mcpField
A
aliyun-emoji

aliyun-emoji

github.com/cinienceCreative & media39654 installsUpdated 11w ago
Repository

About aliyun-emoji

A Model Studio skill for creating fixed-template facial animation clips from portrait images. It detects the face and obtains bounding boxes before using them with a template ID to generate a video.

Key features

  1. 01Detect faces and return bounding boxes
  2. 02Generate animated clips from templates
  3. 03Poll tasks and retrieve video URLs
  4. 04Save request and task records

Use cases

  1. 01Turn a front-facing portrait into an animated clip
  2. 02Review face detection before generating a video

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/cinience/alicloud-skills --skill aliyun-emoji

After installing, type/aliyun-emojiin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
references/
sources.md
scripts/
prepare_emoji_request.py

Details

From the project README

Category: provider

Model Studio Emoji

Validation

mkdir -p output/aliyun-emoji
python -m py_compile skills/ai/video/aliyun-emoji/scripts/prepare_emoji_request.py && echo "py_compile_ok" > output/aliyun-emoji/validate.txt

Pass criteria: command exits 0 and output/aliyun-emoji/validate.txt is generated.

Output And Evidence

  • Save normalized request payloads, detected face boxes, selected template ID, and task polling snapshots under output/aliyun-emoji/.
  • Record the exact portrait URL and whether detection passed.

Use Emoji when the user wants a fixed-template facial animation clip rather than open-ended video generation.

Critical model names

Use these exact model strings:

  • emoji-detect-v1
  • emoji-v1

Selection guidance:

  • Run emoji-detect-v1 first to obtain face_bbox and ext_bbox_face.
  • Use emoji-v1 only after detection succeeds.

Prerequisites

  • China mainland (Beijing) only.
  • Set DASHSCOPE_API_KEY in your environment, or add dashscope_api_key to ~/.alibabacloud/credentials.
  • Input image must be a public HTTP/HTTPS URL.

Normalized interface (video.emoji)

Detect Request
  • model (string, optional): default emoji-detect-v1
  • image_url (string, required)
Generate Request
  • model (string, optional): default emoji-v1
  • image_url (string, required)
  • face_bbox (array, required)
  • ext_bbox_face (array, required)
  • template_id (string, required)
Response
  • task_id (string)
  • task_status (string)
  • video_url (string, when finished)

Quick start

python skills/ai/video/aliyun-emoji/scripts/prepare_emoji_request.py \
  --image-url "https://example.com/portrait.png" \
  --face-bbox 302,286,610,593 \
  --ext-bbox-face 71,9,840,778 \
  --template-id emoji_001

Operational guidance

  • Use a single-person, front-facing portrait with no face occlusion.
  • Template IDs come from the official template list or console experience; do not invent them in production calls.
  • Emoji output is a person video clip, not a sticker pack or text overlay asset.

Output location

  • Default output: output/aliyun-emoji/request.json
  • Override base dir with OUTPUT_DIR.

References

  • references/sources.md

Comments

Markdown supported