MiniMax H3
MiniMax's next-generation video model that generates coherent 2K videos from text, images, or multimodal references, with flexible 5-15 second durations and cinematic scene control.
MiniMax
WaveSpeedMiniMax H3
**MiniMax H3** is MiniMax's next-generation video generation model, delivering coherent 2K video output across three flexible generation modes: text-to-video, image-to-video, and reference-to-video. The model excels at cinematic scene generation, natural motion, and visual consistency—making it a strong choice for creative professionals, marketers, and production workflows. ### Generation Modes - **Text to Video**: Generates coherent 2K videos from text prompts, with flexible 5-15 second duration and adaptive or custom aspect ratios for cinematic scenes and creative videos. - **Image to Video**: Animates a first-frame image into a coherent 2K video, with natural-language motion instructions and optional last-frame control for consistent motion, scene continuity, and cinematic results. - **Reference to Video**: Generates videos from natural-language prompts combined with multimodal references, including images, videos, and audio, guiding subject consistency, motion, timing, visual style, and scene continuity. ### Key Capabilities - **2K resolution output** for crisp, production-ready results - **Flexible duration** from 5 to 15 seconds in one-second increments - **Multiple aspect ratios** including 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16 for any platform - **Multimodal reference support** for image, video, and audio conditioning - **First and last frame control** to precisely bookend animated sequences - **No cold starts** with a ready-to-use REST inference API and affordable pricing MiniMax H3 is best suited for filmmakers, content creators, and developers building applications that require high-fidelity video generation with fine-grained motion and visual control.
Ready to build with MiniMax H3?
Get Started FreeDocumentation & links
Parameters & options
First-frame image URL. Supported image dimensions are 256-5760 pixels per side, with an aspect ratio between 0.4 and 2.5.
Optional last-frame image URL.
Reference image URLs. At least one reference image or video is required.
Reference video URLs. At least one reference image or video is required.
Optional reference audio URLs. Audio cannot be provided alone.
Output video duration in seconds.
Explore similar models
MiniMaxHailuo 2.3 Pro
MiniMax Hailuo 2.3 Pro is a video generation model for ultra-clear 1080P output and physics-aware scenes with responsive rendering.
MiniMaxMinimax Speech 2.8 HD
MiniMax Speech 2.8 HD is a studio-quality text-to-speech model that delivers broadcast-ready, emotionally expressive audio rivaling professional voice actors.
MiniMaxMinimax Music 2.5
MiniMax Music 2.5 is an AI music generation model that delivers professional-grade, structurally precise songs with strikingly realistic sound — no recording studio required.
ByteDanceSeedance 2.0 Fast Turbo
Seedance 2.0 generates Hollywood-grade cinematic videos from text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability. Built on Seed's unified multimodal architecture, it leads on instruction adherence, motion quality, and visual aesthetics.
WanWan 2.7
Seedance 2.0 generates Hollywood-grade cinematic videos from text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability. Built on Seed's unified multimodal architecture, it leads on instruction adherence, motion quality, and visual aesthetics.
KlingKling 3.0 Pro
Kling
Start building with MiniMax H3
No API keys required. Create AI-powered workflows with MiniMax H3 in minutes — free.