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 2.5
Newest ByteDance video model with native audio and clips up to 30 seconds.
Wan 3.0
Alibaba's flagship video model with audio and clips up to 30 seconds.
Grok Imagine
xAI's fast video model with built-in sound: 4-15 second clips from text or one image.
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 4.0
Kling's newest video model with native audio, first/last-frame control, and clips up to 30s.
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 2.1
Google's newest Nano Banana with sharper text and steadier edits. Up to 4K and 10 references.
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 2.5
Newest OpenAI image model with sharper detail and consistent multi-turn edits.
GPT Image 2
Most capable OpenAI model. Supports up to 4K resolution.
Seedream 5.0 Pro
ByteDance image model for dense text, data-rich layouts, and precise edits.
Grok Imagine Image
xAI's image model for photoreal scenes and quick edits. One size tier, up to 5 references.
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.