image-to-video
PixVerse C1 首末帧转视频
PixVerse C1 首末帧转视频模型可根据起始帧和结束帧生成平滑的视频过渡效果，支持多种分辨率和时长配置，可选同步生成音频。
Pixverse V6 图生视频
Pixverse V6 图生视频模型，支持将静态图像转换为动态视频，支持多种分辨率和音频生成。
Pixverse V6 转场视频生成
Pixverse V6 转场视频生成模型。通过文本提示在两张图片之间生成平滑的转场视频，支持多种分辨率和音频生成。
万相 Wan 2.7参考生视频
万相 Wan 2.7参考生视频模型，支持多模态输入（文本/图像/视频），可将人或物体作为主角，生成单角色表演或多角色互动视频。支持智能分镜，生成多镜头视频。支持720P和1080P分辨率，时长2~10秒，按秒计费。输出默认包含音频。
Pixverse C1 参考图生视频
Pixverse C1 参考图生视频工具可根据 1-7 张参考图像生成电影级视频，通过 @ref_name 语法在提示词中引用参考图，支持多角色/物体一致性、多分辨率（360p-1080p）、可变时长（1-15秒）及音频生成。
PixVerse C1 图生视频
PixVerse C1 图生视频模型可将静态图像转换为电影级动态视频，支持 1-15 秒时长、最高 1080p 分辨率，并可选生成原生音频。
Veo 3.1 Lite 首末帧生视频
使用 Google Veo 3.1 Lite 模型从首帧和末帧图片生成视频。支持 4秒、6秒和8秒时长，720p和1080p分辨率，16:9和9:16宽高比。可选音频生成。输入图片最大 20MB。
Veo 3.1 Lite 图生视频
使用 Google Veo 3.1 Lite 模型从输入图片生成视频。支持 4秒、6秒和8秒时长，720p和1080p分辨率，16:9和9:16宽高比。可选音频生成。输入图片最大 20MB。
Veo 3.1: Generating Videos from Reference Images
Use the Google Veo 3.1 model to generate videos guided by 1–3 reference images. It supports 720p and 1080p resolutions, as well as 16:9 and 9:16 aspect ratios. The video length is fixed at 8 seconds. Only "asset" reference types are supported.
Veo 3.1: Generating Video from Start and End Frames
Using the Google Veo 3.1 model, generate a transition video based on the provided start and end frames. Supports durations of 4, 6, or 8 seconds, resolutions of 720p and 1080p, and optional audio generation.
Veo 3.1 Fast: Generating Videos from Reference Images
Use the Google Veo 3.1 Fast model to generate videos guided by 1–3 reference images. Supports 720p and 1080p resolutions, as well as 16:9 and 9:16 aspect ratios. The video duration is fixed at 8 seconds. Only "asset" reference types are supported.
Veo 3.1 Fast: Generating Video from Start and End Frames
Generate videos by specifying a start frame and an end frame, combined with text prompts. The model interpolates between the two frames to generate coherent motion content. Use the Google Veo 3.1 Fast model (veo-3.1-fast-generate-001) for faster generation.
Kling v3.0 Pro: Image to Video
Kling 3.0 is a high-quality model designed for video generation. Its strengths lie in smooth motion and cinematography that closely mimics real-life footage, with excellent control over the rhythm of character movements, camera movements (zooms, pans, and tilts), and spatial relationships within scenes. It delivers consistent results in terms of material texture, lighting variations, and detail consistency (including character clothing, props, and backgrounds). It is ideal for creating short films, storyboards for commercials, and dynamic proof-of-concepts, and its controllability can be further enhanced through clear shot script prompts.It supports an ultra-fast inference API, offers stable performance with no waiting time, and delivers exceptional value for money.
Kling v3.0: Standard Image-to-Video
Kling 3.0 is a high-quality model designed for video generation. Its strengths lie in smooth motion and cinematography that closely mimics real-life footage, with excellent control over the rhythm of character movements, camera movements (zooms, pans, and tilts), and spatial relationships within scenes. It delivers consistent results in terms of material texture, lighting variations, and detail consistency (including character clothing, props, and backgrounds). It is ideal for creating short films, storyboards for commercials, and dynamic proof-of-concepts, and its controllability can be further enhanced through clear shot script prompts.It supports an ultra-fast inference API, offers stable performance with no waiting time, and delivers exceptional value for money.
Wan 2.1: Image to Video
Alibaba Tongyi Wan is renowned for its high image quality, strong temporal consistency, and ability to follow complex prompts, making it ideal for large-scale commercial video generation. Wan 2.1 enhances motion stability and texture detail, making it suitable for bulk production in e-commerce and advertising. Image-to-Video supports driving motion and camera movements using a single reference image, making it ideal for character dance sequences, product demonstrations, and style extensions. The real-time inference API offers stable performance, no waiting time, and affordable pricing.
Wan 2.2: Image to Video
Alibaba Tongyi Wan is renowned for its high image quality, strong temporal consistency, and ability to handle complex prompts, making it ideal for large-scale commercial video generation. Wan 2.2 enhances shot continuity and the naturalness of character movements, delivering more stable results in complex scenes. Its image-to-video generation supports driving both motion and camera work using a single reference image, making it suitable for dance performances, product demonstrations, and style extensions. The real-time inference API offers stable performance with no waiting time and is affordably priced.
Wan 2.5 Image-to-Video Preview
Alibaba Tongyi Wan is renowned for its high image quality, strong temporal consistency, and precise prompt adherence, making it ideal for large-scale commercial video generation. Wan 2.5 delivers further improvements in image clarity and prompt adherence, while the preview version facilitates rapid trial-and-error testing. Image-to-video generation supports using a single reference image to drive motion and camera work, making it suitable for dance performances, product demonstrations, and style extensions. The real-time inference API offers stable performance, zero wait times, and affordable pricing.
Seedance 1.5 Pro: Image to Video
The Seedance series offers reliable generation capabilities, making it ideal for production environments. Designed for production-level use, this series prioritizes stability and controllable output. Its image-to-video feature allows a single reference image to drive motion and camera work, making it suitable for dance performances, product demonstrations, and stylistic extensions. The real-time inference API delivers stable performance with no waiting time and is affordably priced.
Wan 2.6 Image to Video
The Wan2.6 series offers reliable generation capabilities, making it ideal for production environments. Designed for production-level use, this series prioritizes stability and predictable output. Image-to-video generation supports driving motion and camera work using a single reference image, making it suitable for dance performances, product demonstrations, and stylistic extensions. The real-time inference API delivers stable performance with no waiting time and is affordably priced.
Sora 2: Image to Video
The Sora 2 series offers reliable generation capabilities, making it ideal for production environments. Designed for production-grade use, this series prioritizes stability and controllable output. Its image-to-video feature uses a single reference image to drive character movements and camera work, making it suitable for dance performances, product demonstrations, and stylistic extensions. The real-time inference API delivers consistent performance with no waiting time and is affordably priced.