인터페이스는 현지화되어 있으며, Skill 소개와 설명 문서는 선택한 언어로 AI가 자동 번역합니다. 코드·명령어·경로·전문 용어는 원문을 유지하며 원작자 문서가 우선합니다.
Skills 둘러보기
생산성 및 협업 · SKILL.md

pixverse-v4-5-text-to-video

pixverse-v4-5-text-to-video

PixVerse v4.5 | Text to Video. Generate videos from text descriptions using PixVerse v4.5 | Text to Video. Triggers: pixverse, text to video, video generation

Independent GitHub snapshot · Automated classification · Original documentation governs

Skill 문서

GitHub

name: pixverse-v4-5-text-to-video description: "PixVerse v4.5 | Text to Video. Generate videos from text descriptions using PixVerse v4.5 | Text to Video. Triggers: pixverse, text to video, video generation" allowed-tools: Bash(curl *), WebFetch

PixVerse v4.5 | Text to Video

Generate videos from text descriptions using PixVerse v4.5 | Text to Video. Supports multiple aspect ratios (16:9, 4:3, 1:1, 3:4, 9:16), configurable duration, negative prompt support, reproducible results via seed, style selection, quality control.

Quick Start

Requires an each::labs API key. Get one at eachlabs.ai.

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "pixverse-v4-5-text-to-video",
    "version": "0.0.1",
    "input": {
      "prompt": "A serene Japanese garden with cherry blossoms falling gently in the wind"
    }
  }'

Parameters

ParameterTypeDefaultDescription
aspect_ratiostring16:9The video’s width-to-height ratio. Options: 16:9, 4:3, 1:1, 3:4, 9:16
durationstring5Length of the video in seconds.. Options: 5, 8
lip_sync_switchbooleanSet to true if you want to enable this feature. Default is false.
lip_sync_tts_contentstring~140 (UTF-8) characters
lip_sync_tts_speaker_idstring
motion_modestringnormalControls animation speed. Options: normal, fast
negative_promptstringText for things you don’t want to appear in the video. <= 2048 characters
promptstringText description of the scene or video you want to create. <= 2048 characters
qualitystring540pThe resolution quality of the video.. Options: 360p, 540p, 720p, 1080p
seedinteger
sound_effect_contentstring
sound_effect_switchbooleanTrue
stylestringVisual style for the video. Options: anime, 3d_animation, clay, comic, cyberpunk

Examples

Nature scene video:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "pixverse-v4-5-text-to-video",
    "version": "0.0.1",
    "input": {
      "prompt": "A serene Japanese garden with cherry blossoms falling gently in the wind"
    }
  }'

Cinematic aerial shot:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "pixverse-v4-5-text-to-video",
    "version": "0.0.1",
    "input": {
      "prompt": "Cinematic drone shot flying over a misty mountain range at golden hour, volumetric lighting",
      "aspect_ratio": "9:16",
      "duration": "10",
      "negative_prompt": "blurry, distorted, low quality, watermark",
      "style": "anime",
      "seed": 42,
      "quality": "1080p",
      "motion_mode": "fast"
    }
  }'

Related Models

Documentation

저장한 Skills