Skip to main content
Videos

Video generation models

Choose a model for text-to-video, image-to-video, video editing, and more.

Migrate from closed-source models

Map your current Sora, Veo, Kling, or Runway model to an equivalent QwenCloud model.
Model capabilityClosed-source examplesQwenCloud recommendation
Text-to-video (t2v), Image-to-video (i2v)Sora 2, Veo 3.1, Kling 3.0happyhorse-1.1-t2v, happyhorse-1.1-i2v, wan3.0-video, wan3.0-video-prime
Reference-to-video (r2v)Seedance 2.0, Runway Gen-4happyhorse-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 the Wan series, use wan3.0-video, which supports longer videos (up to 30s), adaptive aspect ratio, smart duration, sound toggle, and reference audio, at 480P, 720P, and 1080P. 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.
ModelUse this when...Max resolutionMax duration
wan3.0-videoText-to-video, first-frame/first+last-frame, all-in-one reference480P, 720P, 1080P2--30s
wan3.0-video-primeText-to-video, first-frame/first+last-frame, all-in-one reference (high-speed)480P, 720P, 1080P2--30s
happyhorse-1.1-t2vText-to-video480P, 720P, 1080P3--15s
happyhorse-1.1-i2vImage-to-video (first frame)480P, 720P, 1080P3--15s
happyhorse-1.1-r2vReference images to video480P, 720P, 1080P3--15s
happyhorse-1.0-video-editVideo editing720P, 1080P3--15s
wan2.7-videoeditVideo editing, effect/camera replication720P, 1080Pup to 10s
wan2.2-animate-moveTransfer motion to a static character720P2--30s
wan2.2-animate-mixReplace a character in a video720P2--30s

All models

In the console, the model list, search results, versions, prices, and rate limits follow the current region. Models differ by region, and some are available only in specific regions, so you can only compare models within the same region. Before you choose a model, check the region's tab in Model prices. See Regions and endpoints.
The model pages in the console, including model details and model comparison, show the models, prices, and rate limits of the region selected in the upper-right corner. A model offered in one region may not be listed in another. If you switch regions while a model detail page or the comparison list is open, a model that is not available in the new region is flagged, and the page shows the other regions where the model is available. The comparison page stays open even if only one model remains.
ModelCapabilityFeaturesOutput
happyhorse-1.1-t2vText-to-videoAudio480P, 720P, 1080P. 3–15s. 24 fps, MP4
happyhorse-1.1-i2vFirst-frame image-to-videoAudio480P, 720P, 1080P. 3–15s. 24 fps, MP4
happyhorse-1.1-r2vReference-to-videoAudio480P, 720P, 1080P. 3–15s. 24 fps, MP4
ModelCapabilityFeaturesOutput
happyhorse-1.0-t2vText-to-videoAudio720P, 1080P. 3–15s. 24 fps, MP4
happyhorse-1.0-i2vFirst-frame image-to-videoAudio720P, 1080P. 3–15s. 24 fps, MP4
happyhorse-1.0-r2vReference-to-videoAudio720P, 1080P. 3–15s. 24 fps, MP4
happyhorse-1.0-video-editVideo editingAudio720P, 1080P. 3–15s. 24 fps, MP4
ModelCapabilityFeaturesOutput
wan3.0-videoAll-in-One referenceText-to-video, first/last-frame, all-in-one reference, audio, audio toggle, smart duration, adaptive aspect ratio480P, 720P, 1080P. 2-30s. 30 fps, MP4
wan3.0-video-primeAll-in-One reference (speed-optimized)Text-to-video, first/last-frame, all-in-one reference, audio, audio toggle, smart duration, adaptive aspect ratio480P, 720P, 1080P. 2-30s. 30 fps, MP4
ModelCapabilityFeaturesOutput
wan2.7-t2vText-to-videoAudio sync, multi-shot narrative720P, 1080P. 2–15s. 30 fps, MP4
wan2.7-t2v-2026-06-12Text-to-video (snapshot)Audio sync, multi-shot narrative720P, 1080P. 2–15s. 30 fps, MP4
wan2.7-t2v-2026-04-25Text-to-video (snapshot)Audio sync, multi-shot narrative720P, 1080P. 2–15s. 30 fps, MP4
wan2.7-i2vImage-to-videoFirst frame, first/last frame, video continuation, audio-driven720P, 1080P. 2–15s. 30 fps, MP4
wan2.7-i2v-2026-04-25Image-to-video (snapshot)First frame, first/last frame, video continuation, audio-driven720P, 1080P. 2–15s. 30 fps, MP4
wan2.7-r2v-2026-06-12Reference-to-videoMulti-character, image/video reference format720P, 1080P. 2–10s. 30 fps, MP4
wan2.7-videoeditVideo editingInstruction editing, video migration720P, 1080P. Up to 10s. 30 fps, MP4
ModelCapabilityFeaturesOutput
wan2.6-t2vText-to-videoAudio sync, multi-shot narrative720P, 1080P. 2–15s. 30 fps, MP4
wan2.6-i2vImage-to-videoAudio sync, multi-shot narrative720P, 1080P. 2–15s. 30 fps, MP4
wan2.6-i2v-flashImage-to-videoAudio, multi-shot, fast generation720P, 1080P. 2–15s. 30 fps, MP4
wan2.6-r2vReference-to-videoAudio sync, multi-character, narrative720P, 1080P. 2–10s. 30 fps, MP4
wan2.6-r2v-flashReference-to-videoMulti-character, fast generation720P, 1080P. 2–10s. 30 fps, MP4
ModelCapabilityFeaturesOutput
wan2.5-t2v-previewText-to-videoAudio sync480P, 720P, 1080P. 5s, 10s. 30 fps, MP4
wan2.5-i2v-previewImage-to-videoAudio sync480P, 720P, 1080P. 5s, 10s. 30 fps, MP4
ModelCapabilityFeaturesOutput
wan2.2-t2v-plusText-to-videoNo audio480P, 1080P. 5s. 30 fps, MP4
wan2.2-i2v-plusImage-to-videoNo audio480P, 1080P. 5s. 30 fps, MP4
wan2.2-i2v-flashImage-to-videoNo audio, 50% faster than Wan 2.1480P, 720P, 1080P. 5s. 30 fps, MP4
wan2.2-kf2v-flashFirst/last-frameNo audio480P, 720P, 1080P. 5s. 30 fps, MP4
wan2.2-animate-moveCharacter animationwan-std / wan-pro modes720P. 2–30s. 15/25 fps. MP4
wan2.2-animate-mixCharacter replacementwan-std / wan-pro modes720P. 2–30s. 15/25 fps. MP4

Learn more