Nano Banana Pro
  • Home
  • Assets
  • Pricing
Models
Nano Banana 2.1Nano Banana 2Nano Banana 2 LiteNano Banana ProSeedream 5.5Seedream 5.0 LiteSeedream 5.0 ProSeedream 5.0 FlashGPT Image 2.6 FlareGPT Image 2.6 SunburstGPT Image 2.5 FlareGPT Image 2.5 SunburstGPT Image 2Grok Imagine Image 2.0Z-ImageGemini Omni 1.2 FlashGemini Omni 1.1 FlashGemini OmniMiniMax H3MiniMax H3 MaxMiniMax H3 Max TurboSeedance 2Seedance 2.5Seedance 2 FastSeedance 2 MiniWan 3.0 VideoWan 3.0 Video PrimeKling 3.0Kling 3.0 OmniKling 4.0Kling 4.0 FlashPixVerse V6PixVerse V6 MaxGrok Imagine Video 1.5 PreviewGrok Imagine Video 1.5 LiteVidu Q4
Nano Banana ProNano Banana Pro
Generation mode
Model
0 / 7000
Aspect ratio
Resolution
Duration5s
5s7s9s11s13s15s

MiniMax H3 Max

Create 5–15-second 480p or 768p videos from text, first and last frames, or multimodal reference media. MiniMax H3 Max supports a dedicated reference-to-video workflow using images, video and audio.

MiniMax H3 Max
How it works

Create with MiniMax H3 Max

MiniMax H3 Max is a video generation model in the H3 family. It supports text-to-video, image-to-video using a first frame, a last frame or both, and multimodal reference-to-video. The current EvoLink routes support 480p or 768p MP4 output, with durations from 5 to 15 seconds. Reference mode accepts images, videos and audio, which can help guide a shot’s visual identity, motion or timing beyond what a text prompt alone can specify.

01

Describe the shot

Prompt tips: Keep each clip to one clear action. For image-to-video, use a first frame and, if needed, a last frame to define the shot's start and end.

02

Add references

Generation mode: Text-to-Video / Image-to-Video / Reference-to-Video / Video-to-Video. Reference image: 9. Video references are supported. Audio references are supported. Only use source material you can process, and say what each reference should guide. A reference cannot guarantee identical details.

03

Generate and refine

Duration: 5s / 6s / 7s / 8s / 9s / 10s / 11s / 12s / 13s / 14s / 15s. Resolution: 768p / 480p. Aspect ratio: adaptive / 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16. Check the controls for the active generation mode before submitting. Watch the entire clip for continuity, unintended objects, timing and audio where available before using it.

Generation mode

Text-to-Video / Image-to-Video / Reference-to-Video / Video-to-Video

Duration

5s / 6s / 7s / 8s / 9s / 10s / 11s / 12s / 13s / 14s / 15s

Resolution

768p / 480p

Aspect ratio

adaptive / 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16

Reference image

9 · JPEG / PNG / WebP / image/heic / image/heif · 30 MB

Reference video URL

MP4 / MOV · 50 MB

Reference audio

WAV / MP3 · 15 MB

Prompt (max)

7000

About

What is MiniMax H3 Max?

MiniMax H3 Max is a video generation model in the H3 family. It supports text-to-video, image-to-video using a first frame, a last frame or both, and multimodal reference-to-video. The current EvoLink routes support 480p or 768p MP4 output, with durations from 5 to 15 seconds. Reference mode accepts images, videos and audio, which can help guide a shot’s visual identity, motion or timing beyond what a text prompt alone can specify.

What is MiniMax H3 Max?

MiniMax H3 Max features

Choose text, keyframes or multimodal references depending on how much control your shot needs.

Text to video

Generate a 5–15-second clip from a prompt, with 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16 framing.

Generate a 5–15-second clip from a prompt, with 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16 framing.

First- and last-frame control

Animate from a first frame, a last frame or both to define the visual start and finish.

Animate from a first frame, a last frame or both to define the visual start and finish.

Multimodal reference-to-video

Use up to 9 images, 3 videos and 3 audio clips, with a maximum of 12 reference assets per request.

Use up to 9 images, 3 videos and 3 audio clips, with a maximum of 12 reference assets per request.

480p and 768p output

Choose 480p for lower-cost exploration or 768p for a cleaner result to review.

Choose 480p for lower-cost exploration or 768p for a cleaner result to review.

What you can make with MiniMax H3 Max

Suitable for quick ad iterations, e-commerce product movement, first- and last-frame shots, and video guided by multimodal references.

MiniMax H3 Max is a video generation model in the H3 family. It supports text-to-video, image-to-video using a first frame, a last frame or both, and multimodal reference-to-video. The current EvoLink routes support 480p or 768p MP4 output, with durations from 5 to 15 seconds. Reference mode accepts images, videos and audio, which can help guide a shot’s visual identity, motion or timing beyond what a text prompt alone can specify. Ad concepts,E-commerce videos,Reference-led clips,Storyboard iterations Start with one subject, one action and a clear camera direction. Compare the result with your brief; generated motion can vary.

Describe the shot

Prompt tips: Keep each clip to one clear action. For image-to-video, use a first frame and, if needed, a last frame to define the shot's start and end.

Prompt tips: Keep each clip to one clear action. For image-to-video, use a first frame and, if needed, a last frame to define the shot's start and end. Start with one subject, one action and a clear camera direction. Compare the result with your brief; generated motion can vary.

Add references

Generation mode: Text-to-Video / Image-to-Video / Reference-to-Video / Video-to-Video.

Generation mode: Text-to-Video / Image-to-Video / Reference-to-Video / Video-to-Video. Reference image: 9. Video references are supported. Audio references are supported. JPEG / PNG / WebP / image/heic / image/heif · 30 MB. MP4 / MOV · 50 MB. WAV / MP3 · 15 MB. Only use source material you can process, and say what each reference should guide. A reference cannot guarantee identical details.

Generate and refine

Duration: 5s / 6s / 7s / 8s / 9s / 10s / 11s / 12s / 13s / 14s / 15s. Resolution: 768p / 480p. Aspect ratio: adaptive / 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16.

Duration: 5s / 6s / 7s / 8s / 9s / 10s / 11s / 12s / 13s / 14s / 15s. Resolution: 768p / 480p. Aspect ratio: adaptive / 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16. Check the controls for the active generation mode before submitting. Output quality can affect the credit estimate. Confirm the displayed total before generating.

One look held across every shot

Ad concepts,E-commerce videos,Reference-led clips,Storyboard iterations

Suitable for quick ad iterations, e-commerce product movement, first- and last-frame shots, and video guided by multimodal references. Ad concepts,E-commerce videos,Reference-led clips,Storyboard iterations Choose the framing for your destination and check how uploaded images are cropped.

It hits the beats in the order you write them

Watch the entire clip for continuity, unintended objects, timing and audio where available before using it.

Watch the entire clip for continuity, unintended objects, timing and audio where available before using it. Start with one subject, one action and a clear camera direction. Compare the result with your brief; generated motion can vary. Check the controls for the active generation mode before submitting.

Examples & use cases

What you can make with MiniMax H3 Max

Suitable for quick ad iterations, e-commerce product movement, first- and last-frame shots, and video guided by multimodal references.

01

View example prompt 1

Ad concepts

Suitable for quick ad iterations, e-commerce product movement, first- and last-frame shots, and video guided by multimodal references.

View example prompt

A high-end sneaker rotates slowly on a clean studio platform as soft daylight reveals the fabric texture.

02

View example prompt 2

E-commerce videos

Prompt tips: Keep each clip to one clear action. For image-to-video, use a first frame and, if needed, a last frame to define the shot's start and end.

View example prompt

Animate the opening frame with a smooth camera push, ending naturally on the supplied final frame.

03

View example prompt 3

Reference-led clips

Ad concepts,E-commerce videos,Reference-led clips,Storyboard iterations

View example prompt

A precise shot brief with ordered actions, camera direction, timing, lighting, and output constraints.

FAQ

MiniMax H3 Max FAQ

MiniMax H3 Max FAQ

MiniMax H3 Max is an H3-family AI video model for text-to-video, first- or last-frame image-to-video, and multimodal reference-to-video generation.

Reference mode supports up to 9 images, 3 videos and 3 audio clips, with a maximum of 12 assets in total. You must include at least one reference image or video; audio alone is not accepted.

The current routes support 480p and 768p MP4 output, with integer durations from 5 to 15 seconds.

H3 Max adds multimodal reference-to-video generation with image, video and audio inputs. H3 Max Turbo is the faster, lower-cost tier for text-to-video and first-frame image-to-video workflows.

The generator displays the current estimated cost before you submit. The cost depends on resolution and duration. Reference mode may also add charges based on reference-video length and the number of reference images.

Generation mode: Text-to-Video / Image-to-Video / Reference-to-Video / Video-to-Video. Suitable for quick ad iterations, e-commerce product movement, first- and last-frame shots, and video guided by multimodal references.

Prompt tips: Keep each clip to one clear action. For image-to-video, use a first frame and, if needed, a last frame to define the shot's start and end. Start with one subject, one action and a clear camera direction. Compare the result with your brief; generated motion can vary.

Duration: 5s / 6s / 7s / 8s / 9s / 10s / 11s / 12s / 13s / 14s / 15s. Check the controls for the active generation mode before submitting.

Resolution: 768p / 480p. Check the controls for the active generation mode before submitting. Output quality can affect the credit estimate. Confirm the displayed total before generating.

Aspect ratio: adaptive / 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16. Check the controls for the active generation mode before submitting. Choose the framing for your destination and check how uploaded images are cropped.

Generation mode: Text-to-Video / Image-to-Video / Reference-to-Video / Video-to-Video. Reference image: 9. Video references are supported. Audio references are supported. JPEG, PNG, WebP, image/heic, image/heif · 30 MB. MP4, MOV · 50 MB. WAV, MP3 · 15 MB. Only use source material you can process, and say what each reference should guide. A reference cannot guarantee identical details. Watch the entire clip for continuity, unintended objects, timing and audio where available before using it.

Explore more AI video models

MiniMax H3 Max Turbo

MiniMax H3 Max Turbo

New

MiniMax H3 Max Turbo is the lower-cost speed tier for 480p and 768p text-to-video and first-frame image-to-video, with an optional last frame.

Try now
MiniMax H3

MiniMax H3

New

MiniMax H3 is a multimodal video model for text-to-video, image-to-video and reference-to-video. It offers 768p and 2K output, flexible duration options and reference audio.

Try now
Veo 3.1 Quality

Veo 3.1 Quality

New

Veo 3.1 offers Lite, Fast and Quality variants where available. Choose text-to-video, image-to-video or video-to-video in supported modes; reference-to-video supports up to 3 images and requires Fast at 16:9. Available aspect options are Auto, 16:9 and 9:16. The interface has no duration or resolution selector. Check the displayed credit cost before generating.

Try now
Wan 2.6

Wan 2.6

New

Wan 2.6 supports text-to-video, image-to-video and video-to-video. It offers 5-, 10- and 15-second duration options, 720p and 1080p resolutions, and multi-shot generation.

Try now
Sora 2

Sora 2

The standard Sora model. It is designed for efficient video generation and can be used for storyboards, social clips and creative iterations.

Try now
Vidu Q4

Vidu Q4

New

Animate one first-frame image or use up to 15 reference images. Choose 540p–4K and a duration of 3–16 seconds for image animation or 1–16 seconds for references. Synchronized audio is optional. Reference audio must be MP3 and 3–12 seconds long.

Try now

Create a video with MiniMax H3 Max

Start with text, keyframes or multimodal references, then generate in your browser.
Create with MiniMax H3 Max
Nano Banana Pro
Nano Banana ProNano Banana Pro

Nano Banana Pro gives you access to advanced AI image models for creating professional-quality images.

Email
FAQShowcasesChangelogAPIManga ColorizerCyberpunk
العربيةDeutschEnglishEspañolFrançais繁體中文日本語한국어Bahasa MelayuTürkçeไทยTiếng ViệtPortuguês (Brasil)中文עבריתPolski
© 2026 Nano Banana Pro· All rights reserved
Privacy PolicyTerms of ServiceRefund PolicyRefund RequestAbout Us
HomeNEWToolsAssetsProfile

Image

JPG, JPEG, PNG, WEBP, HEIC, HEIF · 30MB

Drop an image or click to upload.