About Genvizu

What Genvizu is

Genvizu is an AI image and video generation studio for creators, e-commerce sellers, and design teams. It puts three things in one place: a prompt gallery of real published work, a generation workspace for images and video, and an infinite canvas where prompts, references, and outputs connect into a workflow. Everything runs in the browser — no local GPU, no model installation.

What you can do

• Generate images — describe a scene, then pick a model, aspect ratio, resolution (1K / 2K / 4K), and batch count. The generate button shows the exact credit cost before you run it.
• Generate video — describe the shot, then choose model, ratio, resolution, and duration. Cost is computed per second and updates live.
• Reverse a prompt from an image — bring in a picture and get prompt language you can reuse and edit.
• Work on an infinite canvas — Canvas mode links prompt nodes, reference images, generations, and agent steps, so a multi-step idea stays visible as a graph instead of a chat log.
• Run Skills — packaged, parameterised recipes (product photo sets, cover design, sticker packs, and more) that turn a short brief into a structured prompt aimed at the right model.
• Browse the prompt gallery — thousands of works published with their prompts and parameters. Filter by model, category, or tag, open one, and load its idea straight into the generator.
• Use the prompt helpers — translate, polish, improve, and smart-variable detection sit right under the prompt box.

Failed generations are refunded automatically.

Models we run

Image: Grok Image 2, Grok Imagine, Seedream 5.0 and Seedream 5.0 Pro, GPT Image 2, Nano Banana 2 and Nano Banana 2 Lite, FLUX.2 and FLUX.2 Pro, Midjourney 8.1 and Midjourney 8.2, Z-Image.

Video: Gemini Omni Flash 1.1, MiniMax H3 (Hailuo 03), Grok Imagine Video and Grok Imagine Video 1.5, Seedance 2.5, Seedance 2.0 in Mini / Fast / Pro tiers, Veo 3.1 in Lite / Fast / standard tiers.

Post-processing: video upscaling on the Topaz engine, and reverse script from video.

Per-model credit costs by resolution and duration are listed on Model Pricing. The line-up changes as providers ship and retire models.

How we work

• Model facts on this site — resolutions, durations, prompt limits, credit costs — come from our own production configuration and from each provider's official documentation, not from secondhand summaries.
• Pages carrying model specifics show a verification date. When a provider changes an endpoint or a price, we re-check and restamp rather than leave a stale number standing.
• Example prompts in the gallery and inside Skills are run by our team on the models we actually ship. When a model cannot do something reliably, we say so instead of padding a comparison.
• We do not accept payment for reviews, rankings, or placement, and we do not publish sponsored model comparisons.

Pricing at a glance

Genvizu runs on credits. A subscription grants credits every month, and one-time credit packs are available separately and stay valid for 365 days. Free accounts can browse and search the whole gallery and receive bonus credits at sign-up. Plans and per-model costs are on the pricing page.

Content policy and rights

Use of the service is governed by our Terms of Service. Copyright complaints go through our DMCA process. Publishing a workflow to the community gallery is covered by the Workflow Publish Agreement.

Genvizu does not claim ownership of what you generate. Commercial use depends on the model provider's terms and on applicable law: some third-party models, Midjourney among them, limit commercial use under their own terms, and those limits apply whatever your Genvizu plan is. The model disclosure in the app flags this before you generate.

Team and contact

Genvizu is built and operated by the Genvizu Team. For support, corrections to anything published here, licensing questions, or press, write to support@genvizu.com. We reply in English and Chinese.