MiniMax H3 · TEXT, FRAMES, AND REFERENCES

MiniMax H3 AI Video Generator

Create video with native stereo sound from a prompt, first and last frames, or a mixed set of image, video, and audio references.

30 free credits—enough for one 5-second 768P video. No card required.

MiniMax H3 · 10s · 768P

Rainy city tracking shot

A text-led street scene with a moving subject, camera tracking, reflections, and native rain ambience.

MiniMax H3 EXAMPLES

See the inputs behind every clip

Compare text, frame, and reference-led workflows with the prompt, settings, transcript, and honest notes shown for each result.

01

Text

Describe the scene, performance, camera, light, and motion.

02

Frames

Animate a start frame, with an optional end frame to guide the destination.

03

References

Direct identity, movement, rhythm, and sound with images, video, and audio.

MiniMax H3 EXAMPLES

Eight MiniMax H3 workflow examples

Each example includes the inputs, prompt, settings, transcript when applicable, and a short note about the observed result.

Text

Rainy city tracking shot

A text-led street scene with a moving subject, camera tracking, reflections, and native rain ambience.

View prompt and settings

Prompt: integrated_multimodal_description: A continuous cinematic 10-second rainy-night city scene. A fictional clearly adult East Asian woman in a tailored charcoal coat walks calmly beneath a transparent umbrella along an original unbranded metropolitan street. 0-3s: medium-wide establishing view with wet asphalt and cool cyan and warm amber reflections; the camera begins a smooth parallel track. 3-7s: track beside her at walking pace while rain beads on the umbrella and her coat moves naturally; preserve face, hands, wardrobe, and street geometry. 7-10s: ease into a closer three-quarter view as she briefly looks toward the reflected lights, then holds the final composition. Natural motion, stable anatomy, restrained depth of field, no cuts, no readable signs, no logos. overall_soundscape: Native stereo rain, soft footsteps on wet pavement, subtle umbrella patter, and distant original city traffic moving across the stereo field. non_diegetic_music: A sparse original low ambient pulse, quiet beneath the rain, with no recognizable melody.

Text

Astronomer with native dialogue

A cinematic observatory scene combining a speaking character, timed dialogue, room tone, and camera movement.

View prompt and settings

Prompt: integrated_multimodal_description: A continuous cinematic 10-second scene inside an original mountaintop observatory at blue hour. One fictional clearly adult white woman astronomer (S1), wearing practical navy workwear, stands beside a large unbranded telescope. 0-3s: slow dolly from the instrument toward S1 as the dome slit reveals a dense natural star field. 3-7s: S1 turns from the eyepiece toward camera and speaks with restrained wonder, accurate lip sync and natural facial motion: <d>[English] The oldest light is still arriving.</d> 7-10s: she looks back toward the sky while the camera settles; preserve identity, telescope geometry, and realistic hands. No cuts, no readable interface text, no logos. overall_soundscape: Native stereo observatory room tone, a quiet servo movement, faint mountain wind outside, and the clearly recorded voice of S1 centered in the mix. non_diegetic_music: One original low sustained synth chord that blooms gently after the dialogue.

Frames

Fashion image to motion

A first-frame workflow that carries the source styling into a directed fashion movement.

View prompt and settings

Prompt: Use the supplied first frame as the exact opening composition and identity anchor. integrated_multimodal_description: A continuous 10-second editorial fashion shot. The fictional clearly adult East Asian woman in the original emerald sculptural coat walks through the pale stone arcade. 0-3s: begin pixel-aligned to the supplied frame; fabric and hair first respond to a light breeze. 3-8s: the camera performs a slow controlled clockwise orbit while she takes two natural steps and turns her shoulders toward the new camera angle. 8-10s: settle into a stable full-body profile with the same face, emerald coat, black clothing, footwear, architecture, sunlight direction, and proportions. Natural hands and feet, continuous motion, no cuts, no logos, no new people. overall_soundscape: Stereo footsteps on stone, soft fabric movement, and a light open-air breeze. non_diegetic_music: Minimal original brushed percussion with two soft accents.

WHAT MiniMax H3 SUPPORTS

Simple inputs, production-ready controls

Native stereo audio

Generate speech, sound effects, ambience, and music with the video.

Multimodal direction

Use text, images, short videos, and audio together to communicate the shot.

Multiple aspect ratios

Choose a supported format for landscape, portrait, square, or cinematic delivery.

768p and up to 2K

Work at 768p or choose an available 2K output path for higher detail.

Free on signup

30 credits

Enough for one 5-second 768P MiniMax H3 generation.

No credit card required

Claim 30 free credits
Duration768p2K
5 seconds30 credits60 credits
10 seconds60 credits120 credits
15 seconds90 credits180 credits
Pricing

MiniMax H3 FAQ

Quick answers before you create

What can I make with 30 free credits?+

Thirty credits cover one 5-second MiniMax H3 video at 768p. Signing up does not require a credit card.

Does MiniMax H3 generate audio?+

Yes. MiniMax H3 can generate native stereo dialogue, ambience, sound effects, and music alongside the video.

Which inputs can I use?+

Start with text, add a first frame and optional last frame, or direct a reference workflow with images, video, and audio.

Can MiniMax H3 generate 2K video?+

MiniMax H3 supports an up-to-2K regeneration path. Minimax Motion offers 768p and 2K choices where supported by the selected workflow.

MiniMax H3 AI Video Generator | 30 Free Credits