Video Generation
텍스트나 이미지로 고품질 비디오를 생성하는 최신 AI 모델들입니다. Kling, MiniMax Hailuo, Veo, Sora 등 다양한 모델을 지원합니다.
모델 비교표
| 모델 | 크레딧 | 유형 | 특징 |
|---|---|---|---|
| seedance-1-pro-fast | 190 | T2V | ByteDance, 빠른 생성 |
| hailuo-2.3-fast | 285 | T2V | MiniMax, 빠른 버전 |
| kling-v2.1 | 375 | T2V/I2V | Kuaishou, 고품질 |
| hailuo-2.3 | 420 | T2V | MiniMax, 고품질 |
| kling-v2.5-turbo-pro | 525 | T2V/I2V | Kuaishou, 최신 Pro |
| sora-2 | 600 | T2V | OpenAI, 시네마틱 |
| wan-2.5-t2v-fast | 765 | T2V | Alibaba, 빠른 T2V |
| wan-2.5-i2v-fast | 510 | I2V | Alibaba, 빠른 I2V |
| wan-2.5-t2v | 1,500 | T2V | Alibaba, 고품질 T2V |
| wan-2.5-i2v | 1,500 | I2V | Alibaba, 고품질 I2V |
| veo-3.1-fast | 1,800 | T2V | Google, 빠른 생성 |
| pixverse-v5 | 2,400 | T2V | PixVerse, 고품질 |
| veo-3.1 | 4,800 | T2V | Google, 최고 품질 |
모델 상세 정보
각 모델의 상세한 파라미터, 예제 코드, 활용 팁을 확인하세요.
Google Veo 3.1
Google's state-of-the-art video generation model with built-in audio generation, producing cinematic-quality videos with synchronized sound.
Google Veo 3.1 Fast
Fast version of Veo 3.1 with audio generation, optimized for speed while maintaining high quality output.
OpenAI Sora 2
OpenAI
OpenAI's video generation model with realistic physics simulation and audio generation capabilities, producing highly coherent videos.
Kling v2.1
Kuaishou
Kling v2.1 with 720p/1080p support and frame transition capabilities for smooth, high-quality video generation.
Kling 2.5 Turbo Pro
Kuaishou
Cinematic-grade video generation with enhanced motion and scene coherence. Top-tier Kling model for professional output.
MiniMax Hailuo 2.3
MiniMax
Realistic human motion video generation with advanced character consistency and natural movement.
MiniMax Hailuo 2.3 Fast
MiniMax
Lower-latency version of Hailuo 2.3 optimized for faster generation while maintaining good quality for human motion videos.
PixVerse V5
PixVerse
Advanced video generation with special effects capabilities and anime-optimized output, supporting multiple visual styles.
Wan 2.5 T2V
Alibaba
Text-to-video model with audio synchronization support, producing high-quality videos from text prompts with natural motion.
Wan 2.5 T2V Fast
Alibaba
Fast text-to-video generation variant of Wan 2.5, optimized for speed with good quality output.
Wan 2.5 I2V
Alibaba
Image-to-video model with lip sync support, animating still images into realistic videos with natural motion.
Wan 2.5 I2V Fast
Alibaba
Fast image-to-video variant of Wan 2.5, optimized for rapid generation of animated videos from still images.
Seedance 1 Pro Fast
ByteDance
ByteDance's cinematic video generation model with fast generation speed and professional output quality.
Hailuo 2.3 (MiniMax)
MiniMax의 고품질 비디오 생성 모델.
curl -X POST https://api.core.today/v1/predictions \
-H "Content-Type: application/json" \
-H "X-API-Key: cdt_your_api_key" \
-d '{
"model": "minimax/hailuo-2.3",
"input": {
"prompt": "A golden retriever running on the beach at sunset, slow motion, cinematic",
"duration": 6,
"aspect_ratio": "16:9"
}
}'이미지 → 비디오 (Image-to-Video)
첫 프레임 이미지를 제공하여 비디오를 생성합니다.
1. 이미지 업로드
curl -X POST https://api.core.today/v1/files/upload-url \
-H "X-API-Key: cdt_your_api_key" \
-H "Content-Type: application/json" \
-d '{"filename": "first_frame.jpg", "content_type": "image/jpeg"}'2. 비디오 생성
curl -X POST https://api.core.today/v1/predictions \
-H "Content-Type: application/json" \
-H "X-API-Key: cdt_your_api_key" \
-d '{
"model": "kwaivgi/kling-v2.5-turbo-pro",
"input": {
"prompt": "Camera slowly zooms in, gentle wind blowing",
"image": "https://files.core.today/.../first_frame.jpg",
"duration": 5
}
}'카메라 워크 프롬프트
더 나은 비디오를 위해 카메라 움직임을 프롬프트에 포함하세요:
기본 움직임
zoom in- 줌 인zoom out- 줌 아웃pan left/right- 패닝tilt up/down- 틸트
고급 움직임
tracking shot- 트래킹drone shot- 드론 샷slow motion- 슬로우 모션time lapse- 타임랩스
모델 선택 가이드
저비용 빠른 생성
seedance-1-pro-fast (190크레딧)
고품질 T2V
hailuo-2.3 (420크레딧)
I2V (이미지→비디오)
kling-v2.5-turbo-pro (525크레딧)
최고 품질
veo-3.1 (4,800크레딧)