high-clarity commercial deliverables.

Parameters

Parameter	Requirement	Description
video_url	Required	Source videos support 3–60 seconds. Credits equal min(detected seconds, 15) × the resolution rate, normalized to six decimal places.
prompt	Required	Required, nonblank, and at most 2,500 characters. Describe the edits, optionally with reference images.
reference_image_urls	Optional	String array. Up to 5 reference image URLs, described in the prompt using natural language.
resolution	Optional	String. Output resolution. Choose between 720p and 1080p. The Playground preselects 1080p. Default`1080p720p`
audio_setting	Optional	String. Audio policy. auto (synthesizes audio matching new visual) or origin (preserves source track). The Playground preselects auto. Default`autoorigin`
seed	Optional	Integer. 0 to 2147483647 for reproducible generation foundations.
enable_safety_checker	Optional	Boolean. Enables content safety moderation for inputs and outputs.

How to Call Happy Horse 1.0 Video Edit API

Step 1: Prepare Source Video & API KeyHost your 3–60s video at a public URL and set Authorization: Bearer VIDGO_API_KEY in your request headers.
Step 2: Configure Instructions & AssetsSet video_url, describe modifications in prompt, optionally attach reference images, and choose your audio policy.
Step 3: Submit Request & Retrieve VideoCall POST /api/generate/submit, poll until finished, and access the final transformed MP4 video.

Happy Horse 1.0 Pricing Overview

Source videos support 3–60 seconds. Credits equal min(detected seconds, 15) × the resolution rate, normalized to six decimal places. 720p costs 32 credits/s ($0.16/s); 1080p costs 64 credits/s ($0.32/s). Credits are deducted on submission and refunded if the task fails.

Usage	Rate	Details
720p	32 credits/s	Fast restyling test; billable duration is capped at 15s (480 credits maximum).
1080p	64 credits/s	High-fidelity production; billable duration is capped at 15s (960 credits maximum).

Best Use Cases

Live-Action Stylistic TransformationsConvert live-action footage or street clips into anime, cyberpunk, or oil painting styles while keeping original micro-motions.
Wardrobe Replacement & Virtual FittingRestyle clothing, hair, or accessories using reference images, adhering to realistic fabric folds and body mechanics.
Atmospheric Lighting & Weather ShiftsTransform daytime footage into rainy neon nightscapes, sunsets, or snowstorms without re-shooting live scenes.
Multi-Version Marketing IterationsDerive diverse aesthetic iterations from a single master commercial shoot to lower creative A/B testing production budgets.
VFX Previsualization & ConceptualizationEnable film production teams to preview complex creature transformations and surreal effects before committing high VFX spend.
Viral Social Media Trend RemixingRe-render trending dance videos and short-form clips with eye-catching visual contrasts for high engagement.

Pro Tips

Ensure source footage has clear subjects and stable lighting, as motion kinematics are closely tied to input clarity
When targeting specific garment or prop textures, supply reference images and describe their relevant features in the prompt
Set audio_setting to origin whenever you want to preserve dialogue, voiceover, or original environmental sound effects
Source footage from 3 to 60 seconds is supported, while billable duration is automatically capped at 15 seconds for maximum cost efficiency
Select 1080p resolution to avoid border tearing or swimming artifacts across continuous restyled motion
Pass a consistent seed value to freeze the underlying style generator, making it easy to isolate wording adjustments

Usage Notes

Set model to alibaba/happyhorse-1.0/video-edit in the top-level request body.
Source footage video_url supports 3 to 60 seconds, with billing capped strictly at 15 seconds.
Prompt is required; describe the intended reference features in prompt; no specific image marker syntax is required.
Audio policy audio_setting accepts auto (regenerates audio) or origin (preserves source audio).

Related Models

Gemini Omni 1.1 Flash Text-to-Video preview

Gemini Omni 1.1 Flash Text-to-VideoGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

Gemini Omni 1.1 Flash Image-to-Video preview

Gemini Omni 1.1 Flash Image-to-VideoGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

Gemini Omni 1.1 Flash Reference-to-Video preview

Gemini Omni 1.1 Flash Reference-to-VideoGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

Gemini Omni 1.1 Flash Video Edit preview

Gemini Omni 1.1 Flash Video EditGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

MiniMax H3 Max Turbo Text to Video preview

MiniMax H3 Max Turbo Text to VideoMiniMax H3 Max Turbo Text to Video turns text into coherent 5–15 second videos with synchronized native stereo audio and fast generation. It follows physical motion while rendering subtle changes in light and shadow.

MiniMax H3 Max Turbo Image to Video preview

MiniMax H3 Max Turbo Image to VideoMiniMax H3 Max Turbo Text to Video turns text into coherent 5–15 second videos with synchronized native stereo audio and fast generation. It follows physical motion while rendering subtle changes in light and shadow.

MiniMax H3 Max Text to VideoMiniMax H3 Max Text to Video turns text prompts into cinematic video with native stereo audio, faster-than-real-time generation, and precise instruction following. It renders complex camera work and physical motion with fine detail across multiple resolutions and common aspect ratios.

MiniMax H3 Max Image to VideoMiniMax H3 Max Text to Video turns text prompts into cinematic video with native stereo audio, faster-than-real-time generation, and precise instruction following. It renders complex camera work and physical motion with fine detail across multiple resolutions and common aspect ratios.

MiniMax H3 Max Reference to Video preview

MiniMax H3 Max Reference to VideoMiniMax H3 Max Text to Video turns text prompts into cinematic video with native stereo audio, faster-than-real-time generation, and precise instruction following. It renders complex camera work and physical motion with fine detail across multiple resolutions and common aspect ratios.

Wan 3.0 Prime Text-to-VideoAlibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.

Wan 3.0 Prime Image-to-VideoAlibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.

Wan 3.0 Prime Reference-to-Video preview

Wan 3.0 Prime Reference-to-VideoAlibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.

Wan 3.0 Text-to-VideoAlibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.

Wan 3.0 Image-to-VideoAlibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.

Wan 3.0 Reference-to-VideoAlibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.

FLUX 3 Text to VideoBlack Forest Labs FLUX 3 video model with text-to-video, image-to-video, first-last-frame, extend-video, and keyframes workflows at 720p or 1080p for 5 to 20 seconds, with optional native audio.

Happy Horse 1.0 Video Edit API Frequently Asked Questions

What is the Happy Horse 1.0 Video Edit API?

Happy Horse 1.0 Video Edit is an Alibaba model for video-to-video editing and restyling. It transforms 3–60s source footage using natural-language instructions and up to 5 optional reference images into 720p or 1080p re-rendered video, featuring exceptional motion fidelity, local element substitution, and global style transfer. Built on an advanced spatiotemporal video restyling architecture, it strictly adheres to source motion skeletons and camera momentum while rendering desired wardrobe, weather, and stylistic changes, with audio passthrough support. You can call it programmatically or try it from the playground above.

What source video duration does Happy Horse 1.0 Video Edit support?

Source videos support 3–60 seconds. Credits equal min(detected seconds, 15) × the resolution rate, normalized to six decimal places.

How do you reference images in Happy Horse 1.0 Video Edit prompts?

Include up to 5 image URLs in reference_image_urls and describe the intended reference features in prompt. This guides the model to transfer specific textures, patterns, or character appearances directly into the video.

Can Happy Horse 1.0 Video Edit preserve original audio?

Yes. Set audio_setting to origin to pass through the original voice dialogue, ambient sound, and background music from the source. Setting it to auto directs the model to synthesize a fresh soundtrack aligned with the restyled visual.

How does the billing cap work for Happy Horse 1.0 Video Edit?

For any video longer than 15 seconds (such as 25s or 50s clips), billing is strictly capped at 15 seconds (480 credits for 720p, 960 credits for 1080p). You will never be charged for duration exceeding 15 seconds.

Does Happy Horse 1.0 Video Edit alter underlying motion dynamics?

The model uses the source motion, actor pacing, and camera trajectory as references, with edits focused on surface textures, styles, and visual assets.

When should you choose Happy Horse 1.0 Video Edit over Reference to Video?

Choose Video Edit when you have an existing video track and want to inherit its exact pacing, blocking, and choreography while altering the aesthetic style or wardrobe. If you are generating a new shot from scratch using still images, use Reference to Video.