Create stunning 2K AI videos from text, images, first/last frames, and reference images, videos or audio. Flexible 4-15 second clips with adaptive aspect ratio.
Generate a 2K video purely from a text prompt.
Describe the scene, motion, and style you want in the video
4-15 seconds
MiniMax H3 always outputs 2K quality video.
This parameter defines the aspect ratio of the video.
Ready to Create Your MiniMax H3 Video
MiniMax H3 is a next-generation multimodal AI video generation model that turns text, images, first/last frame pairs, and reference assets (images, videos, audio) into polished 4-15 second clips at 2K resolution. One model covers text-to-video, image-to-video, frame interpolation, and reference-guided generation.
With adaptive aspect ratio for image-guided workflows and cinematic ratios (16:9, 9:16, 1:1, 4:3, 3:4, 21:9) for text-to-video, MiniMax H3 is ideal for product shots, character motion, stylized scenes, and fast creative iteration at transparent per-second pricing.
Start from a text prompt, animate a single image, guide motion with first and last frames, or attach reference images, videos and audio. H3 adapts to the assets you already have.
Every clip renders at 2K resolution with sharp detail and smooth motion, ready for professional use on any platform without upscaling.
Dial in the exact clip length you need, from quick 4-second loops to fuller 15-second scenes. Per-second pricing keeps short tests affordable.
Define exactly how your video starts and ends. H3 interpolates the motion between two frames for precise, storyboard-like transitions.
Attach up to 9 images, 3 videos and 3 audios as reference material. Guide subjects, style and even sound for consistent, on-brand results.
Choose 16:9, 9:16, 1:1, 4:3, 3:4 or 21:9 for text-to-video. Image and reference modes automatically use adaptive ratio so your source framing stays intact.
Pick Text-to-Video, Image-to-Video, First & Last Frame, or Reference Assets mode based on your starting point.
Write a prompt, upload an image or first/last frames, or attach reference images, videos and audio.
Choose 4-15s duration and an aspect ratio for text mode. Output is always crisp 2K.
Click Generate and wait for processing. Preview the result and download your MiniMax H3 video when ready.
MiniMax H3 generates 4-15 second 2K videos from text prompts, single images, first/last frame pairs, or multimodal reference assets including images, videos and audio.
H3 generates 2K videos with any whole-second duration from 4 to 15 seconds. Text-to-video supports 16:9, 9:16, 1:1, 4:3, 3:4 and 21:9; image and reference modes use adaptive ratio.
Pricing is per second of output video: 30 gems/s at 2K. A 5s clip costs 150 gems; the cost display updates before you generate.
You can attach up to 9 reference images, 3 reference videos and 3 reference audios, with 12 assets in total. Reference audio must be combined with at least one image or video.
Upload a first frame and a last frame image, and MiniMax H3 generates a smooth transition video between them. Aspect ratio adapts automatically to your source images.
Generation time varies by duration and mode, but most 2K clips are ready within 2-5 minutes. Longer videos and reference-heavy inputs take more time.
