MiniMax H3 （自部署）

MiniMax H3 is a general-purpose, omni-modal video generation model developed by MiniMax. It unifies the understanding of text, images, video, and audio inputs, and is capable of generating videos up to 15 seconds in length at 2K resolution with native stereo audio. Unlike earlier systems that separated tasks such as text-to-video, image-to-video, and editing into distinct models, H3 treats them as a single generalized task, using natural language to describe how reference materials relate to the target output.

Doubao-Seedance-2.0

豆包大模型团队推出的新一代专业级多模态创作视频模型 Seedance 2.0，支持图像、视频、音频等多模态作为参考输入生成视频，还具备视频编辑、延长等能力，能高精度还原各类细节并稳定角色特征，具备极致拟真的视听稳定性，深度适配商业广告、影视制作与社交媒体营销等各大核心场景

HappyHorse-1.1-I2V

HappyHorse-1.1-I2V supports image-to-video generation, further enhancing visual quality, dynamic performance, and cross-clip consistency. The model can more accurately understand input images and continue the creative intent, bringing significant improvements in character skin texture, cross-clip ID consistency, motion fluidity, text rendering stability, and audio-visual synchronization, outputting high-quality videos that are more realistic, natural, rich in detail, and highly consistent.

HappyHorse-1.1-T2V

HappyHorse-1.1-T2V supports text-to-video generation, further enhancing text semantic understanding, camera scheduling, and dynamic generation performance. The model can more accurately restore creative intent, generating higher-quality videos that are smoother, more natural, richer in detail, and more consistent in terms of character movements, scene atmosphere, visual aesthetics, and physical motion.

HappyHorse-1.0-I2V

HappyHorse-1.0-I2V 是阿里巴巴 ATH 团队推出的 15B 参数统一多模态 Transformer 视频生成模型。支持图生视频（Image-to-Video），以图像为起点，精准保留原图内容，生成自然流畅的动态视频。具备高度还原的动态画面生成能力，能够精准理解文本语义，输出流畅自然、细节丰富的高质量视频。支持 720P/1080P 分辨率。

HappyHorse-1.0-R2V

HappyHorse-1.0-R2V 支持参考生视频，更加稳定的主体与场景参考，支持最多9张图片参考，能够精准保持创作意图，实现更强表现能力。

HappyHorse-1.0-T2V

Cinematic creative generation, ultimate dynamic details. 文生视频，精准理解语义，细节丰富画质流畅。支持1080p原生分辨率，同步音频，多镜头故事讲述，7种语言唇形同步。

HappyHorse-1.0-Video-Edit

HappyHorse-1.0 视频编辑模型，支持对已有视频进行风格变换、局部替换等二次创作。支持截取前15秒编辑，输出分辨率与输入一致，实现从1到N的创意延展。

Dreamina-Seedance-2.0-mini

Supports multimodal references, featuring video editing and extension capabilities

Seedance 2.5

字节跳动最新一代多模态视频生成模型，支持文本、图片、视频、音频等参考输入，强化角色一致性、复杂运镜、动作表现和长镜头生成，可用于高质量影视级视频创作。

Dreamina-Seedance-2.0

新一代专业级多模态视频创作模型，支持基于图像、视频和音频等多模态参考输入生成视频，同时具备视频编辑和扩展能力。

Dreamina-Seedance-2.0-fast

Seedance-2.0-fast is a new generation multimodal video creation model, inheriting the core features and advantages of Seedance-2.0 with faster speed. It supports generating videos from reference images/videos/audio, video editing, video extension, and first and last frame generation.