Video generation and editing - Alibaba Cloud Model Studio

Choose the right model for text-to-video, image-to-video, and video editing.

Migrate from closed-source models

Map your current Sora, Veo, Kling, or Runway model to an equivalent Bailian model.

Model capability	Closed-source examples	Bailian recommendation
Text-to-video (t2v), Image-to-video (i2v)	Sora 2, Veo 3.1, Kling 3.0	`happyhorse-1.1-t2v`, `happyhorse-1.1-i2v`, `wan3.0-video`, `wan3.0-video-prime`
Reference-to-video (r2v)	Seedance 2.0, Runway Gen-4	`happyhorse-1.1-r2v`, `wan3.0-video`, `wan3.0-video-prime`

Text-to-video

Generate videos with audio from text prompts. We recommend happyhorse-1.1-t2v. It supports 1080P resolution and clips up to 15 seconds long.

For longer videos (up to 30s), adaptive aspect ratio, smart duration, audio toggle, and reference audio, use wan3.0-video. It supports 480P, 720P, and 1080P resolutions. The speed-optimized version wan3.0-video-prime significantly improves generation speed while maintaining high quality.

Image-to-video

Create dynamic videos from static images. For first-frame image-to-video, use happyhorse-1.1-i2v. For the Wan series, use wan3.0-video (speed-optimized: wan3.0-video-prime), which supports first-frame and first/last-frame image-to-video.

First-frame image-to-video

Generate video from a single image. We recommend happyhorse-1.1-i2v, which supports audio, 1080P, and 3 to 15 seconds.

First/last-frame stitching for long videos

Use a first/last-frame model such as wan3.0-video to stitch multiple clips together. Setting the last frame of one clip as the first frame of the next creates seamless transitions, ideal for narratives, product demos, or tutorials.

Reference image-to-video

Maintain character consistency across scenes using reference images. We recommend happyhorse-1.1-r2v. For the Wan series, use wan3.0-video (speed-optimized: wan3.0-video-prime), which supports all-in-one reference capabilities with multiple reference images, videos, and audio. It also supports file input (docx, ppt, pdf, etc.) and web links as references.

Video editing

Edit existing videos using text instructions for style transfer, element replacement, and other operations. We recommend happyhorse-1.0-video-edit. For effect replication or camera movement replication, use wan2.7-videoedit.

Character animation

Motion-driven character animation

To transfer motion from a reference video to a character in a static image, use wan2.2-animate-move. The background remains unchanged. The pro mode (wan-pro) produces results closer to live-action footage, while the standard mode (wan-std) is faster and more cost-effective.

Character replacement in video

To replace a character in a video with one from a source image, use wan2.2-animate-mix. It also supports pro and standard modes.

Recommended models

Model ID	Use case	Max resolution	Max duration
`wan3.0-video`	Text-to-video, first/last-frame image-to-video, all-in-one reference-to-video	480P, 720P, 1080P	2-30s
`wan3.0-video-prime`	Text-to-video, first/last-frame image-to-video, all-in-one reference-to-video (speed-optimized)	480P, 720P, 1080P	2-30s
`happyhorse-1.1-t2v`	Text-to-video	480P, 720P, 1080P	3–15s
`happyhorse-1.1-i2v`	First-frame image-to-video	480P, 720P, 1080P	3–15s
`happyhorse-1.1-r2v`	Reference image-to-video	480P, 720P, 1080P	3–15s
`happyhorse-1.0-video-edit`	Video editing	720P, 1080P	3–15s
`wan2.7-videoedit`	Video editing, effect replication, camera movement replication	720P, 1080P	2–10s
`wan2.2-animate-move`	Transfer motion to a static character	720P	2–30s
`wan2.2-animate-mix`	Replace a character in a video	720P	2–30s

All models

HappyHorse 1.1

Model ID	Type	Features	Output specs
`happyhorse-1.1-t2v`	Text-to-video	Audio	480P, 720P, 1080P. 3–15s. 24 fps, MP4
`happyhorse-1.1-i2v`	First-frame image-to-video	Audio	480P, 720P, 1080P. 3–15s. 24 fps, MP4
`happyhorse-1.1-r2v`	Reference image-to-video	Audio	480P, 720P, 1080P. 3–15s. 24 fps, MP4

HappyHorse 1.0

Model ID	Type	Features	Output specs
`happyhorse-1.0-t2v`	Text-to-video	Audio	720P, 1080P. 3–15s. 24 fps, MP4
`happyhorse-1.0-i2v`	First-frame image-to-video	Audio	720P, 1080P. 3–15s. 24 fps, MP4
`happyhorse-1.0-r2v`	Reference image-to-video	Audio	720P, 1080P. 3–15s. 24 fps, MP4
`happyhorse-1.0-video-edit`	Video editing	Audio	720P, 1080P. 3–15s. 24 fps, MP4

Wan 3.0

Model ID	Type	Features	Output specs
`wan3.0-video`	All-in-One reference	Text-to-video, first/last-frame, all-in-one reference, audio, audio toggle, smart duration, adaptive aspect ratio	480P, 720P, 1080P. 2-30s. 30 fps, MP4
`wan3.0-video-prime`	All-in-One reference (speed-optimized)	Text-to-video, first/last-frame, all-in-one reference, audio, audio toggle, smart duration, adaptive aspect ratio	480P, 720P, 1080P. 2-30s. 30 fps, MP4

Wan 2.7

Model ID	Type	Features	Output specifications
`wan2.7-t2v`	text-to-video	Audio sync, multi-shot narrative	720P, 1080P. 2–15s. 30 fps, MP4
`wan2.7-t2v-2026-06-12`	text-to-video	Audio sync, multi-shot narrative	720P, 1080P. 2–15s. 30 fps, MP4
`wan2.7-t2v-2026-04-25`	text-to-video	Audio sync, multi-shot narrative	720P, 1080P. 2–15s. 30 fps, MP4
`wan2.7-i2v`	image-to-video	First frame, first/last frame, video continuation, audio-driven	720P, 1080P. 2–15s. 30 fps, MP4
`wan2.7-i2v-2026-04-25`	image-to-video	First frame, first/last frame, video continuation, audio-driven	720P, 1080P. 2–15s. 30 fps, MP4
`wan2.7-r2v-2026-06-12`	video reference	Multi-character, ImageN/VideoN reference format	720P, 1080P. 2–10s. 30 fps, MP4
`wan2.7-videoedit`	video editing	Instruction-based editing, style transfer	720P, 1080P. 2–10s. 30 fps, MP4

Wan 2.6

Model ID	Type	Features	Output specifications
`wan2.6-t2v`	text-to-video	Audio sync, multi-shot narrative	720P, 1080P. 2–15s. 30 fps, MP4
`wan2.6-i2v`	image-to-video	Audio sync, multi-shot narrative	720P, 1080P. 2–15s. 30 fps, MP4
`wan2.6-i2v-flash`	image-to-video	Audio, multi-shot, fast generation	720P, 1080P. 2–15s. 30 fps, MP4
`wan2.6-r2v`	video reference	Audio sync, multi-character, narrative	720P, 1080P. 2–10s. 30 fps, MP4
`wan2.6-r2v-flash`	video reference	Multi-character, fast generation	720P, 1080P. 2–10s. 30 fps, MP4
`wan2.6-t2v-us`	text-to-video	Audio sync, multi-shot narrative; for US deployment scope	720P, 1080P. 2–15s. 30 fps, MP4
`wan2.6-i2v-us`	image-to-video	Audio sync, multi-shot narrative; for US deployment scope	720P, 1080P. 2–15s. 30 fps, MP4

Wan 2.5

Model ID	Type	Features	Output specifications
`wan2.5-t2v-preview`	text-to-video	Audio sync	480P, 720P, 1080P. 5s, 10s. 30 fps, MP4
`wan2.5-i2v-preview`	image-to-video	Audio sync	480P, 720P, 1080P. 5s, 10s. 30 fps, MP4

Wan 2.2

Model ID	Type	Features	Output specifications
`wan2.2-t2v-plus`	text-to-video	No audio	480P, 1080P. 5s. 30 fps, MP4
`wan2.2-i2v-plus`	image-to-video	No audio	480P, 1080P. 5s. 30 fps, MP4
`wan2.2-i2v-flash`	image-to-video	No audio, 50% faster than 2.1	480P, 720P, 1080P. 5s. 30 fps, MP4
`wan2.2-kf2v-flash`	first/last frame	No audio	480P, 720P, 1080P. 5s. 30 fps, MP4
`wan2.2-animate-move`	character animation	wan-std / wan-pro modes	720P. 2–30s. 15/25 fps. MP4
`wan2.2-animate-mix`	character replacement	wan-std / wan-pro modes	720P. 2–30s. 15/25 fps. MP4

Wan 2.1 (Wan 2.7 is recommended)

Model ID	Type	Features	Output specifications
`wan2.1-t2v-plus`	text-to-video	No audio	720P. 5s. 30 fps, MP4
`wan2.1-t2v-turbo`	text-to-video	No audio	480P, 720P. 5s. 30 fps, MP4
`wan2.1-i2v-plus`	image-to-video	No audio	720P. 5s. 30 fps, MP4
`wan2.1-i2v-turbo`	image-to-video	No audio	480P, 720P. 3–5s. 30 fps, MP4
`wan2.1-kf2v-plus`	first/last frame	No audio	720P. 5s. 30 fps, MP4
`wan2.1-vace-plus`	video editing	No audio	720P. Max 5s. 30 fps, MP4