Vidu 2.0: Image to Video Online
Bottom line
Shengshu's image-to-video specialist turns one still into a 4-second clip at up to 1080p. Upload a starting frame, choose Vidu 2.0 in the Image to Video tool, and animate it on VdoBloom — the credit price appears before every generation.

Vidu 2.0 does one job: it takes an image you already have and puts it in motion. There is no text-to-video mode here — every generation starts from a still, which keeps the workflow honest. The composition, character design, and color grade are decided by your source frame; the model's work is deciding how that frame should move.
That constraint suits creators who art-direct in an image tool first. Generate or retouch a keyframe until it is exactly right, then hand it to Vidu 2.0 for a 4-second clip at 720p or 1080p, framed at 16:9 or square 1:1. Because the output stays anchored to your input, it drifts from the intended look far less than prompting a scene from nothing.
Vidu comes from Shengshu Technology, the Beijing team spun out of Tsinghua University research, and 2.0 is the family's enhanced image-to-video generation. On VdoBloom it carries a 3.9 rating and MODERATE content filtering, and the credit cost of each run is shown before you generate.
What creators use Vidu 2.0 for
- Bringing concept art or illustration to life while preserving the exact style of the original frame.
- Turning square 1:1 product photos into short motion clips for listings and feed posts.
- Animating keyframes produced by VdoBloom's image models, using the still as a lock on composition and look.
How to use Vidu 2.0 on VdoBloom
- 1Open the Image to Video tool and select Vidu 2.0 from the model picker.
- 2Upload your starting image and describe the motion you want in the prompt.
- 3Choose your duration (4–4s), quality (720p/1080p), aspect ratio, review the credit cost, and generate.
Frequently asked questions
Can Vidu 2.0 generate video from a text prompt alone?
No. Vidu 2.0 is image-to-video only — every generation requires a source still. You use the prompt to describe motion and camera behavior, but the image defines what appears on screen.
How long are Vidu 2.0 clips and at what resolution?
Generations are 4 seconds long, output at 720p or 1080p. Framing options are 16:9 widescreen or 1:1 square.
What content restrictions apply on Vidu 2.0?
It carries VdoBloom's MODERATE label, meaning standard filtering: normal creative and commercial imagery is fine, while explicit uploads or prompts are rejected. Filters apply to the source image as well as the prompt.
Why choose Vidu 2.0 over Vidu's Q-series models?
Choose it when you already have the exact frame you want animated. Because it only accepts image input, results stay tightly anchored to your still, whereas the text-capable Q-series models give the generator more freedom to interpret.