13 AI models for image and video
Pick the right model for the job, from photorealistic 4K stills to cinematic 15-second video. Every model runs inside DesignerBox on one credit balance, one library, one workflow.
Image models
ImageNano Banana Pro
High-quality image generation and editing powered by Gemini 3 Pro
5 credits per imageOpen model
ImageNano Banana 2
Fast production-scale image generation on Gemini 3.1 Flash
3 credits per imageOpen model
ImageGPT Image 2
OpenAI next-gen image model with photorealistic quality up to 4K
8 credits per imageOpen model
ImageSeedream 5
2K-3K resolution with native text rendering, editing, and style transfer
4 credits per imageOpen model
ImageFLUX 2 Flex
Superior typography, retexturing, and multi-reference editing
7 credits per imageOpen model
ImageFLUX Pro 1.1
Professional-grade text-to-image generation
5 credits per imageOpen modelKontext Multi
Combine multiple references for consistent character and style
5 credits per imageOpen modelVideo models
VideoVeo 3.1
Highest quality realistic generation with native audio
30 credits per second at 1080pOpen model
VideoVeo 3.1 Fast
Quick drafts with native audio at moderate cost
12 credits per second at 1080pOpen model
VideoSora 2 Pro
OpenAI premium model for high-quality cinematic output with audio
70 credits per second at 1080pOpen model
VideoSeedance 2.0
Highest quality with audio, interpolation, and multi-reference. Up to 15 seconds
12 credits per second at 720pOpen model
VideoKling 2.6 Pro
Latest Kling with improved motion quality and consistency
8 credits per second at 720pOpen modelRunway Gen-4.5
Polished visuals and image animation with strong aesthetic quality
15 credits per second at 720pOpen modelHow to choose a model
There is no single best model. The right one depends on what you are making, how many versions you need, and how much of your credit balance the job deserves. Three rules cover most decisions.
Match the model to the job, not the benchmark
Text inside the image is a different problem from photoreal skin, and neither is the same as animating a still. GPT Image 2 and Seedream 5 lead on typography, Nano Banana Pro on prompt fidelity, Kontext Multi on keeping one character consistent across a campaign.
Iterate cheap, finish expensive
Draft with the fast, low-credit models and spend the premium rate only on the frame you are shipping. Nano Banana 2 at 3 credits lets you try 50 directions for what a handful of premium runs would cost, then rerun the winner on Nano Banana Pro.
For video, price the clip, not the second
Video is billed per second, so length drives cost more than model choice. An 8-second Veo 3.1 clip at 1080p costs 240 credits; the same brief on Veo 3.1 Fast costs 96. Storyboard the length first, then pick the tier.
Not sure which image model to pick?
See every model run the same prompt, side by side, across product shots, portraits, ads with text, and more, then choose by result instead of by name.
Questions about AI models
Which AI model is best for image generation?
Do I need a separate subscription for each model?
How much does each model cost to run?
Can I use the output commercially?
Which video models generate audio?
Start generating with any model
Free to start, no credit card required. Switch between every model inside the same workflow.