Happy Horse 1.0 Image to Video API

alibaba/happyhorse-1.0/image-to-video

Happy Horse 1.0 Image to Video transforms still images into cinematic dynamic videos, supporting 3–15 second duration, 720p or 1080p resolution, and optional prompt guidance. It faithfully preserves initial subject likeness, material texture, and framing perspective while infusing scenes with natural physical motion and smooth camera trajectories.

Input

Prompt

203/2500

First frame

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

Resolution

Duration

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 Reference to Video Happy Horse 1.0 Video Edit

Examples

The observatory dome slowly rotates open as the first sunlight sweeps across the plateau, haze drifting through the valley, camera gently pushing in, no text, no logos, no watermark, no promotional marks

The turntable rotates slowly, showing the stoneware vase from every side as window light shifts across its glaze, dust motes drifting, vertical composition, no text, no logos, no watermark, no promotional marks

The vintage train doors slide shut and the train pulls away, its lights streaking softly while paper scraps drift along the empty platform, illustration style preserved, subtle camera drift, no text, no logos, no watermark, no promotional marks

REST API

Quick Start

Authenticate via API Key, submit a first-frame image with optional motion prompt, 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 an Image to Video Task

Configure inputs with 1 image URL in image_urls, and set model to alibaba/happyhorse-1.0/image-to-video.

Submit Request

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "alibaba/happyhorse-1.0/image-to-video",
  "input": {
    "prompt": "The observatory dome slowly rotates open as the first sunlight sweeps across the plateau, haze drifting through the valley, camera gently pushing in, no text, no logos, no watermark, no promotional marks",
    "duration": 5,
    "resolution": "1080p",
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/alibaba/happyhorse-1.0/image-to-video/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/image-to-video",
  "input": {
    "prompt": "The observatory dome slowly rotates open as the first sunlight sweeps across the plateau, haze drifting through the valley, camera gently pushing in, no text, no logos, no watermark, no promotional marks",
    "duration": 5,
    "resolution": "1080p",
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/alibaba/happyhorse-1.0/image-to-video/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
image_urls	array	Yes	—	String array. Contains exactly 1 image URL serving as the opening keyframe.
prompt	string	No	—	String. Up to 2,500 characters. Optional directives for camera movement, subject action, and ambiance.
resolution	string	No	1080p	String. Output resolution. Supports 720p and 1080p.
duration	integer	No	5	Integer. Output duration from 3 to 15 seconds.
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	Single First Frame + Optional Prompt	Supply 1 opening image alongside optional text instructions.
First Frame Requirement	Exactly 1 Image URL	Provided in image_urls as a publicly accessible image URI.
Output Format	MP4 Video	Asynchronous response returns task_id; final result provides downloadable video URL.
Resolution	720p / 1080p	Default preselected to 1080p.
Duration	3–15 seconds	Default preselected to 5 seconds.
Aspect Ratio	16:9 / 9:16 / 1:1 / 4:3 / 3:4	Default preselected to 16:9.
Billing	Per-second rate	720p at 16 credits/s, 1080p at 32 credits/s.

View Happy Horse 1.0 Image to Video API docs

Happy Horse 1.0 Image to Video

Happy Horse 1.0 Image to Video is tailored for single-image first-frame animation. By taking a single still image as the foundational opening frame, the model infers realistic physical motion and cinematic camera transitions in latent space. It generates plausible dynamics autonomously without prompts, or follows optional text instructions to direct precise zooms, pans, lighting, and action pacing.

Key Capabilities & Advantages

Pixel-Level First-Frame Identity & Framing LockTightly anchors initial subject likeness, clothing texture, and spatial perspective, preventing opening distortions and face drift.
Autonomous Latent Motion SynthesisText prompt is completely optional; the model infers contextually coherent environment motion and action without textual guidance.
Directed Camera Choreography & Prompt GuidanceWhen text instructions are provided, it precisely coordinates camera pans, zooms, and action beats with image semantics.
3–15s Smooth Spatiotemporal EvolutionEliminates motion tearing and flickering artifacts, smoothly developing narrative tension and lighting interplay over duration.
720p Fast Testing & 1080p Crisp DeliveryBalances rapid turnaround during visual testing with pristine commercial-grade asset exports.
Seed Reproducibility & Motion TuningAn optional seed stabilizes generation noise for identical first frames, allowing isolated comparison of motion scales.

Parameters

Parameter	Requirement	Description
image_urls	Required	String array. Provide exactly 1 public image URL as the initial opening frame.
prompt	Optional	String. Up to 2,500 characters. Guides specific subject action, camera movement, and lighting atmosphere.
resolution	Optional	String. Output resolution. Choose between 720p and 1080p. The Playground preselects 1080p. Default`1080p720p`
duration	Optional	Integer. Output duration from 3 to 15 seconds. The Playground preselects 5 seconds. Default`5346789101112131415`
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 Image to Video API

Step 1: Prepare First Frame & API KeyHost your starting image publicly and configure Authorization: Bearer VIDGO_API_KEY in your headers.
Step 2: Configure Image & Motion ParametersPass the image URL inside image_urls, optionally supply motion prompt guidance, and select duration and resolution.
Step 3: Submit Task & Retrieve VideoCall POST /api/generate/submit to receive a task_id, poll status until finished, and download the resulting MP4.

Happy Horse 1.0 Pricing Overview

Billed per second based on resolution and duration. 720p is 16 credits/s ($0.08/s), and 1080p is 32 credits/s ($0.16/s). Credits are deducted on submission and refunded if the task fails.

Usage	Rate	Details
720p	16 credits/s	Fast motion testing; a standard 5s generation costs 80 credits.
1080p	32 credits/s	High-fidelity production; a standard 5s generation costs 160 credits.

Best Use Cases

Portrait Photography & Character AnimationImpart lifelike micro-expressions, hair flutter, and gentle lighting shifts into still photo portraits and studio shots.
E-Commerce Dynamic Product VisualsTurn still product photography into elegant orbiting clips with natural reflections and material highlights to boost conversion.
Concept Art & Illustration ShowcasesExpand digital paintings and game concept art into dynamic environments with parallax depth and camera drift.
Social Media Hooks & Creative OpeningsLaunch campaigns from memorable key visual stills, transitioning into eye-catching motion within the critical first seconds.
Historical Archival Photo RevivalBreathe delicate motion and cinematic pan-and-scan into vintage photographs and documentary archives.
Brand Asset ExpansionRapidly transform static key visual posters into animated promotional content across diverse duration and ratio formats.

Pro Tips

Ensure the starting image has clear subjects and good lighting, as high input quality directly impacts motion stability
Specify explicit cinematic verbs in the prompt (e.g., camera pans right, slow push-in) to govern camera movement
Leave prompt empty when seeking spontaneous, scene-inferred motion that naturally emerges from image semantics
Choose 1080p resolution to capture intricate surface textures, clothing weaves, and facial details
Use a duration of 5 seconds or longer for complex choreography to give movements sufficient time to unfold
Lock generation noise with a fixed seed value when comparing variations of motion prompts on the same still image

Usage Notes

Set model to alibaba/happyhorse-1.0/image-to-video in the top-level request body.
The image_urls field accepts exactly 1 image URL representing the opening frame.
The prompt field is optional and accepts up to 2,500 characters.
Duration supports 3 to 15 integer seconds; resolution supports 720p or 1080p.

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 Image to Video API Frequently Asked Questions

What is the Happy Horse 1.0 Image to Video API?

Happy Horse 1.0 Image to Video is an Alibaba model for video generation from images. It takes a single still image as an opening frame alongside optional prompt directives to generate 3–15s cinematic videos in 720p or 1080p, featuring exceptional first-frame fidelity and natural motion inference. Built on an advanced spatiotemporal diffusion architecture, it anchors opening subject anatomy, attire details, and perspective while introducing physically coherent motion and camera fluidity. You can call it programmatically or try it from the playground above.

Is a starting image required for Happy Horse 1.0 Image to Video?

Yes. This endpoint requires exactly 1 publicly accessible image URL passed in the image_urls array to serve as the opening anchor frame for the video.

Can Happy Horse 1.0 Image to Video generate videos without a prompt?

Yes. The prompt parameter is completely optional. If omitted, the model autonomously infers natural dynamics directly from scene semantics. Adding a prompt allows you to explicitly guide camera trajectory and action pacing.

How does Happy Horse 1.0 Image to Video preserve subject and composition?

The model performs continuous latent diffusion conditioned on the starting keyframe, anchoring initial facial likeness, texture details, and spatial depth before smoothly evolving them into motion.

Can Happy Horse 1.0 Image to Video generate 15-second clips?

Yes. The duration parameter accepts any integer second between 3 and 15 seconds, with 5 seconds preselected in the playground. Extended durations maintain physical consistency and frame stability.

Does Happy Horse 1.0 Image to Video support 1080p output?

Yes. Both 720p and 1080p resolution tiers are supported. The 1080p option faithfully preserves high-frequency textures, fine hair strands, and lighting nuance from the source image.

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

Choose Image to Video when you have a finalized opening still frame and want the camera or action to start directly from that composition. If you need 1–9 reference images to guide character identity across a completely new shot, choose Reference to Video.