AI models
The AI models built into DesignerBox
Pick a model in Generate, or let DesignerBox pick one for each request. Every run uses the credits of your plan, with no separate subscription for each model.
- Claude
- ChatGPT
- Cursor
The models
Image and video models in one place
Open a model to see what it is good at, the shapes it makes and how to use it in DesignerBox.
Image models
Pick one in Generate, or set it in a workflow step.
Nano Banana ProGoogle's image model for fine detail, readable text and editsGoogle
Nano Banana 2Google's fast image model for drafts and large setsGoogle
GPT Image 2OpenAI's image model for long briefs and text, up to 4KOpenAI
Seedream 5ByteDance's image model for people, clothing and text, at 2K to 3KByteDance
FLUX 2 FlexTypography, retexturing and edits from several referencesBlack Forest Labs
FLUX Pro 1.1Steady, photoreal pictures for large setsBlack Forest Labs
Video models
The model and the length of a clip set its cost. Video starts on the Premium plan.
Also built in
More models in Generate and in workflow steps
- Kontext Multi, Black Forest Labs. The same person or style across several pictures.
- Runway Gen-4.5, Runway. Polished clips that animate a still picture.
Same brief, three models
The same brief on three image models
Image models differ most on skin, clothes, food and words on the picture. Compare the results, then choose.
One product shot on three models
The same brief for a product photo, made on three image models. Pick the one whose result you like, then use it in Generate or in a workflow step.
Compare models in Generate
FLUX 2 Flex
GPT Image 2
Nano Banana ProOne fashion brief on three models
A model in a green evening dress, the same brief on three image models. Clothes and skin are where image models differ most.
Compare models in Generate
FLUX 2 Flex
Nano Banana Pro
Seedream 5One food brief on three models
A burger and fries for a menu, the same brief on three image models.
Compare models in Generate
FLUX 2 Flex
Nano Banana Pro
Seedream 5One ad with words on three models
An ad with a headline on it, the same brief on three image models. Some models spell words on a picture better than others.
Compare models in Generate
GPT Image 2
Nano Banana Pro
Seedream 5One portrait on three models
A head shot for a profile or a team page, the same brief on three image models.
Compare models in Generate
FLUX 2 Flex
GPT Image 2
Nano Banana ProStart free. You see the price before you make anything.
Video models start on the Premium plan. Your own photos and prompts start on the Pro plan.
How to choose
Three rules for picking a model
There is no single best model. The right one depends on what you are making.
- Match the model to the jobWords on a picture are a different problem from real-looking skin. GPT Image 2 and Seedream 5 are strong on text. Nano Banana Pro follows the brief closely.Open Generate
- Draft fast, finish on the bestTry ideas on a fast model, then make the final picture on the strongest one. In a workflow, that is two steps.See workflows
- For video, choose the length firstVideo costs more the longer the clip. Plan the length first, then pick the model. You see the price before you press Generate.See AI video ads
Which AI model is best for image generation?
There is no single best model. Nano Banana Pro is strong at following the brief and at real-looking skin. GPT Image 2 is strong at text on the picture and 4K detail. Seedream 5 is strong at typography. FLUX 2 Flex is strong at edits from several references.
Do I pick the model for each run?
You can. In Generate you choose the model, the size and the number of results. In Create, DesignerBox picks the model for you. In a workflow you set the model in each step, and in a batch you set it for each row or for all rows.
Do I pay for each model separately?
No. The models are built into DesignerBox. Each run uses credits from your plan, and you see the price before you press Generate.
Can I use the results commercially?
Yes, from the Pro plan up. Pro, Premium and Ultra include the commercial licence, so you can use results in products, ads, client work and social posts. Free and Basic do not include it.
Which video models make sound?
Veo 3.1, Veo 3.1 Fast, Seedance 2.0 and Kling 2.6 Pro make video with sound. Runway Gen-4.5 makes video only.
Make your first pictures today.
Sign up with Google or your email. Nothing to set up.
Get started free- Claude
- ChatGPT
- Cursor















