QwenQwen Instruction-based video editing

HappyHorse 1.0 Video Edit

Start from an existing video and test a specific change against the original.

TokenHot lists HappyHorse 1.0 Video Edit as a separate video route. Start from an existing video and test a specific change against the original. Compare candidate clips against the supplied material and your shot criteria.

  • Instruction-based video editing
  • 720p and 1080p Playground
  • Queued API task

The Playground requires an HTTPS source-video URL and accepts one optional JPG or PNG reference up to 10 MiB. It offers 720p or 1080p and has no ratio or duration selector.

Try this model

Provide a source video and describe the changes to make.

happyhorse-1.0-video-edit

Input

Reference image (optional)

JPG / PNG · Up to 10 MB. Uploaded when you generate.

Resolution

Uses your account balance at the model’s current rates.

Generated result

Your creation appears here

Enter a prompt, choose your settings, and generate.

USD /s

Pricing

GroupTierPrice
default720P$0.135
default1080P$0.23895
default
720P$0.135
1080P$0.23895

Public list prices are shown in USD. Final charges may vary by account group and usage tier.

Overview

What is HappyHorse 1.0 Video Edit?

The TokenHot example sends a video URL and a reference_image URL in input.media. It selects 720P in parameters.

The published API example returns a queued task with a task ID. Keep that ID and check status before reviewing the output. A submission is separate from a finished clip.

wardrobe

Test a wardrobe change on a moving subject

A candidate edit for checking garment appearance and motion continuity.

lighting treatment

Compare a different lighting treatment

A candidate look to review side by side with the original.

prop replacement

Try a local prop replacement

A candidate local edit with the surrounding scene available for comparison.

From brief to deliverable

Put HappyHorse 1.0 Video Edit to work

Start with a concrete task and decide what a useful result looks like.

Video editors

Test a wardrobe change on a moving subject

Use an HTTPS source clip URL, a jacket reference and a clear edit instruction to prepare a clip your team can review.

Tools you need
A shot brief, a playback view and a reviewer.
Keep in mind
Compare the edited take with the source at several points in the motion.
View a task brief

Test a wardrobe change on a moving subject. Use the supplied input to aim for a candidate edit for checking garment appearance and motion continuity. Review the candidate against the shot criteria before using it.

Video editors

Compare a different lighting treatment

Use an HTTPS source clip URL and a written lighting direction to prepare a clip your team can review.

Tools you need
A shot brief, a playback view and a reviewer.
Keep in mind
Check whether the edit changed framing or subject detail unexpectedly.
View a task brief

Compare a different lighting treatment. Use the supplied input to aim for a candidate look to review side by side with the original. Review the candidate against the shot criteria before using it.

Video editors

Try a local prop replacement

Use an HTTPS source clip URL, one reference image of the replacement and a clear target to prepare a clip your team can review.

Tools you need
A shot brief, a playback view and a reviewer.
Keep in mind
Inspect frames around the edit for changes to neighboring objects.
View a task brief

Try a local prop replacement. Use the supplied input to aim for a candidate local edit with the surrounding scene available for comparison. Review the candidate against the shot criteria before using it.

Capabilities in context

Key features

FeatureWhat you getWhy it matters
TokenHot model IDhappyhorse-1.0-video-editUse the exact value for the intended video mode.
TokenHot request endpointPOST /v1/video/generationsUse input.media to identify the source clip and reference image.
Task responseQueued task IDUse the task ID to check status before downloading a result.
Playground controlsCurrent TokenHot interfaceSource-video URL, optional reference image and resolution.
Output reviewInspect the candidate videoCompare framing, motion and unwanted changes against the brief.

The TokenHot API example and Playground implementation define the controls described here. Alibaba Cloud documents the provider's own model family. Scenario images were made with ImageGen to illustrate workflows. TokenHot route documentation · TokenHot model details · Alibaba Cloud HappyHorse model modes

Audience & fit

Where HappyHorse 1.0 Video Edit fits

Test a wardrobe change on a moving subject

A candidate edit for checking garment appearance and motion continuity.

Compare a different lighting treatment

A candidate look to review side by side with the original.

Try a local prop replacement

A candidate local edit with the surrounding scene available for comparison.

Cost context

Plan the cost of a useful result

Check the current TokenHot table

Use the rates shown for this model and your selected settings.

Compare cost per accepted take

Include iterations you reject when deciding whether the route fits the job.

Start with a small test

Check the input mode and motion brief with one candidate before producing several takes.

Use the current pricing table for available rates and account groups. Model IDs and prices come from TokenHot’s catalog; provider pricing and subscriptions are separate.

API

Code examples

curl --location --request POST 'https://api.tokenhot.ai/v1/video/generations' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "happyhorse-1.0-video-edit",
    "input": {
        "prompt": "Make the centaur character in the video wear the striped sweater from the image",
        "media": [
            {
                "type": "video",
                "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260409/dozxak/Wan_Video_Edit_33_1.mp4"
            },
            {
                "type": "reference_image",
                "url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260415/hynnff/wan-video-edit-clothes.webp"
            }
        ]
    },
    "parameters": {
        "resolution": "720P"
    }
}'

FAQ

Frequently asked questions

What is HappyHorse 1.0 Video Edit best suited for?

HappyHorse 1.0 Video Edit is suited to the input, output, and capability types listed on this page. Test production workloads before choosing it for a critical system.

How is HappyHorse 1.0 Video Edit priced?

Pricing is shown in the pricing section above. Actual cost depends on usage volume, account group, and the request payload.

How can I call HappyHorse 1.0 Video Edit?

Use the model ID shown above with one of the supported API protocols. Code examples are provided when usage data is available.

Which TokenHot model ID should I use?

Use happyhorse-1.0-video-edit in the model field.

What does the TokenHot request example show?

A source-video URL and a reference_image URL in input.media, with resolution set to 720P.

What can I set in the Playground?

Supply an HTTPS video URL and choose 720p or 1080p. You can add one JPG or PNG reference up to 10 MiB. There are no ratio or duration controls.

Does a successful submission return the finished clip?

The published example returns a queued task ID. Check the task status and retrieve the result after it finishes.

When should I use HappyHorse 1.0 R2V?

Use reference-to-video when you are starting from still references and do not have an existing source clip to edit.

Get started

Build with HappyHorse 1.0 Video Edit

Use in Console