October DealsAmazon USOctober deal check: compare before you payAmazon US: current deals, useful picks and tech finds.Check DealsSlow PC?RecommendedPC slow today? Run a repair scan before it gets worseResolve common Windows issues and optimize system performance.Scan NowOctober DealsAmazon USDeal season is back - check today's better picksAmazon US: current deals, useful picks and tech finds.See Picks×
Skip to content
ThatPainter
AI video

Google’s Veo 3.1 Update Adds More Expressive Ingredients to Video, Native 9:16, and 4K Output

Google’s Veo 3.1 update improves Ingredients to Video, adds native 9:16 output, and expands 1080p and 4K options—but access and limits vary by product and model.

By ThatPainter Team 8 min read
Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

What’s actually slowing this PC down?

Pick the symptom - the matching free tool is one click away.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

ThatPainter is reader-supported. When you buy through links on our site, we may earn an affiliate commission. Learn More

Google announced a Veo 3.1 update on January 13, 2026 that improves reference-image video generation, adds native 9:16 portrait output, and expands supported professional workflows to 1080p and 4K. The changes apply across Google products, but not uniformly: resolution, duration, model, pricing, and access depend on whether you use Gemini, YouTube Create, Flow, Google Vids, the Gemini API, or Vertex AI.

What Google changed in Veo 3.1

The update focuses on three practical improvements:

  • More expressive Ingredients to Video: prompts and reference images can guide richer dialogue, movement, storytelling, characters, objects, and environments.
  • Native vertical generation: Veo 3.1 can create video in a 9:16 portrait composition instead of generating landscape footage that must later be cropped.
  • Higher-resolution options: supported professional products expose 1080p and 4K output, although Google’s consumer announcement describes this as “upscaling” and availability is not universal.

Google presents expressiveness and consistency as product improvements, not as independently measured benchmark results. In practice, reference images provide stronger visual direction, but they do not guarantee perfect identity, hands, text, object geometry, lip synchronization, or continuity.

Free tools Windows power users keep installed

One-click scans. No signup required.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.
#1 Best Overall
Sale
ZYDIIE 4K Video Camera Camcorder UHD 64MP Vlogging Camera for YouTube 18x Digital Zoom 3" 270° Rotation IPS Touchscreen Video Camcorder with Night Vision, Remote Control, 32GB Card, 2 Batteries
  • 4K & 64MP Video Camera Camcorder: Capture life in breathtaking detail with 4K Ultra HD recording and vibrant 64MP photos, powered by an advanced high-sensitivity CMOS sensor. Equipped for exploring the beautiful world, this video camera is your perfect companion! Ideal for video recording, travel vlogs, family activities, interviews, studying, and cherishing precious moments
  • 18X Digital Zoom & Infrared Night Vision: This 4K camcorder powerful 18x digital zoom brings distant action right to you. Capture clear details of people and landscapes. With the push of “OK” button, activate the IR cut filter. This night vision camcorder delivers high-contrast black & white video in total darkness, providing a clearer image than standard low-light color mode
  • 3.0 Inches Touchscreen with 270° Rotation: This camcorder features a brilliant 3-inch touchscreen that puts complete control in your hands. The screen rotates a full 270 degrees, making it a game-changer for vloggers. Easily frame yourself for solo shots, capture high-angle overhead videos, or get creative low-angle perspectives
  • Webcam & Remote Control: Instantly transform your camcorder into webcam with a single USB cable. No complex drivers needed. Just connect and ready to go. Elevate your live streams and professional presentations with stunning 4K clarity. This video camera comes with a handy wireless remote to start/stop recording, and take photos without ever touching the device—ideal for solo creators, vloggers, and group shots
  • Multifunctional Camcorder: This 4K camcorder is loaded with pro features. Like face detection, video pause, slow motion, continuous shooting, time-lapse, self-timer, recording while charging, date stamp. Resulting in consistently smooth, sharp, and stunning footage in every scene. The two high-capacity batteries and 32GB micro SD card ensure that you won't miss a single beautiful moment in life

Read Google’s Veo 3.1 announcement for the launch description.

How Ingredients to Video works

Unlike text-to-video, which asks the model to invent the scene from a written description, Ingredients to Video combines a prompt with reference images. Those images act as visual ingredients for the clip.

  • Text-to-video: the prompt describes the complete visual concept.
  • Image-to-video: one image guides the generated video.
  • Ingredients to Video: multiple images help define subjects, objects, settings, or visual relationships.
  • Video extension: Veo continues a previously generated clip, subject to stricter resolution and duration limits.

The current Gemini API documentation supports up to three reference images for image-based direction. For example, one image could guide a character, another a product, and a third the environment. The prompt still needs to describe the action, camera movement, timing, lighting, dialogue, and interactions.

Reference images constrain appearance; they do not force an exact pose, wardrobe, camera angle, or object construction. A useful workflow is to keep reference images visually clear and complementary, then specify the intended relationship between them in the prompt.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

See the Gemini API video documentation for the current reference-image requirements and model controls.

What “more expressive” means

Google says Veo 3.1 produces richer dialogue, livelier movement, more dynamic storytelling, and improved consistency for characters and backgrounds. These claims describe the intended capability of the update rather than a published independent score.

For creators, the most important change is the combination of visual references and a detailed action prompt. A reference image may help preserve a character’s general appearance while the prompt controls what that character does. The result can still vary from generation to generation, particularly during complex interactions or fast motion.

Rank #2
Sale
MWIRB 8K Video Camera Camcorder Latest 88MP Ultra HD Video Cameras WiFi Vlogging Camera for YouTube 18X Digital Video Cameras with Microphone 6-Axis Anti-Shake IR Night Vision Video Recorder
  • Latest 8K Video Camera with Remote Control : This Video camera features 8K video resolution at 15FPS, with additional options for 6K at 30FPS, 5K at 30FPS, 4K at 30FPS, 1080P at 60FPS/30FPS, 720P at 60FPS/30FPS. With an impressive 88MP image resolution and 18X digital zoom, this camcorder delivers exceptional visuals. The included remote control allows for effortless self-recording and photography from any angle, making it an ideal 8K vlogging camera for bloggers and content creators.
  • Experience Smooth and Stable Footage with Our 8K Camcorder : Featuring advanced 6-Axis anti-shake technology for high-precision stabilization. The 3-inch, 270-degree rotatable touch screen allows for effortless self-recording and framing, making it perfect for vlogging and self-blogging. Additionally, the digital video camera's intuitive interface and user-friendly navigation ensure easy operation, so you can focus on capturing stunning 8K video and photos.
  • Infrared Night Vision Video Camera with WiFi : Stay connected and share your moments instantly with our 8K Camera's built-in Wi-Fi and companion app "iSmart DV2". Download the app on your Android/iOS device to easily transfer photos/videos, and share them directly to social media platforms like Facebook and YouTube. Additionally, this camera features infrared night vision, allowing you to capture footage in low-light environments, producing clear black and white images even in complete darkness.
  • Dual-Functionality and Enhanced Audio : This 8K video camera for YouTube doubles as a high-quality webcam, simply connect via USB and switch to "Webcam" mode for seamless video calling, live streaming, vlogging, and online teaching. The included external X-Y stereo microphone reduces ambient noise and captures clear, stable audio, ensuring professional-grade sound quality for your recordings.
  • Versatile camcorders video camera 8k for Every Adventure: This multifunctional camera features a range of creative modes, including continuous shooting, time-lapse, slow motion, and recording while charging. Perfect for capturing life's adventures, whether you're traveling, camping, hiking, or enjoying your favorite sports. Plus, our dedicated team is available to provide technical support, troubleshooting, and answers to any questions you may have after your purchase.

High resolution does not solve temporal or semantic problems. A 4K clip may still contain jerky motion, identity drift, garbled on-screen text, implausible hand interactions, inconsistent lighting, or audio and lip-sync errors. Treat the output as generated footage that requires editorial review, not as a finished production asset.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

Native 9:16 portrait video

Veo 3.1 adds native 9:16 generation for Ingredients to Video. This is important for YouTube Shorts, TikTok-style content, Instagram Reels, mobile advertising, portrait product demonstrations, and character-led social clips.

Native portrait generation gives the model a vertical canvas from the beginning. That is preferable to cropping a landscape result because cropping can remove faces, products, action, or important background context. It does not, however, guarantee good composition. Subjects can still be placed too close to an edge, captions can fall outside safe areas, and action may be framed poorly.

Prompts for vertical video should specify subject placement and camera distance. For example, request a “medium portrait shot with the subject centered in the upper two-thirds and clear empty space below for captions” when a social edit needs a text-safe area.

The current API documentation lists both 16:9 and 9:16 for Veo 3.1 and Veo 3.1 Fast.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

Does Veo 3.1 really generate 4K?

The answer depends on the wording and the product.

Google’s January announcement calls the feature “upscaling to 1080p and 4K.” The current Gemini API documentation, meanwhile, lists 720p, 1080p, and 4k as selectable output resolutions for supported Veo 3.1 modes. The safest conclusion is that the API exposes 4K as a direct output setting, but readers should not assume that every Veo interface creates native-capture-level 4K detail.

A larger 4K file can improve delivery resolution and apparent sharpness. Upscaling cannot reliably recreate every fine detail that was absent from the generated image sequence. It also cannot correct bad motion, incorrect physics, or inconsistent faces.

Rank #3
Sale
Aidzhi 4K Video Camera Camcorder 96MP UHD Vlogging Camera for YouTube 18X Digital Zoom 3.0 IPS 270° Rotation Touch Screen Video Recorder with Remote Control, Night Vision, 32GB Card, 2 Batteries
  • 4K & 96MP Video Camera Camcorder: This 4K video camera is capable of capturing precious moments with 4K Ultra HD video and 96MP still photos. Equipped with a high-sensitivity CMOS sensor, this camcorder ensures vivid colour reproduction and crisp, sharp image detail. Suitable for a wide range of scenarios—from capturing travel scenery and family gatherings to everyday snapshots—this vlogging camera meets all your filming needs.
  • 18X Digital Zoom & Infrared Night Vision: This 4K camcorder features 18X digital zoom, allowing you to easily zoom in on distant scenes and capture clear details from afar. Activate the IR cut filter with one click via the OK button. This 4K video camcorder’s professional infrared night vision mode allows it to record high-contrast black-and-white footage even in pitch-black conditions.
  • 3.0 Inch Touchscreen & 270° Rotatable Design: This 4K camcorder is equipped with a 3.0-inch HD touchscreen, delivering sensitive response and intuitive operation for effortless setting adjustment. Featured with a 270° flip screen, this vlogging camcorder allows real-time scene preview anytime you record. Perfect for vlogging, selfie shooting and video blogging, it supports portrait close-up, high-angle overhead recording and low-angle creative framing.
  • Webcam Function & Wireless Remote Control: This video camera camcorder can be used as a computer webcam by simply connecting with USB cable, no complicated driver installation required. This digital video camera supports 4K clear image quality for live streaming, online meetings and video calls. Equipped with wireless remote control, you can start or stop recording and take photos remotely, great for solo shooting, vlog creation and group photo taking.
  • Multifunctional Camcorder with Full Accessories: Packed with practical professional functions: face detection, video pause, slow motion, time-lapse shooting, self-timer, recording while charging and date stamp. This 4K video recorder camera produces smooth, sharp and cinematic footage in various scenes. It comes with a full set of supporting accessories out of the box, including 2 rechargeable batteries and a 32G memory card, ready for you to start shooting right away.

In the API, 1080p and 4K require an 8-second duration. Video extension is limited to 720p. Veo 3.1 Lite supports 720p and 1080p but not 4K.

Where the update is available

Google names the Gemini app, YouTube, YouTube Create, Flow, the Gemini API, Vertex AI, and Google Vids as destinations for the broader Veo 3.1 rollout. They do not expose identical features.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

Gemini, YouTube Shorts, and YouTube Create

Google said enhanced Ingredients to Video and portrait mode were available in the Gemini app, while Ingredients to Video was also coming to YouTube Shorts and YouTube Create. YouTube’s announcement describes vertical clips generated from up to three supplied images.

Consumer access can vary by country, language, account, plan, rollout status, and product interface. Availability in a consumer app should not be interpreted as unlimited use or API access.

Details are available in the YouTube support announcement.

Flow

Flow is the better fit for creators and filmmakers who prefer a visual, story-oriented interface over code. It is useful for visual iteration, but readers should check the live product page for current plan access and pricing rather than assume that every Veo 3.1 capability is included in every plan.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

Google Vids

Google Vids adds portrait-sized Ingredients to Video clips for Workspace-oriented business-video and presentation workflows. Rollout began January 13, 2026, but eligibility depends on Workspace edition, account, and rollout status. Vids is designed for collaborative document and presentation workflows, not high-volume automated generation.

Rank #4
Sale
Canon VIXIA HF G70 Camcorder 1/2.3" 4K UHD CMOS Sensor 20x Optical Zoom, 800x Digital, Image Stabilization, HDMI, USB Live Streaming, Time Stamp On-Screen Display Recording
  • 4K sensor and DIGIC DV6 image processor deliver crisp, sharp 4K UHD images, while an 8-blade aperture achieves cinema-style out-of-focus highlights.
  • On-Screen Display (OSD) “Time Stamp” Recording embeds date, time, timecode and other data in your original camera files.
  • UVC Livestreaming - Stream HD video directly from the camera via UVC1 to a PC or Mac computer.
  • Powerful 20x optical zoom and advanced image stabilization.
  • Adjustable focusing speeds and advanced Hybrid AF system provide fast and precise focusing with face detection.

See the Google Workspace update for the rollout notice.

Gemini API and Vertex AI

The Gemini API is suited to developers, agencies, and automation builders who need explicit controls and usage-based billing. Vertex AI is better suited to organizations that need Google Cloud projects, IAM, governance, quotas, enterprise billing, and integration with existing Cloud systems.

Google’s announcement specifically limits the 1080p and 4K options to Flow, the Gemini API, and Vertex AI rather than promising those resolutions across every listed product.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

Current Gemini API specifications

Capability Veo 3.1 and Veo 3.1 Fast Veo 3.1 Lite
Model examples veo-3.1-generate-preview, veo-3.1-fast-generate-preview Lite model family
Aspect ratios 16:9 and 9:16 Check current model documentation
Duration 4, 6, or 8 seconds; reference images and 1080p/4K require 8 seconds Mode-dependent
Resolution 720p, 1080p, and 4K where supported 720p and 1080p; no 4K
Audio Generated natively with video Generated with supported audio mode
Extension Limited to 720p Check current documentation
Frame rate 24 fps Check current documentation

Veo 3.1 and Veo 3.1 Fast are listed as preview models in the Gemini API documentation. Preview behavior, limits, availability, and model identifiers can change, so production applications should monitor release notes, pin compatible versions where possible, and run regression tests.

Illustrative portrait 4K request

The important controls for an API request are an 8-second duration, a 9:16 aspect ratio, a 4K resolution, and a Veo 3.1 model that supports reference images. A compact Python flow looks like this:

import time
from google import genai
from google.genai import types

client = genai.Client()

operation = client.models.generate_videos(
    model="veo-3.1-generate-preview",
    prompt=(
        "A cinematic vertical product video. The person in the first reference "
        "image holds the object from the second reference image in the setting "
        "shown in the third image. Natural movement, clear dialogue, soft studio lighting."
    ),
    config=types.GenerateVideosConfig(
        aspect_ratio="9:16",
        resolution="4k",
        duration_seconds=8,
        reference_images=[
            # Add reference-image objects using the current SDK documentation.
        ],
    ),
)

while not operation.done:
    time.sleep(10)
    operation = client.operations.get(operation)

video = operation.response.generated_videos[0]

This is an asynchronous operation and produces one video per request. Copy the exact reference-image object construction from the current official SDK documentation; SDK syntax and model identifiers may change.

Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Support on Ko-Fi

API pricing and the cost of iteration

Current Gemini API list prices for video with audio are:

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.
Best Value
Sale
DJI Osmo Pocket 3 Creator Combo, Vlogging Camera with 1'' CMOS & 4K/120fps
  • Capture Stunning Footage - Osmo Pocket 3 vlogging camera features a 1-inch CMOS sensor and records in 4K resolution at an impressive 120fps. Capture breathtaking night views and sunsets with enhanced clarity.
  • Effortlessly Frame Your Shots - Get the ideal composition with Osmo Pocket 3's expansive 2-inch touch screen that rotates for both horizontal and vertical shooting.
  • Ultra-Steady Footage - Say goodbye to shaky videos! Osmo Pocket 3's advanced 3-axis mechanical stabilization delivers superb stability. Enjoy smooth footage while dancing, chasing pets, or hiking.
  • Create Captivating Vlogs With ActiveTrack 6.0 - Stay effortlessly in focus as you record on the go. Set Osmo Pocket 3 up on a tripod and jump, dance, or spin, but remain center-frame.
  • Fast and Accurate Focusing - Osmo Pocket 3 digital camera locks onto your subject for sharp, clear footage. Whether filming action-packed scenes or still shots, it ensures every detail is captured.
Model 720p 1080p 4K
Veo 3.1 Standard $0.40/sec $0.40/sec $0.60/sec
Veo 3.1 Fast $0.10/sec $0.12/sec $0.30/sec
Veo 3.1 Lite $0.05/sec $0.08/sec Not supported

That makes an 8-second clip approximately $3.20 on Standard at 720p or 1080p, $4.80 on Standard at 4K, $0.96 on Fast at 1080p, $2.40 on Fast at 4K, and $0.64 on Lite at 1080p. These figures exclude other application or Google Cloud costs and assume successful generation.

A sensible production workflow is to create drafts at 720p or 1080p, select the strongest take, then render the final version at 4K only when the delivery target requires it. Google’s documentation warns that higher resolution increases latency and cost.

Check the Gemini API pricing page before budgeting. Vertex AI pricing and Cloud billing should be checked separately on Google Cloud’s generative-AI pricing page.

Limitations creators and developers should expect

  • Portrait composition: native 9:16 avoids a landscape crop but does not guarantee safe placement for faces, products, action, or captions.
  • Reference-image consistency: references can improve visual control without guaranteeing exact identity, clothing, geometry, or continuity.
  • Duration and resolution: API reference-image, 1080p, and 4K workflows currently require 8 seconds; extension supports only 720p.
  • Audio: Veo 3.1 generates audio with the video, but dialogue, pronunciation, sound effects, and synchronization require review. Audio-processing failures can prevent generation; the pricing documentation says charges apply only when generation succeeds.
  • People generation: settings and restrictions vary by generation mode, region, and policy. Requests involving people or supplied images may be blocked or limited.
  • Preview volatility: preview models can change behavior, limits, or availability. Production users need monitoring and regression testing.
  • Rights and consent: supplying a person’s likeness, branded object, artwork, or location requires appropriate permission and review before commercial publication.

Which Google product should you choose?

  • Gemini app or YouTube Create: best for quick experiments and short-form social content without API automation.
  • Flow: best for visual, filmmaking-oriented iteration and creators who do not need programmatic control.
  • Gemini API: best for developers and agencies that need automation, explicit settings, and per-second cost calculations.
  • Vertex AI: best for enterprise teams needing Cloud governance, IAM, quotas, billing, and system integration.
  • Google Vids: best for Workspace teams placing generated clips inside collaborative presentations and business-video projects.

No option removes the need for editing, captioning, continuity checks, audio cleanup, safety review, or platform-specific export. A subscription or API account also does not guarantee successful generations or publication-ready footage.

What’s actually slowing this PC down?

Pick the symptom - the matching free tool is one click away.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

Bottom line

Veo 3.1 is a meaningful workflow update rather than a universal 4K switch. Its strongest practical benefits are better reference-image direction, native portrait composition, and higher-resolution options in selected products. For social creators, 9:16 generation is the clearest immediate advantage. For developers and production teams, the important details are the 8-second requirement, model differences, preview status, asynchronous API behavior, and the cost of repeated attempts.

Use lower resolution while iterating, reserve 4K for approved takes, and verify the exact product, plan, region, model, and current documentation before promising a capability to a client.

Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.

More from the Paint Desk

Recommended PC Tool
Recommended PC Tool
PC Slower Than It Used to Be?Free scan - under a minute
Crashes, No Sound, or Screen Glitches?Free driver scan

Two free Windows tools

One Free Minute Could Fix That PC

Before you go - each of these free tools takes about a minute and tackles what quietly slows a Windows PC down.

Special offer. View Outbyte info, uninstall instructions, EULA, and Privacy Policy.