dGEN Visual StudioMCP & AI Agent Sign in

Every top model for image
and video. One AI studio.

The all-in-one platform to generate and edit high-resolution images and videos with top-tier AI models. Maintain brand consistency using custom LoRAs, co-create with an intelligent AI assistant, or construct reusable node-based visual workflows for creators and autonomous AI agents via MCP.

Nano Banana Pro

Veo 3.1

GPT Image 2.5

Kling 3.0

Seedance 2.5

Seedream 5

FLUX 3

MiniMax H3

Join the waitlist MCP & AI Agent

Watch the trailer

The whole studio in 45 seconds

AI Image GeneratorProduct shots, ads and edits from a prompt, a photo or your own LoRA.

AI Video GeneratorTurn an idea or a still into a cinematic clip, with sound where the model makes it.

AI AssistantSay what you need. Name a model or let it choose one, and it writes the prompts.

dGEN FlowBuild a workflow once, then run it for every product, client or campaign.

Tools & TemplatesTemplates and one-click tools that already do the job. Change the input and run.

MCP & AI AgentLet Claude or your own agent run the studio while you do something else.

Made in the studio

See what comes out

Fantasy, film, product and fashion, all made in this studio. Hover a clip to play it.

An astronaut on a red dune watching two moons rise over a ruined alien ring on the horizon.

A model in a mirror-chrome gown on white salt flats at sunrise.

A running shoe made of moss and flowers floating in a beam of light above a forest floor.

Three longships sailing into a snowy fjord under green and violet northern lights.

See everything made in the studio

Models

The right model for every job

Pick the model that is strongest at what you are making, and switch the moment a better one lands. One studio, one balance, no subscription per lab.

Kandinsky 6

Best forCinematic clips from long prompts, and steady video upscaling

Recraft 4.1 Flash

Best forCheap drafts, icons and flat illustration in your colours

Bria FIBO Edit

Best forProduct and clothing photos for a webshop

Gemini Omni Flash 1.1

Best forA character that keeps its look and voice across clips

MiniMax H3 Max

Best forRecasting, extending and lip-syncing footage you already have

Wan 3.0

Best forShots that run from your start frame to your end frame

BiRefNet

Best forClean cut-outs for product photos

FLUX 3

Best for4K stills and long clips from one family

Bria

Best forBigger images, and backgrounds out of video

PixVerse V6

Best forCheap video drafts, with sound when you need it

Wan 2.7

Best forCoherent motion from a prompt, no start image needed

Pika 2.2

Best forTurning a photo into a moving shot

See all models How to pick one

Features

Everything you need to ship real work

One good image is luck. Forty that belong together, on a deadline, is a studio.

Create

Direct the shot, not the prompt

Pick a camera move, a lens and a light. The studio writes the prompt.

Describe it. The assistant builds it.

Say what you want in your own words. Name a model or let it pick one, and it sets the rest up.

Compare five models in one run

One prompt, five results side by side. Pick the winner instead of guessing.

Stay consistent

One idea becomes a finished sequence

Describe your piece once and every shot comes back in the same style.

Your character, in every scene

One reference image, or your own LoRA, holds through the whole sequence.

Every format, first time right

Vertical, wide or square. The studio sets it up on the model you chose.

Scale up

Build it once, reuse it forever

Save how you work as a pipeline and run it for the next client unchanged.

Let an AI agent run the studio

Connect Claude over MCP and it generates while you do something else.

Start halfway, not from scratch

Open a template that already does the job. Change the prompt and run it.

Stay in control

See it before you pay for it

Storyboard in stills first. Approve the frames, then shoot the video.

Know the price before you press go

The cost sits on the button. If a run breaks on our side, the credits come back.

Nothing you make gets lost

Everything lands in your library, searchable by prompt and by model.

In the studio

Work the way you want. Same models, same price.

Type a prompt, describe the job, build a pipeline, or hand it to an agent. Nothing is locked behind the way in that you pick.

dGEN AI Image Generator in the studio

dGEN AI Image Generator

Text to image, image to image, and your own LoRA.

dGEN AI Video Generator in the studio

dGEN AI Video Generator

Text to video, image to video and video to video, with sound where the model supports it.

dGEN AI Assistant in the studio

dGEN AI Assistant

Describe what you want and it writes the prompts. Name a model and it uses that one, or leave the choice to it.

dGEN Flow in the studio

A node canvas that turns a one-off into a repeatable pipeline.

Why dGEN

What most platforms do not give you

Fair pricing, work you can repeat, and your files stored in Europe. Built in the Netherlands by dGEN Labs.

Credits that never expire

Most platforms sell monthly credits that lapse. Here you buy a pack once and keep what you do not use.

The price before you press go

Every run shows its cost on the button. If it breaks on our side, the credits come back.

Pay per run, top up when you like

There is no subscription and no monthly minimum. A quiet month costs you nothing.

Your process, saved as a Flow

Most tools stop at one prompt. A Flow keeps the whole pipeline, so the next batch is one click.

An agent can do the work

Connect Claude or your own agent over MCP. It runs the studio with the permissions you give it.

Stored in the EU, never trained on

Your files and account are stored in the EU. We do not train models on your work, and you can use it commercially.

Guides

Get better results, faster

The model is rarely the problem, the prompt is. These guides show you what to say, which model to say it to, and what it costs.

A photographic print on a desk with one area masked off by tape.

Make an image, then change it

The second attempt is usually an edit, not a new generation. Knowing which is which saves most of the cost.

A clapperboard on a dark table, one corner lit, the slate empty.

From an idea to a clip

The four ways a video model can be started, and how to tell which one your idea needs.

A ceramic mug on an oak table, lit from one side, the background falling out of focus.

How to write a prompt that works

The same idea gets a different result on every model. This is why, and what to write instead.

Two printed film stills side by side on a dark table: the same scene, a different person in each.

A different person in the same video

Film once, cast as often as you like. The motion, the cuts and the sound stay exactly as they were.

A virtual reality headset resting on a desk beside a printed world map.

Video you can look around in

One clip that holds the whole sphere around the viewer, for a headset, a 360 player or a scrollable embed.

A strip of film on a light box with a few frames marked in red grease pencil.

Working on footage you already have

Make a clip longer, put a scene in the middle, sharpen it, or make a face speak, without starting over.

Pricing

Credits that never expire.

Buy a pack once and use it whenever you like. You pay per run, and the price is on the button before you press it.

15,000

credits

≈ 93 images or 10 clips

€15

Get early access

Most popular

42,400

credits+6% extra

≈ 265 images or 30 clips

€40

Get early access

82,500

credits+10% extra

≈ 515 images or 58 clips

€75

Get early access

172,500

credits+15% extra

≈ 1,078 images or 123 clips

€150

Get early access

300,000

credits+20% extra

≈ 1,875 images or 214 clips

€250

Get early access

600,000

credits+20% extra

≈ 3,750 images or 428 clips

€500

Get early access

Custom

for teams

Contact

All prices exclude VAT. Estimates use Nano Banana for images and 5‑second Kling 2.5 Turbo clips. Every model shows its own price before you run it.

If a run breaks on our side or at the provider, you get every credit back. How refunds work

FAQ

Questions people ask first

What is dGEN Visual Studio?

One studio for AI images and video, with 141 models: 17 for images, 24 for editing and 100 for video. Use the generator, let the assistant set it up, or save a workflow on the canvas and run it again.

What does it cost?

You buy credits in packs, starting at €15 excluding VAT, and pay per run. The price is on the button before you start. There is no subscription, and credits you buy do not expire.

What happens if a generation fails? Do I lose the credits?

If something breaks on our side or at the provider, you get every credit back. If a model refuses a request it had already started, you pay only what that attempt cost us and the rest comes back.

Can I use the results commercially?

Yes. We claim no ownership of what you make, and every model in the studio is licensed by its provider for commercial use. We checked all of them.

Do I own the copyright in what I generate?

You are free to use what you make. Whether it is also protected by copyright depends on how much of your own creative work goes in: under European law, an image made purely from a prompt may not be. Your own photo, style or edits strengthen your position.

All questions and full answers →

Get early access

The studio opens in stages. We let people in in the order they signed up, and you start with 1,000 free credits.

We use your address only to let you in, and for nothing else. You are on the list once you confirm the email.