# 동영상 모델

> Nodaro에서 실행할 수 있는 모든 동영상 모델과 각 모델의 기능, 크레딧 가격을 정리했습니다.

Source: https://nodaro.ai/ko/docs/models/video

Nodaro에서는 64개의 동영상 모델을 실행할 수 있습니다. 아래 각 행은 해당 모델의 설정, 크레딧 가격, 프롬프트 팁을 담은 페이지로 연결됩니다.

## MiniMax

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [Hailuo 02 I2V Pro](https://nodaro.ai/docs/models/video/hailuo-02-i2v-pro) | MiniMax | Image to video, Text to video | 158 | Hailuo 02 Pro — strong photoreal motion, fixed 5-second clips. Supports end frame. |
| [MiniMax H3](https://nodaro.ai/docs/models/video/minimax-h3) | MiniMax | Image to video, Text to video | 253부터 | MiniMax H3 — premium multimodal tier: first/last frame + image/video/audio references, native audio, 2K (default) or 768P output, 4-15s per-second pricing. |
| [Hailuo 2.3 Pro](https://nodaro.ai/docs/models/video/hailuo-2-3-pro) | MiniMax | Image to video | 143부터 | Hailuo 2.3 Pro — newer Hailuo with 768P / 1080P resolutions. |
| [Hailuo 2.3 Standard](https://nodaro.ai/docs/models/video/hailuo-2-3-standard) | MiniMax | Image to video | 83부터 | Cheaper Hailuo 2.3 tier — good baseline quality. |
| [Hailuo 02 Standard](https://nodaro.ai/docs/models/video/hailuo-02-standard) | MiniMax | Image to video, Text to video | 83부터 | Hailuo 02 Standard — economical option with end-frame support. |

## Google

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [VEO 3.1 Quality](https://nodaro.ai/docs/models/video/veo-3-1-quality) | Google | Image to video, Text to video | 1,100부터 | Google VEO 3.1 Quality — premium cinematic video. 4/6/8s clips, optional end frame, native audio. No reference-to-video mode (Fast/Lite only). Flat per-generation pricing across durations. |
| [VEO 3.1 Fast](https://nodaro.ai/docs/models/video/veo-3-1-fast) | Google | Image to video, Text to video | 165부터 | VEO 3.1 Fast — cheaper VEO 3.1 tier, 4/6/8s with audio. Good balance for most uses. Flat per-generation pricing across durations. |
| [VEO 3.1 Lite](https://nodaro.ai/docs/models/video/veo-3-1-lite) | Google | Image to video, Text to video | 83부터 | VEO 3.1 Lite — most cost-effective VEO tier for high-volume generation. 4/6/8s with audio, supports first+last frame. |
| [Gemini Omni](https://nodaro.ai/docs/models/video/gemini-omni) | Google | Image to video, Text to video | 253부터 | Google multimodal video with native audio; text/image-to-video + video-edit. |
| [Gemini Omni Flash](https://nodaro.ai/docs/models/video/gemini-omni-flash) | Google | Image to video, Text to video | 176부터 | Google Gemini Omni Flash — faster/cheaper Omni tier: multimodal video with native audio, text/image-to-video + video-edit. |
| [VEO Extend](https://nodaro.ai/docs/models/video/veo-extend) | Google | Video extension | 209부터 | Extend an existing VEO 3.1 clip by another segment. |
| [VEO 1080p Upscale](https://nodaro.ai/docs/models/video/veo-1080p-upscale) | Google | Video upscaling | 22 | Upscale VEO output to 1080p. |
| [VEO 4K Upscale](https://nodaro.ai/docs/models/video/veo-4k-upscale) | Google | Video upscaling | 418 | Upscale VEO output to 4K. |

## Kuaishou

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [Kling 2.6](https://nodaro.ai/docs/models/video/kling-2-6) | Kuaishou | Image to video, Text to video | 152부터 | Kling 2.6 I2V — strong motion realism. 5s/10s, optional native audio. |
| [Kling 2.5 Turbo Pro](https://nodaro.ai/docs/models/video/kling-2-5-turbo-pro) | Kuaishou | Image to video, Text to video | 121부터 | Faster Kling — good quality at lower cost. Supports end frame. |
| [Kling 3.0](https://nodaro.ai/docs/models/video/kling-3-0) | Kuaishou | Image to video, Text to video | 297부터 | Premium Kling 3.0 — variable 3-15s duration, native audio, 720P/1080P. |
| [Kling 2.1 Master](https://nodaro.ai/docs/models/video/kling-2-1-master) | Kuaishou | Image to video | 440부터 | Master tier I2V — strong cinematic quality. |
| [Kling 3 Omni](https://nodaro.ai/docs/models/video/kling-3-omni) | Kuaishou | Image to video | 275부터 | Kling 3 Omni — 3-15s, 720p/1080p, end frame + reference images, native audio. |
| [Kling 2.6 Motion Transfer](https://nodaro.ai/docs/models/video/kling-2-6-motion-transfer) | Kuaishou | Motion transfer | 88부터 | Transfer the motion from a driving video onto a still subject. Kling 2.6 base. |
| [Kling 3.0 Motion Transfer](https://nodaro.ai/docs/models/video/kling-3-0-motion-transfer) | Kuaishou | Motion transfer | 165부터 | Premium motion transfer via Kling 3.0. |
| [Kling Avatar Standard](https://nodaro.ai/docs/models/video/kling-avatar-standard) | Kuaishou | Lip sync | 308 | Lip-sync a still portrait to driving audio. Standard quality. |
| [Kling Avatar Pro](https://nodaro.ai/docs/models/video/kling-avatar-pro) | Kuaishou | Lip sync | 616 | Premium lip-sync — better mouth shape and timing. |

## xAI

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [Grok Imagine (I2V)](https://nodaro.ai/docs/models/video/grok-imagine-i2v) | xAI | Image to video | 55부터 | Grok image-to-video — stylized motion. Up to 15s. |
| [Grok Imagine Video 1.5](https://nodaro.ai/docs/models/video/grok-imagine-video-1-5) | xAI | Image to video | 325부터 | Grok Imagine 1.5 image-to-video — 1–15s, 480p/720p, per-second pricing. Requires an input image. |

## Bytedance

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [Seedance 2](https://nodaro.ai/docs/models/video/seedance-2) | Bytedance | Image to video, Text to video | 253부터 | Seedance 2 — premium tier with native audio. Per-second pricing by resolution. |
| [Seedance 2 Fast](https://nodaro.ai/docs/models/video/seedance-2-fast) | Bytedance | Image to video, Text to video | 198부터 | Cheaper / quicker Seedance 2 tier. |
| [Seedance 2 Mini](https://nodaro.ai/docs/models/video/seedance-2-mini) | Bytedance | Image to video, Text to video | 132부터 | Budget Seedance 2 tier — 480p/720p only, per-second pricing by resolution. |
| [Seedance 2.5](https://nodaro.ai/docs/models/video/seedance-2-5) | Bytedance | Image to video, Text to video | 374부터 | Seedance 2.5 — up to 30s in one shot, native audio, wide multimodal references. 480p/720p/1080p. |
| [Bytedance Lite I2V](https://nodaro.ai/docs/models/video/bytedance-lite-i2v) | Bytedance | Image to video, Text to video | 63 | Cheapest Bytedance video tier with end-frame support. |
| [Bytedance Pro I2V](https://nodaro.ai/docs/models/video/bytedance-pro-i2v) | Bytedance | Image to video, Text to video | 193 | Pro Bytedance video tier — better quality. |
| [Bytedance Pro Fast I2V](https://nodaro.ai/docs/models/video/bytedance-pro-fast-i2v) | Bytedance | Image to video | 99 | Faster Bytedance Pro variant. |
| [Seedance 2 Extend](https://nodaro.ai/docs/models/video/seedance-2-extend) | Bytedance | Video extension | 286부터 | Extend ANY video: generates the continuation (audio included) and trim-stitches it into one seamless clip. |
| [OmniHuman 1.5](https://nodaro.ai/docs/models/video/omnihuman-1-5) | Bytedance | Lip sync | 1,122부터 | Premium prompt-directed talking avatar from a still image + audio. 720p / 1080p, up to 60s. People, pets, anime. |

## Alibaba

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [Wan 3.0](https://nodaro.ai/docs/models/video/wan-3-0) | Alibaba | Image to video, Text to video | 176부터 | Wan 3.0 — multimodal: first/last frame or image/video/audio references, native audio, 2-30s at 480p/720p/1080p. |
| [Wan 3.0 Prime](https://nodaro.ai/docs/models/video/wan-3-0-prime) | Alibaba | Image to video, Text to video | 275부터 | Wan 3.0 Prime — Alibaba's high-speed Wan 3.0 tier: same multimodal surface and 2-30s range, faster turnaround at a higher per-second rate. |
| [Wan 2.6 I2V](https://nodaro.ai/docs/models/video/wan-2-6-i2v) | Alibaba | Image to video | 193부터 | Wan 2.6 image-to-video — 5/10/15s at 720p/1080p. |
| [Wan 2.2 Turbo](https://nodaro.ai/docs/models/video/wan-2-2-turbo) | Alibaba | Image to video, Text to video | 110부터 | Cheap, fast Wan turbo — 5s. Serves both i2v and t2v under one id. |
| [Wan 2.6](https://nodaro.ai/docs/models/video/wan-2-6) | Alibaba | Video to video, Text to video | 193부터 | Wan 2.6 — text-to-video and video-to-video under a single id. |
| [Wan Flash V2V](https://nodaro.ai/docs/models/video/wan-flash-v2v) | Alibaba | Video to video | 110 | Faster Wan V2V variant. |
| [Wan 2.7 VideoEdit](https://nodaro.ai/docs/models/video/wan-2-7-videoedit) | Alibaba | Video to video | 352 | Guided video editing with optional reference image, audio control, and prompt expansion. |
| [Wan 2.7 I2V](https://nodaro.ai/docs/models/video/wan-2-7-i2v) | Alibaba | Image to video | 207 | Wan 2.7 image-to-video — 2–15s at 720p/1080p, supports start+end frame. |
| [Wan 2.7 T2V](https://nodaro.ai/docs/models/video/wan-2-7-t2v) | Alibaba | Text to video | 207 | Wan 2.7 text-to-video — 2–15s at 720p/1080p. |

## Lightricks

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [LTX 2.3 Pro](https://nodaro.ai/docs/models/video/ltx-2-3-pro) | Lightricks | Image to video, Text to video | 264부터 | Lightricks LTX 2.3 Pro — text/image/audio→video up to 4K, 6/8/10s, end-frame interpolation. |
| [LTX 2.3 Fast](https://nodaro.ai/docs/models/video/ltx-2-3-fast) | Lightricks | Image to video, Text to video | 198부터 | Lightricks LTX 2.3 Fast — text/image→video up to 20s at 1080p (6/8/10s at 2K and 4K). No audio input, no extend. |

## HappyHorse

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [HappyHorse 1.1](https://nodaro.ai/docs/models/video/happyhorse-1-1) | HappyHorse | Text to video | 311 | HappyHorse 1.1 text-to-video — 3–15s at 720p/1080p, 9 aspect ratios incl. 21:9/9:21, per-second pricing. |
| [HappyHorse 1.1 I2V](https://nodaro.ai/docs/models/video/happyhorse-1-1-i2v) | HappyHorse | Image to video | 311 | HappyHorse 1.1 image-to-video — 3–15s at 720p/1080p, aspect ratio inferred from input image, per-second pricing. |
| [HappyHorse 1.1 Ref2V](https://nodaro.ai/docs/models/video/happyhorse-1-1-ref2v) | HappyHorse | Image to video | 311 | HappyHorse 1.1 reference-to-video — 1–9 reference images, 3–15s at 720p/1080p, per-second pricing. |
| [HappyHorse Edit](https://nodaro.ai/docs/models/video/happyhorse-edit) | HappyHorse | Video to video | 385 | HappyHorse video-edit — video-to-video transformation, up to 60s input, 720p/1080p output. |

## Runway

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [Runway Gen-3](https://nodaro.ai/docs/models/video/runway-gen-3) | Runway | Image to video, Text to video | 33 | Runway Gen-3. 5/10s at 720p/1080p. |
| [Runway Aleph V2V](https://nodaro.ai/docs/models/video/runway-aleph-v2v) | Runway | Video to video | 385 | Runway Aleph — video-to-video conversion. |
| [Runway Extend](https://nodaro.ai/docs/models/video/runway-extend) | Runway | Video extension | 352 | Extend a Runway video by another clip. |

## Topaz

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [Topaz Video Upscale](https://nodaro.ai/docs/models/video/topaz-video-upscale) | Topaz | Video upscaling | 209 | High-quality video upscale and enhancement. |

## InfiniTalk

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [InfiniTalk](https://nodaro.ai/docs/models/video/infinitalk) | InfiniTalk | Lip sync | 121부터 | Audio-driven talking-head from a still image. 480p / 720p. |

## Sync

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [Sync Lipsync v3](https://nodaro.ai/docs/models/video/sync-lipsync-v3) | Sync | Lip sync | 1,100부터 | Dub existing footage — re-syncs lips to a new audio track. Video input, billed per second. |

## Volcengine

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [Volcengine Lip Sync](https://nodaro.ai/docs/models/video/volcengine-lip-sync) | Volcengine | Lip sync | 330부터 | Video-to-video AI dubbing — re-syncs lips to a new vocal track. Multi-speaker (scene detection + speaker ID) in basic mode. Video input, billed per second. |

## Depth Anything

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [Video Depth Anything](https://nodaro.ai/docs/models/video/video-depth-anything) | Depth Anything | Video depth | 330부터 | Temporally consistent depth video from any clip. Grayscale or colormapped, up to 2,400 frames or 300 seconds. |
| [Depth Anything (per frame)](https://nodaro.ai/docs/models/video/depth-anything-per-frame) | Depth Anything | Video depth | 33부터 | Depth Anything v1 run on each frame. Grayscale or inferno colormap; may flicker between frames. Up to 80 s. |

## Nodaro

| Model | Maker | Modes | Credits | Details |
| --- | --- | --- | --- | --- |
| [Video Analysis (Fast)](https://nodaro.ai/docs/models/video/video-analysis-fast) | Nodaro | Video analysis | 200부터 | Analyze a video into a structured shot list (scenes, camera, audio) — fast, economy tier. Billed per duration bucket. |
| [Video Analysis (Fast — legacy)](https://nodaro.ai/docs/models/video/video-analysis-fast-legacy) | Nodaro | Video analysis | 225부터 | Legacy fast-tier analysis model (backed the fast tier from 2026-07 until 2026-07-29). Kept so stored raw-model configs keep running and keep pricing under their own identifier; new fast-tier runs use the current fast model. |
| [Video Analysis (Pro)](https://nodaro.ai/docs/models/video/video-analysis-pro) | Nodaro | Video analysis | 238부터 | Analyze a video into a structured shot list (scenes, camera, audio) — higher-fidelity, default tier. Billed per duration bucket. |
| [Video Analysis (Mixed)](https://nodaro.ai/docs/models/video/video-analysis-mixed) | Nodaro | Video analysis | 297부터 | Our most advanced analysis tier — multiple analysis engines combined into one result for maximum completeness and accuracy. Billed per duration bucket. |
| [Video Analysis (Smart)](https://nodaro.ai/docs/models/video/video-analysis-smart) | Nodaro | Video analysis | 455부터 | Highest-accuracy analysis — a hybrid pass that blends a native skeleton read with several donor analysis rolls, then always refines the merged result to find shot boundaries and identify the cast by appearance. Best choice when the shot list will drive regeneration. Billed per duration bucket. |
| [AI Audit](https://nodaro.ai/docs/models/video/ai-audit) | Nodaro | Video audit | 237부터 | Re-watches a clip against a wired analysis, applies video-verified corrections under guards, and returns a disclosed report of what changed. Billed per duration bucket. |
| [AI Audit (with analysis run)](https://nodaro.ai/docs/models/video/ai-audit-with-analysis-run) | Nodaro | Video audit | 436부터 | Same video-verified audit as AI Audit, but auto-runs a fast analysis first when none is wired in, then applies corrections under guards and returns a disclosed report. Billed per duration bucket. |