Edit or Restyle a Short Video · Alibaba

Provide a publicly accessible HTTPS link to one 2–10 second video. You may add an editing instruction and up to four reference images; a successful edit produces one downloadable MP4.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Use edit-video-alibaba (Tool ID 6429724d-de67-48c9-b798-e4c1019a9a63) to restyle my 5-second video as claymation. Reuse my Toolmu connection or follow https://toolmu.com/SKILL.md within my existing authorization and budget. First ask for my publicly accessible HTTPS video link; do not invent a link or use other example footage. After I provide an eligible link, place one object with type=video and url=my supplied link in body.media. Set body.prompt="Convert the entire scene to a claymation style", body.resolution=720P and body.audio_setting=origin; omit body.duration to keep the source length. Add no reference images unless I provide them; supplied references use type=reference_image in the same media array, with at most four. Complete the same run rather than automatically submitting another while it is processing. Preserve its result and give me the actual MP4 download link after success, explaining that the link is temporary, typically about 24 hours. Do not claim a finished video before a successful result is available.

Task:
Make [my 5-second video link] look like [clay animation]. The link should play for anyone without signing in. If it opens a post instead of the video, ask for another link. Keep the sound and length. Share the download link when done, and ask before another version.

Paste into your connected AI's conversation.

Connection guide

Up to 1.8 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

Alibaba

Edit or Restyle a Short Video · Alibaba

Provide a publicly accessible HTTPS link to one 2–10 second video. You may add an editing instruction and up to four reference images; a successful edit produces one downloadable MP4.

You receive

A successful edit returns one MP4 video encoded with H.264. You can restyle the scene or request changes to subjects, clothing or objects, optionally guided by reference images, at 720P or 1080P. Choose whether to keep the original audio or let the model decide it.

Start with your task

Make [my 5-second video link] look like [clay animation]. The link should play for anyone without signing in. If it opens a post instead of the video, ask for another link. Keep the sound and length. Share the download link when done, and ask before another version.

What to know

Media must meet the file requirements and be available through public HTTPS links. Editing can take several minutes, and visual fidelity or exact adherence is not guaranteed. The download link is temporary, typically about 24 hours; save the completed result promptly.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
body`body`	`object`	Required	Required fields `media`
Random seed`body.seed`	`integer`	Optional	Optional integer from 0 to 2147483647. A fixed seed can help reproducibility, but the same seed does not guarantee identical results. Minimum `0` Maximum `2147483647`
Video and optional reference images`body.media`	`array`	Required	Required array containing exactly one video and optionally up to four reference images. Each entry must include its type and public HTTPS URL. Minimum items `1`
[]`body.media[]`	`object`	—	Required fields `type, url`
Public media link`body.media[].url`	`string`	—	Required for each media entry: a nonempty, publicly accessible HTTPS file URL. This Tool does not accept local paths, HTTP links, Base64 data or Asset Center IDs. Minimum length `1`
Media type and file requirements`body.media[].type`	`string`	—	Required: video for the one MP4/MOV clip, 2–10 seconds and up to 100 MB, with width and height each 240–4096 pixels. reference_image for an optional JPG, JPEG, PNG (no alpha), BMP or WEBP image, up to 20 MB each, with width and height each 240–8000 pixels; at most four images. Both media types require aspect ratios from 1:8 to 8:1. Options `video, reference_image`
Output aspect ratio`body.ratio`	`string`	Optional	Optional 16:9, 9:16, 1:1, 4:3 or 3:4. If omitted, the output follows the source video's proportions rather than forcing a preset. Options `16:9, 9:16, 1:1, 4:3, 3:4`
Editing instruction`body.prompt`	`string`	Optional	Optional nonempty instruction, up to 5000 characters, describing the desired style or changes to subjects, clothing or objects. For example: Convert the entire scene to a claymation style. Minimum length `1` Maximum length `5000`
Truncation length in seconds`body.duration`	`integer`	Optional	Optional integer from 2 to 10, used to truncate the output from its beginning. Omit it to keep the source length; it is not a video-extension control, and 0 is not accepted. Minimum `2` Maximum `10`
AI Generated watermark`body.watermark`	`boolean`	Optional	Optional boolean; default false. true requests the AI Generated watermark in the lower-right corner of the video. Default `false`
Output resolution tier`body.resolution`	`string`	Optional	Optional 720P or 1080P; this Tool defaults to 720P. Selects the output resolution tier, not a guarantee of improved source detail. Default `720P` Options `720P, 1080P`
Audio handling`body.audio_setting`	`string`	Optional	Optional auto or origin; default auto. auto lets the model retain or generate audio based on the instruction. origin retains the source video's original audio without regeneration. Default `auto` Options `auto, origin`
Expand the instruction`body.prompt_extend`	`boolean`	Optional	Optional boolean; default true. Enables model-assisted rewriting of the instruction and can add processing time. It does not guarantee a better or exact edit. Default `true`
Requested exclusions`body.negative_prompt`	`string`	Optional	Optional text up to 500 characters describing content you want excluded. It guides the edit but does not guarantee those elements will be absent. Maximum length `500`

View raw JSON

{
  "type": "object",
  "required": [
    "body"
  ],
  "properties": {
    "body": {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "media"
      ],
      "~standard": {
        "vendor": "zod",
        "version": 1,
        "jsonSchema": {}
      },
      "properties": {
        "seed": {
          "type": "integer",
          "maximum": 2147483647,
          "minimum": 0,
          "description": "Optional integer from 0 to 2147483647. A fixed seed can help reproducibility, but the same seed does not guarantee identical results."
        },
        "media": {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "type",
              "url"
            ],
            "properties": {
              "url": {
                "type": "string",
                "minLength": 1,
                "description": "Required for each media entry: a nonempty, publicly accessible HTTPS file URL. This Tool does not accept local paths, HTTP links, Base64 data or Asset Center IDs."
              },
              "type": {
                "enum": [
                  "video",
                  "reference_image"
                ],
                "type": "string",
                "description": "Required: video for the one MP4/MOV clip, 2–10 seconds and up to 100 MB, with width and height each 240–4096 pixels. reference_image for an optional JPG, JPEG, PNG (no alpha), BMP or WEBP image, up to 20 MB each, with width and height each 240–8000 pixels; at most four images. Both media types require aspect ratios from 1:8 to 8:1."
              }
            },
            "additionalProperties": false
          },
          "minItems": 1,
          "description": "Required array containing exactly one video and optionally up to four reference images. Each entry must include its type and public HTTPS URL."
        },
        "ratio": {
          "enum": [
            "16:9",
            "9:16",
            "1:1",
            "4:3",
            "3:4"
          ],
          "type": "string",
          "description": "Optional 16:9, 9:16, 1:1, 4:3 or 3:4. If omitted, the output follows the source video's proportions rather than forcing a preset."
        },
        "prompt": {
          "type": "string",
          "maxLength": 5000,
          "minLength": 1,
          "description": "Optional nonempty instruction, up to 5000 characters, describing the desired style or changes to subjects, clothing or objects. For example: Convert the entire scene to a claymation style."
        },
        "duration": {
          "type": "integer",
          "maximum": 10,
          "minimum": 2,
          "description": "Optional integer from 2 to 10, used to truncate the output from its beginning. Omit it to keep the source length; it is not a video-extension control, and 0 is not accepted."
        },
        "watermark": {
          "type": "boolean",
          "default": false,
          "description": "Optional boolean; default false. true requests the AI Generated watermark in the lower-right corner of the video."
        },
        "resolution": {
          "enum": [
            "720P",
            "1080P"
          ],
          "type": "string",
          "default": "720P",
          "description": "Optional 720P or 1080P; this Tool defaults to 720P. Selects the output resolution tier, not a guarantee of improved source detail."
        },
        "audio_setting": {
          "enum": [
            "auto",
            "origin"
          ],
          "type": "string",
          "default": "auto",
          "description": "Optional auto or origin; default auto. auto lets the model retain or generate audio based on the instruction. origin retains the source video's original audio without regeneration."
        },
        "prompt_extend": {
          "type": "boolean",
          "default": true,
          "description": "Optional boolean; default true. Enables model-assisted rewriting of the instruction and can add processing time. It does not guarantee a better or exact edit."
        },
        "negative_prompt": {
          "type": "string",
          "maxLength": 500,
          "description": "Optional text up to 500 characters describing content you want excluded. It guides the edit but does not guarantee those elements will be absent."
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

Result schema

Output fields have not been documented yet.

Additional notes

Reference images guide a desired style or appearance; they do not guarantee an exact likeness. Inspect the completed video to see whether the requested visual changes and motion suit your task.

Alibaba video editing documentation describes the model. This Tool uses the public HTTPS media inputs and defaults shown in the reference above.

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

Choose origin to retain the input video's original audio. The default auto setting lets the model decide from the instruction; it may retain the original audio or generate new audio.

Edit or Restyle a Short Video · Alibaba

Edit or Restyle a Short Video · Alibaba

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Share your video

Describe the change

Save the finished video

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Share your video

Describe the change

Save the finished video

Questions about this tool.

How do I keep the original audio?

Can I keep the original duration or make the video longer?

Can I use a local file, Base64 data or an Alibaba asset ID?