Turn one photo, or up to 15 images and 3 voice clips, into 3–16s video with sound, up to 4K.
Every clip below is a Vidu Q4 generation the Renoise team made for this page at 1080p, one take each, with the inputs shown in the corner. Hover a clip with sound to hear it.
Give Vidu Q4 up to 15 reference images, people, products, places or a style, and it builds one shot around them while keeping each recognizable. Shown: a portrait and a product photo become an 8-second kitchen scene with the same woman and the same tumbler.
Add up to 3 audio clips next to your images and Vidu Q4 speaks in that voice, with lip movement matched to the line you write. Shown: one photo and a 3-second voice sample turn into a café vlog intro with a brand-new line.
Start from one frame and Vidu Q4 animates it at the frame’s own aspect ratio. ShengShu tuned Q4 for martial arts, running and fights with fewer deformations. Shown: a rooftop still becomes a high kick and a return to guard in the rain.
Vidu Q4 renders fireballs, smoke, sparks and dust together with the sound of them, because audio is always generated with the picture. Shown: a still of a desert fuel depot turned into a fireball, rolling smoke, flying sparks and a dust wave.
Vidu Q4 is ShengShu Technology’s image-driven AI video model with native audio, released as Vidu Q4 Preview on October 7, 2026. It turns one first frame, or 1–15 reference images plus up to 3 voice clips, into a 3–16 second clip at 540P, 720P, 1080P, 2K or 4K. It does not do text-to-video.
In Renoise, Vidu Q4 sits next to Seedance, Kling, MiniMax and more than 30 other models on one subscription, in the Videos page, the Canvas, the Agent, and the API and CLI.
Only have a text prompt, or need a shot longer than 16 seconds? Use Seedance 2.5.
Specs as available in Renoise, checked November 11, 2026. 10-bit per ShengShu.
Open Videos and pick Vidu Q4. Use Start Frame to animate one image, or Multi-shot to combine up to 15 reference images and 3 voice clips. The two modes don’t mix, and every Vidu Q4 task needs at least one image.
Say what each reference is (“Image 1 is the woman, Image 2 is the tumbler, Audio 1 is her voice”), then the action, the camera move and any dialogue in quotes. Describe the sound you want too; Vidu Q4 always generates audio.
Choose 540P to 4K and 3–16 seconds; in Multi-shot also 16:9, 9:16 or 1:1. Test the motion at 540P first: short clips take a few minutes, while a 16-second 1080P clip can take about half an hour and 4K longer.
From ShengShu’s preview launch to every resolution tier in Renoise.
The first public preview of the next Vidu flagship goes live on Vidu’s web app and API, with image-to-video and reference-to-video only.
Vidu Q4 joins the Renoise video picker, Canvas, Agent, API and CLI at 720P and 1080P, 3–16 seconds.
Renoise opens the cheaper 540P tier and native 2K and 4K output, all at 3–16 seconds.
Sources: ShengShu press release (October 7, 2026), Renoise model list and changelog. Last updated
Three reference-driven video models in Renoise, compared on the limits Renoise exposes.
| In Renoise | Seedance 2.5 | Kling 4.0 Omni | |
|---|---|---|---|
| Clip length | 3–16s | 4–30s | 3–30s |
| Max resolution | 4K | 1080p | 4K |
| References | 15 images · 3 audio | 30 images · 10 videos · 10 audio | 10 images · 5 videos |
| Text-to-video | No | Yes | Yes, via Kling 4.0 |
| Credits · 5s at 720p | 95 | 160 | 130 |
| Best for | Voice-driven characters, 4K from a photo | Long shots, video and audio references | 30s shots that copy a reference video |
Renoise model list and credit estimates (checked 2026-11-11).
A 5-second clip costs 120 credits at 1080P on Vidu Q4, against 190 on Kling 4.0 Omni and 360 on Seedance 2.5, and Vidu Q4 also offers 2K and 4K.
It takes up to 3 voice clips beside 15 images, so a character can speak in a voice you supply. Kling 4.0 Omni takes no audio references.
Vidu Q4 needs an image and stops at 16 seconds. Seedance 2.5 and Kling 4.0 take plain text and run to 30 seconds.
MiniMax H3 also generates sound, takes first and last frames and reference videos, and costs 60 credits for 5 seconds at 768p; it stops at 2K and 15 seconds.
As of October 2026, 100,000+ creators in 170+ countries and regions use Renoise AI, an AI video, image and audio platform, to generate 300,000+ images and videos with 30+ models.
Source: Renoise internal data, March–October 2026. Figures are rounded down and updated quarterly. Last updated
Real feedback from creators who use Renoise AI to make videos, images and ads.
Renoise is pretty easy to use, with a clean and smooth interface. The results from Seedance 2.5 also feel noticeably smoother in action sequences.
Renoise Ai is a good tool for making ai videos and photos. it puts several Ai models in one place, so you don't need to use many different apps.
あまりAIツールを使ったりしたことなかったですが、キャラクターの固定や動画を続いて作成できて使いやすいです。これからどんどん進んでいくアップデートが楽しみです。
Renoise has been a great platform for AI creativity. The tools are easy to use, the experience is smooth, and it makes creating content more enjoyable and efficient. I really appreciate the work the team is doing and look forward to seeing more improvements. Highly recommended!
What I like about Renoise AI compared to other platforms: Fast generation speed: Slow generation takes up way too much time, but Renoise AI is surprisingly about 30% faster. Intuitive and user-friendly UI: Cheaply made platforms have terrible UIs that make me not even want to log in, but Renoise is very clean and convenient. Remembers my previous settings: It helpfully remembers my last workspace settings. Some odd platforms force you to re-adjust everything every single time you generate a video, which is extremely frustrating. Overall preference: For all these reasons, Renoise AI is definitely my preferred platform. Thank you!
Renoise is your go to one stop all for ai creators. all view and use all models in one place, for any type of content you have your mind on!
I have a creat experience with the app. Consistent characters but also unique. THere were some issues with storyline continuity and non-typical humanoid characters.
One Renoise plan unlocks Vidu Q4 and every other video and image model, billed per generation from your plan credits.
For your first AI creations
per month
≈ 150 GPT Image 2 Generations
≈ 60 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For creating every week
per month
≈ 450 GPT Image 2 Generations
≈ 180 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For professional-scale production
per month
≈ 1,750 GPT Image 2 Generations
≈ 700 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For your first AI creations
per month, billed annually
Save $48compared to monthly
≈ 150 GPT Image 2 Generations
≈ 60 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For creating every week
per month, billed annually
Save $216compared to monthly
≈ 450 GPT Image 2 Generations
≈ 180 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
For professional-scale production
per month, billed annually
Save $960compared to monthly
≈ 1,750 GPT Image 2 Generations
≈ 700 Seedance 2.0 videos
The agent takes your idea all the way to a finished cut.
Starter and Standard: production work in Director Mode uses credits by usage. Advanced: free.
No queue. Start as many paid generations as you want at once.
Renoise Agent runs on frontier models from leading AI labs to plan your shots, write prompts, and pick the right model for each one. Chatting with the Agent is free on every plan.
Content generated with Renoise.ai may be used commercially, subject to our Terms of Service
Yes. ShengShu released Vidu Q4 Preview on October 7, 2026, on its own web app and API, and Vidu Q4 has been live in Renoise since October 13, 2026, with 540P, 2K and 4K added on October 15. ShengShu has not given a date for the full Q4 release.
Yes. ShengShu’s current release is called Vidu Q4 Preview, and that is the model behind Vidu Q4 in Renoise; Renoise just drops the word Preview from the picker. When ShengShu ships the full Q4, the same Renoise entry will move to it.
No. Every Vidu Q4 generation needs at least one image: either one first frame, or 1–15 reference images. A prompt with no image is rejected before any credits are charged. For text-only video, use Seedance 2.5 or Kling 4.0, or make a first frame with an image model and animate it with Vidu Q4.
Any whole number of seconds from 3 to 16, in both Start Frame and Multi-shot mode, at every resolution. For a longer piece, chain several Vidu Q4 shots in the Canvas, or use Seedance 2.5 or Kling 4.0, which run up to 30 seconds per clip.
Yes. Vidu Q4 renders natively at 540P, 720P, 1080P, 2K and 4K in Renoise, and ShengShu says 2K and 4K come in 10-bit color. 4K costs 78 credits per second and is the slowest tier, so test the motion at 540P or 720P first.
Up to 15 reference images plus up to 3 audio clips in Multi-shot mode, or exactly one first frame in Start Frame mode. The two modes can’t be combined. Vidu Q4 takes no last frame, no reference video and no audio without an image.
Yes, always. Vidu Q4 generates dialogue, ambience and sound effects together with the picture, and in Renoise the audio can’t be switched off. Put the lines in quotes and describe the sounds you want; if you need a silent clip, mute it when you edit.
Vidu Q4 is billed per second: 9 credits at 540P, 19 at 720P, 24 at 1080P, 38 at 2K and 78 at 4K. A 5-second clip is 45 credits at 540P, 95 at 720P and 120 at 1080P. References add nothing. See pricing for plans.
Vidu Q4 is one of the slower video models in Renoise. Short clips finish in a few minutes, but a 16-second 1080P clip or a task with many references can take about half an hour, and 2K and 4K take longer. You can keep working in the Canvas while it runs.
Vidu Q4 is made by ShengShu Technology, the company behind Vidu. Renoise does not train video models; it runs Vidu Q4 next to Seedance, Kling and others. You own your output, and content made in Renoise can be used commercially, subject to the Terms of Service. Use only faces and voices you have the rights to.
Animate a frame or combine up to 15 images and 3 voice clips with Vidu Q4, then switch to Seedance 2.5 or Kling 4.0 shot by shot in the same Canvas.