MiniMax H3 与 AI 模型
以 Hailuo 3.0 为创作工作流核心
使用 MiniMax H3 进行文生视频或图生视频创作，支持同步音频和最长 15 秒片段。项目需要其他图像或视频能力时，可选择辅助模型。
视频模型
MiniMax H3
MiniMax H3 (Hailuo 3.0) for text-to-video and image-to-video with synchronized audio and clips up to 15 seconds.
Seedance 2.0
ByteDance video generation model for text-to-video and image-to-video.
Seedance 2.0 Fast
Faster ByteDance video model for rapid text-to-video and image-to-video iteration.
Kling 3.0
Kling video model with native audio, first/last-frame image-to-video, and up to 15s duration.
Veo 3.1
Google's flagship video model with native audio for text-to-video and image-to-video.
Veo 3.1 Fast
Faster, cheaper Google Veo model with native audio for rapid iteration.
辅助图像模型
Nano Banana 2
Next-gen with reasoning-guided generation. Supports up to 4K resolution.
Nano Banana Pro
Highest quality Google model. Supports up to 4K resolution.
GPT Image 2
Most capable OpenAI model. Supports up to 4K resolution.
Flux 2 Pro
Photorealistic Black Forest Labs model with strong multi-reference consistency.
Flux 2 Flex
Higher-control Flux 2 tier for precise typography, composition, and details.