模型广场

选择模型后可复制配置给 AI,也可以快速测试当前连接延迟。

重置筛选
全部 8文本 0图像 0音频 0视频 8

happyhorse-1.0-i2v

图像视频

Alibaba

Extends a single starting image into a full shot, preserving its composition and style, and outputs 3–15 second clips at up to 1080p. Suited for turning still assets into motion.

上下文
待核
输入 / 1M tokens
-
输出 / 1M tokens
-
缓存读 / 1M
-
缓存写 / 1M
-
Creative GenerationHigh-Quality GenerationContent Generation

happyhorse-1.0-r2v

图像视频

Alibaba

Takes a set of reference images to lock character, scene, and style, holding the subject consistent across shots. Outputs 3–15 second clips at up to 1080p.

上下文
待核
输入 / 1M tokens
-
输出 / 1M tokens
-
缓存读 / 1M
-
缓存写 / 1M
-
Creative GenerationHigh-Quality GenerationContent Generation

happyhorse-1.1-i2v

图像视频

Alibaba

Smoother motion than 1.0 across camera moves and body movement. Extends a single starting image into a full shot, outputting 3–15 second clips at up to 1080p.

上下文
待核
输入 / 1M tokens
-
输出 / 1M tokens
-
缓存读 / 1M
-
缓存写 / 1M
-
Creative GenerationHigh-Quality GenerationContent Generation

happyhorse-1.1-r2v

图像视频

Alibaba

Holds characters more consistent across frames than 1.0. Takes a set of reference images to lock character, scene, and style, outputting 3–15 second clips at up to 1080p.

上下文
待核
输入 / 1M tokens
-
输出 / 1M tokens
-
缓存读 / 1M
-
缓存写 / 1M
-
Creative GenerationHigh-Quality GenerationContent Generation

wan2.6-i2v

文本图像音频视频

Alibaba

Alibaba Tongyi Wanxiang Wan 2.6 image-to-video model animates a reference image into 720p/1080p clips with synchronized audio, preserving subject consistency with cinematic motion.

上下文
待核
输入 / 1M tokens
-
输出 / 1M tokens
-
缓存读 / 1M
-
缓存写 / 1M
-
Creative GenerationMultimodal Understanding

wan2.6-i2v-flash

文本图像音频视频

Alibaba

Speed-optimized Wan 2.6 image-to-video variant with optional audio output, generating 720p/1080p clips quickly and cost-effectively for high-throughput image animation.

上下文
待核
输入 / 1M tokens
-
输出 / 1M tokens
-
缓存读 / 1M
-
缓存写 / 1M
-
Cost EffectiveReal-time ResponseCreative Generation

wan2.6-r2v

文本视频图像视频

Alibaba

Alibaba Tongyi Wanxiang Wan 2.6 reference-to-video model replicates the actions, effects, and camera movement of a reference video to produce up to 10 second 720p/1080p clips with synchronized audio.

上下文
待核
输入 / 1M tokens
-
输出 / 1M tokens
-
缓存读 / 1M
-
缓存写 / 1M
-
Creative GenerationMultimodal Understanding

wan2.6-r2v-flash

文本视频图像视频

Alibaba

Speed-optimized Wan 2.6 reference-to-video variant with optional audio output, replicating reference-video motion into up to 10 second 720p/1080p clips for fast, cost-effective production.

上下文
待核
输入 / 1M tokens
-
输出 / 1M tokens
-
缓存读 / 1M
-
缓存写 / 1M
-
Cost EffectiveReal-time ResponseCreative Generation
需要完整模型清单或企业接入方案?进入控制台