MiniMax H3 Reference to Video

MiniMax H3 is a frontier video model. This endpoint generates 2K video from multimodal references up to 9 images for subject and style, 3 video clips for motion, and 3 audio clips each cited in the prompt by order, keeping subjects consistent while following the referenced motion and audio.

Inference$ Commercial useFrom 30 credits per run

About MiniMax H3 Reference to Video

stylizedtransformlipsync

Pricing

A run with the default settings costs 30 credits. The exact cost updates in the playground as you change settings, and you're only charged when you press Run. Failed runs are refunded automatically.

Inputs

prompttextarearequired

Text prompt for video generation. Refer to reference assets by their modality and order in the reference lists: Image 1, Image 2, Video 1, Audio 1, and so on.

durationintegerdefault: 5

The duration of the video in seconds.

resolutionselectdefault: "2K"

The resolution of the generated video. 480P and 768P are native generation modes; 2K and 4K upscale a 768P base result.

Options: 480P, 768P, 2K

seedinteger

Random seed. A random seed is selected when omitted.

enable_safety_checkerbooleandefault: true

If set to true, the safety checker will be enabled.

sync_modebooleandefault: false

Return the generated video as base64 instead of a CDN URL.

prompt_expansion_modetextareadefault: "balanced"

How much effort to spend rewriting the prompt before generation. 'disabled' skips prompt expansion. 'fast' returns in about a second. 'balanced' picks per request. 'quality' spends up to ~30s on a richer prompt.

aspect_ratioselectdefault: "adaptive"

The aspect ratio of the generated video.

Options: adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

reference_image_urlsfile-list

URLs of subject/style reference images, referenced in the prompt as Image 1, Image 2, and so on. Reference images, videos, and audio clips must add up to at most 12 files.

reference_video_urlsfile-list

URLs of motion/reference video clips (2-15 seconds each, combined duration at most 15 seconds), referenced in the prompt as Video 1, Video 2, and so on. Reference images, videos, and audio clips must add up to at most 12 files.

reference_audio_urlsfile-list

URLs of reference audio clips (2-15 seconds each, combined duration at most 15 seconds), referenced in the prompt as Audio 1, Audio 2, and so on. Images, videos, and audio can be provided individually or together. Reference images, videos, and audio clips must add up to at most 12 files.

target_audio_urlfile

Optional URL of an audio clip at least 2 seconds long (maximum 15 MB) to pin to the generated soundtrack. Cannot be combined with reference audio. Longer clips are trimmed to the generated video's length, keeping the beginning; shorter clips are padded with silence. The clip is resampled to 32 kHz stereo and replaces the output soundtrack without changing playback speed. Accepts an HTTP(S) URL or a base64 data URI.

More from MiniMax H3 Reference

MiniMax H3 Image to Video

MiniMax H3 is a frontier video model. This endpoint animates a supplied image into 2K video, using it as the opening frame or pairs a first and last frame to control a transition between two images with the aspect ratio following the input.

stylizedtransform

image-to-video

MiniMax H3 Text to Video

MiniMax H3 is a frontier video model. This endpoint generates video from a text prompt alone, rendering at 2K in durations from 5 to 15 seconds across seven aspect ratios.

stylizedtransform

text-to-video

Related image to video models

Kling Video v3 Image to Video [Pro]

Kling 3.0 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support.

image-to-video

H3 Max Image to Video

fal's H3 Max is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality

stylizedtransform

image-to-video

H3 Max Turbo Image to Video

fal's H3 Max Turbo is a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics while co-optimized with our custom inference stack for higher throughput with no compromises on output quality

stylizedtransform

image-to-video

Kling Video

Kling 2.5 Turbo Pro: Top-tier image-to-video generation with unparalleled motion fluidity, cinematic visuals, and exceptional prompt precision.

stylizedtransform

image-to-video

H3 Max Reference to Video

stylizedtransform

image-to-video

✦ new

Kling 4.0 Image to Video

Kling 4.0 animates a starting image into a 3 to 30-second video at 720p or 1080p, with optional ending frames and per-shot prompts.

multi-shotcinematic

image-to-video

✦ new

FLUX 3 Max Image to Video

fal’s FLUX 3 Max is a post-trained variant of FLUX 3 Video, tuned for stronger prompt adherence and better visual quality while optimized for lower latency.

fastaudio

image-to-video

Kling Video v3 Image to Video [Standard]

Kling 3.0 Standard: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation, with custom element support.

image-to-video

Seedance 2.5 US Reference to Video

US-hosted ByteDance Seedance 2.5 generates video with native audio from up to 30 images, 10 videos, and 10 audio references. Supports reference-guided generation, video editing, and extension at 480p, 720p or 1080p.

stylizedtransform

image-to-video

Wan 3.0

Wan 3.0 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

stylizedtransform

image-to-video

Kling Video v2.6 Image to Video

Kling 2.6 Pro: Top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation.

image-to-video

Kling AI Avatar v2 Standard

Kling AI Avatar v2 Standard: Endpoint for creating avatar videos with realistic humans, animals, cartoons, or stylized characters

image-to-video