Vidu Q1, Q2 and Q3 on VdoBloom: Which Model, and How to Use It

VdoBloom runs three main Vidu models — Q1, Q2 Pro and Q3 — and they sit at different points on one trade-off. Q1 is the simplest and cheapest: every clip is a fixed 5 seconds at 1080p for a flat 25 credits. Q2 Pro is the cinema-quality finisher, with 4, 5 or 8 seconds up to 100 credits. Q3 reaches 16 seconds and generates audio together with the picture, from 40 credits. Pick by duration, audio and how much control you want.

Updated October 2026.

What the Vidu line is

Vidu is Shengshu Technology’s proprietary, hosted video generation family — there is no open-weights release, and it runs through VdoBloom’s dashboard rather than as a downloadable model. The three main tiers here are Vidu Q1, Vidu Q2 Pro and Vidu Q3, with a fast Turbo sibling beside two of them. Every model in the family accepts a text prompt or a starting image, frames at 16:9, 9:16 or 1:1, tops out at 1080p, and carries a MODERATE content filter — VdoBloom’s standard tier, not the strictest. Each also holds a 3.9 catalog rating. Where they differ is duration, audio and price, and that is what decides which one to open.

Vidu Q1: fixed 5 seconds, 1080p, flat 25 credits

Q1 strips the settings menu down to almost nothing. Every generation is 5 seconds and every generation is 1080p; the only choices left are your prompt or reference image and a frame shape of 16:9, 9:16 or 1:1. Because duration and resolution never change, there is nothing else to price by, so Q1 is a flat 25 credits per generation whether you start from text or an image. It also supports two style presets, general and anime — unique among the Vidu models covered here.

What it is good at: single-shot b-roll at a consistent length for direct assembly in an editor, prompt-wording experiments where a fixed format keeps every attempt comparable, and anime clips that use the built-in preset instead of describing style in prose. What it gives up is choice — no 720p option, no 4- or 8-second durations. New accounts start with 10 free credits, which covers less than half of a single 25-credit render.

Vidu Q2 Pro: 4, 5 or 8 seconds, cinema-quality finishing tier

Q2 Pro is the render you export, not the one you experiment with. It prioritizes motion coherence and image fidelity over speed, works from a text prompt or a source image, and outputs 4, 5 or 8 seconds at 720p or 1080p in 16:9, 9:16 or 1:1. It adds movement-amplitude and background-music controls that Q1 does not have. It does not generate its own audio, though — a silent soundtrack has to come from somewhere else.

Pricing runs from 30 credits (4s/720p) to 100 credits (8s/1080p): 30, 40 and 65 credits at 720p for 4, 5 and 8 seconds, and 45, 60 and 100 credits at 1080p for the same durations. A sensible workflow pairs it with its Turbo sibling: rough the idea in cheaply, then re-render the confirmed prompt here for delivery. It is the right pick for cinematic 8-second establishing shots, vertical hero clips, and final product or brand animation where the extra cost over Turbo buys noticeable polish.

Vidu Q3: up to 16 seconds with native audio

Q3 is Shengshu’s flagship and the longest single take in VdoBloom’s Vidu line: 5, 8 or 16 seconds, with audio generated together with the picture in every render. That changes what one generation can be — a short scene with sound design, a talking beat with ambience, or a product moment with an audio bed can come out of a single prompt instead of a video-plus-separate-audio-pass workflow. It accepts text or a reference image, outputs 720p or 1080p, and frames at 16:9, 9:16 or 1:1.

Pricing runs 40 credits for 5 seconds at 720p up to 145 credits for 16 seconds at 1080p: 40, 63 and 125 credits at 720p for 5, 8 and 16 seconds, and 45, 70 and 145 credits at 1080p for the same durations. Audio is included in every price — there is no separate charge for sound. Q3 is the model for scene-length clips with generated sound, social videos that ship straight from generation, and image-anchored shots where a reference frame sets the look and Q3 adds motion and audio together.

Duration, resolution and credit comparison

Model	Durations	Resolutions	Aspect ratios	Audio	Credits	Filter
Vidu Q1	5s (fixed)	1080p (fixed)	16:9, 9:16, 1:1	Not listed	25 flat	MODERATE
Vidu Q2 Pro	4, 5, 8s	720p, 1080p	16:9, 9:16, 1:1	No	30, 40, 65 (720p); 45, 60, 100 (1080p)	MODERATE
Vidu Q3	5, 8, 16s	720p, 1080p	16:9, 9:16, 1:1	Yes, with video	40, 63, 125 (720p); 45, 70, 145 (1080p)	MODERATE

Read across the credit row and the shape of the family becomes clear: Q1 is a flat price for a fixed clip, Q2 Pro escalates quickly at the long, high-resolution end, and Q3 sits between Q2 Pro’s mid-range and its top end while adding sound on every render. For the difference between a subscription and pay-as-you-go credits, see VdoBloom’s pricing.

The Turbo siblings, and why they affect the choice

Q2 Turbo and Q3 Turbo share the exact spec sheet of their standard siblings and cost roughly half as much, trading some rendering quality for speed. Q2 Turbo runs 15, 18 and 24 credits at 720p and 20, 22 and 30 credits at 1080p for 4, 5 and 8 seconds. Q3 Turbo runs 20, 28 and 55 credits at 720p and 30, 35 and 73 credits at 1080p for 5, 8 and 16 seconds — and it keeps Q3’s audio, which matters because a silent preview cannot tell you whether a sound-dependent concept works. The practical routine for either pair is identical: explore on Turbo at about half price, then pay the standard-tier premium once for the confirmed final.

Five example prompts that work on Vidu

Because the prompt is the main lever on every Vidu model, being specific about a single action and the camera tends to produce more predictable results than a long, multi-clause description. A few that map onto the strengths above:

Q1 with the anime preset: “A lone swordsman walks through falling cherry blossoms, slow dolly forward, cel-shaded anime style, soft wind moving the petals.”
Q2 Pro, 8s establishing shot: “An aerial drone rises over a coastal cliff at golden hour, waves breaking far below, slow reveal of the horizon line.”
Q3, 16s with ambience: “A barista pours latte art into a cup on a wooden counter, warm morning light, gentle steam rising, quiet ambient cafe sound.”
Q1 image-to-video from a product still: “The bottle rotates slowly on a turntable under studio lighting, plain white background, the label stays sharp.”
Q3 image-anchored portrait: “The woman turns her head toward the camera and smiles, the background stays fixed, low room tone underneath.”
Q2 Pro product detail: “Macro push-in on a watch face as the second hand sweeps, shallow depth of field, cool studio light.”

Limits to plan around

The Vidu family shares a set of hard edges worth knowing before you spend. Every model caps at 1080p — there is no 4K tier in this line. Durations are fixed steps, not a slider: Q1 is locked at 5 seconds, Q2 Pro and Q2 Turbo at 4, 5 or 8, and Q3 at 5, 8 or 16. Q2 Pro produces no audio, so any clip that needs sound has to route through Q3 or Q3 Turbo. And the content filter is MODERATE on all of them: ordinary creative and commercial subjects generate normally, but explicit material is refused at the provider level, and there is no permissive tier to switch to. On the upside, the cost is shown before every generation and a failed render is refunded automatically.

Which model to pick

You want the cheapest reliable shot, 5 seconds is fine and it is silent: Vidu Q1 at a flat 25 credits. No knobs, no surprises.
You are iterating on a concept: Q2 Turbo (4/5/8s) or Q3 Turbo (5/8/16s), then finish on the standard tier.
You need a polished 8-second clip with strong motion and no audio: Vidu Q2 Pro.
You need a longer take, or sound baked into the file: Vidu Q3, up to 16 seconds with audio on every render.
Budget first, sound last: build on Q2 Pro and move only the finished concept to Q3 if a longer or louder version is worth the jump.

If you would rather compare Vidu against other generators entirely, best Vidu alternatives covers the neighbours, and how AI video credits work explains the pricing model before you commit.

Frequently asked questions

Which Vidu model is cheapest on VdoBloom?

Vidu Q1 at a flat 25 credits, because it is locked to 5 seconds and 1080p. Q2 Turbo undercuts it at 720p for any duration (15 to 24 credits) and roughly matches it at 1080p (20 to 30 credits), while adding a 720p option and 4- and 8-second durations that Q1 does not have.

Can any Vidu model generate audio?

Yes — Vidu Q3 and Q3 Turbo generate sound together with the picture in every render, at no separate charge. Q2 Pro produces no audio, and Q1 does not list audio generation in its catalog entry, so route any sound-dependent clip through the Q3 pair.

How long can a Vidu clip be?

Vidu Q3 reaches 16 seconds, with 5- and 8-second options for shorter beats. Q2 Pro and Q2 Turbo top out at 8 seconds. Q1 is fixed at 5 seconds by design.

What is the resolution limit across the Vidu line?

1080p. Every model in the family caps there, with 720p as the lower tier on Q2 Pro, Q2 Turbo, Q3 and Q3 Turbo, and no 4K option.

Does Vidu allow mature or NSFW content?

No. VdoBloom rates the family’s content filter MODERATE — standard filtering, not a permissive HOT tier. Explicit material is refused regardless of phrasing, and VdoBloom’s own moderation applies on top of the provider’s filter.

Ready to try the family for yourself? Open the text-to-video tool, pick Vidu Q1 for a flat-price test or move straight to Vidu Q3 if you need a longer take with sound, and the exact cost is shown before anything is generated.