Google Veo 3.1 Fast Video Generator
Veo 3.1 Fast is the faster tier of Google's Veo 3.1 video generation model
What is Veo 3.1 Fast?
Veo 3.1 Fast is the faster tier of Google's Veo 3.1 video generation model. On blubiu it produces one 8-second 720p clip per run, from a text prompt or from a first frame (with an optional last frame), and can generate sound with the picture. Each clip has a single fixed price.
Developer: Google · Checked 2026-11-02
What Veo 3.1 Fast is good at
- +Transitions between two known images: give a first and a last frame and describe the motion in between, as in first and last frame video.
- +Self-contained 8-second beats with sound, such as a product reveal or a short reaction shot.
- +Cheap drafts with sound: per second it is the lowest-priced video model on blubiu, as long as 8 seconds at 720p fits the shot.
- +Bringing one still to life: add a single image in image to video and it becomes the opening frame, so the prompt only has to describe the movement and the sound.
- +Short product moments: make the packshot first with AI product photography, then animate the reveal from that frame with sound.
When not to use it
- −You need a length other than 8 seconds or a resolution other than 720p. Seedance 2.0 runs 4–15 seconds at 480p–1080p. See Seedance 2.0 →
- −You need several reference images to hold a character's look. Veo 3.1 Fast takes a first/last frame only; Seedance 2.0 takes up to 9 references. See Seedance 2.0 →
- −The person in a photo should copy the moves from a real clip. This model invents motion from the prompt and frames; AI motion transfer takes it from footage. See Kling Motion Control →
Veo 3.1 Fast versions and specs
| Version | Inputs | Length | Resolution | Sound | Price |
|---|---|---|---|---|---|
| VEO 3.1 Fast | Text, First frame (+ optional last) | 8 s | 720P | Optional | 14 credits/clip; subscribers 40% off: 9 credits/clip |
Standard prices, read live from the platform catalog; once signed in, the Generate button shows your account's actual price. Failed generations are refunded.
How to prompt Veo 3.1 Fast
Write for exactly 8 seconds
The length is fixed, so describe a beat that fills 8 seconds — a start state, one change, an end state — rather than a whole scene.
Make the frames agree
When you pass both frames, keep the subject, lighting and camera height consistent between them; the model has to invent everything that differs.
Turn sound on and name it
Sound is optional and set by the Sound on / Muted switch in the generator. With it on, say what should be heard ("crowd murmur, one camera shutter, no music"); mute it when you will lay your own track.
Pick the ratio before the frames
On blubiu it renders 16:9, 9:16 or 1:1; 3:4 is sent as 9:16 and 4:3 as 16:9. Crop your first and last frames to the ratio you choose, or the edges of the picture may be lost.
Two images at most
In the generator, one image is used as the first frame and two as the first and last frame. A third image switches the input to reference mode, which this model doesn't support, so keep it to two.
Make both frames from one character
Generate the two frames from the same character image, for example two poses from the AI outfit changer. When the face and outfit already match, the model only has to invent the movement between them.
Veo 3.1 Fast FAQ
What is Veo 3.1 Fast?
It is the faster tier of Google's Veo 3.1 video model. On blubiu it makes 8-second 720p clips from text or a first/last frame, with optional sound, and you pay with blubiu credits rather than a Google account.
Can I choose a different length or resolution?
Not with this model on blubiu: every clip is 8 seconds at 720p. For 4–15 seconds or up to 1080p use Seedance 2.0; for 2K use MiniMax H3.
How is it priced?
A fixed number of credits per clip, shown in the table above and on the Generate button. Failed generations are refunded.
Can I try Veo 3.1 for free?
Yes, with the Free plan's monthly credits. Every clip costs the same fixed amount, which the Generate button shows before you confirm, and failed runs are refunded automatically. Plans and credit packs are on the pricing page.
Can the clip have sound?
Yes, it is optional. The Sound on / Muted switch in the generator decides; with sound on, describe what should be heard in the prompt, such as ambience, a voice line or an effect, and say "no music" if you don't want a score.
What aspect ratios does it support?
Landscape 16:9, vertical 9:16 and square 1:1 on blubiu. Other ratios are mapped: 3:4 is rendered as 9:16 and 4:3 as 16:9, so pick one of the three to get exactly what you see in your frames.
Can I use reference images?
No, only a first frame and an optional last frame. To hold a character's look with several references, use reference to video with Seedance 2.0 or Wan 3.0.
How do I get 1080p or 4K from a clip?
Upscale it after it is made. FlashVSR on the AI video upscaler lifts the 720p clip to 1080P, 2K or 4K and keeps the same motion, length and frame rate.
How do I make a video longer than 8 seconds?
Chain clips. Take the final frame of one clip in your editor and use it as the first frame of the next, keep the same subject and light in the prompt, then join the clips. For one continuous shot up to 15 seconds, use Seedance 2.0 instead.
Veo 3.1 or Seedance 2.0 for a short clip with sound?
Choose Veo when 8 seconds at 720p fits the shot and you want one fixed price per clip, from text or a first and last frame. Choose Seedance when you need another length, 1080p, or several reference images to keep a character on-model.
Tools that use Veo 3.1 Fast
Create Video with AI →
Create video with AI from a sentence, a first frame, first and last frames or up to 9 reference images: 1–15 second clips with Seedance, Veo, MiniMax and Wan.
AI Text to Video Generator →
Turn a written description into a 1–15 second video with Seedance, MiniMax H3, Veo and more — no images needed.
AI Image to Video Generator →
Upload an image as the first frame, describe the motion and generate a video with Seedance, Veo 3.1, MiniMax H3 Lite or Wan 3.0.
Pair Veo 3.1 Fast with
AI Product Photography Generator →
Make the product still first, then use it as the first frame for an 8-second reveal with sound.
AI Outfit Changer →
Get the same character in two poses or outfits and use them as the first and last frame of a transition.
GPT Image 2 & 2.5 Image Generator →
Draw the opening and closing frames at the ratio you will render, so nothing gets cropped.
AI Video Upscaler →
Lift a 720p clip you like to 1080P, 2K or 4K without generating it again.
Other video models
Make 4–15 second videos with sound from text, a first frame or up to 9 reference images with ByteDance's Seedance 2.0 — Mini, Fast and 2.0 compared.
Use MiniMax H3, the Hailuo video model, for 2K clips with reference images and videos, or H3 Lite for the cheapest silent drafts from 1 second.
Use Alibaba's Wan 3.0 for 2–15 second videos with sound from text, a first frame or reference images, or to replace the person in a video.
Run Kling Motion Control 2.6 online: a full-body photo copies the moves from a 3–30 second video, at 720P or 1080P. No Kling account needed; try it free.
Upscale an MP4 or MOV up to 120 seconds to 720P, 1080P, 2K or 4K with FlashVSR, a video super-resolution model. Billed per source second.
See image models →