Model directory

AI Models Available in ClipCanva

Search and filter the AI models connected to ClipCanva. Each model page explains what it takes as input, what it returns, and the kind of work it suits.

Filter by image or video without leaving this pageEach model page states its inputs, outputs, and credit costCompare two models side by side before you commit

Browse and Search the Models

Filter by image or video work, or search for a model by name.

AI Image

GPT Image 2

Review supported inputs and image-generation workflows for GPT Image 2.

AI Image

FLUX 3

Coming soon: track FLUX 3 image and video capabilities, KIE API updates, and upcoming ClipCanva support.

AI Image

Nano Banana 2

Review supported inputs and image-generation workflows for Nano Banana 2.

AI Image

Seedream 5.0 Pro

Review supported inputs and image-generation workflows for Seedream 5.0 Pro.

AI Video

Veo 3.1

Review supported inputs and video-generation workflows for Veo 3.1.

AI Video

Kling 3

Review supported inputs and video-generation workflows for Kling 3.

AI Video

Seedance 2.0 Mini

Review supported inputs and video-generation workflows for Seedance 2.0 Mini.

AI Video

ClipCanva Video Pro

Review supported inputs and video-generation workflows for ClipCanva Video Pro.

AI Video

PixVerse V6

Generate PixVerse V6 videos from text prompts or source images in ClipCanva.

What This Directory Covers

This is the index of generation models available inside ClipCanva workflows. Each entry links to a model page that describes the input it accepts, the output it produces, the controls exposed in the interface, and the credit cost of a run, so you can choose before spending anything.

Includes: Image and video generation models connected to workflows
Not included: Retired models and models not available in ClipCanva

Browse by Job

Start from the result you need.

Generate an image from a prompt

Written brief in, still image out, for product shots, posters, thumbnails, and concept art.

Generate an image from a prompt

Edit an image you already have

Change a background, object, or detail in an existing picture using an instruction.

Edit an image you already have

Generate video from a prompt

Written scene description in, short clip out, for social posts and product storytelling.

Generate video from a prompt

Animate a still image

Start from one frame and add camera or subject motion to turn it into a clip.

Animate a still image

Compare two models

Put two models next to each other on capability, workflow fit, and credit cost.

Compare two models

Browse by Input and Output

Match a model to the assets you already have.

Text to image

No source file needed. Describe the image and pick a model tuned for stills.

Text to image

Image to image

Supply a picture and an instruction to change style, background, or specific details.

Image to image

Text to video

Describe a scene and get a clip, with pacing and motion set by the model you choose.

Text to video

Image to video

Supply a still frame and let the model add movement rather than inventing the whole scene.

Image to video

Models People Open First

Common starting points across image and video work.

GPT Image 2

An image model with strong prompt control and more readable text than most alternatives.

Why it is featured

A reliable default when the brief includes labels, layout, or precise instructions.

GPT Image 2

Nano Banana 2

An image model built around editing instructions rather than full regeneration.

Why it is featured

Best when you already have an image and want to change one part of it.

Nano Banana 2

Veo 3.1

A video model for prompt-driven clips with coherent scene motion.

Why it is featured

A common first test when the brief starts from text rather than footage.

Veo 3.1

Kling 3.0 Turbo

A video model often used for short-form clips and image-led motion.

Why it is featured

Useful for generating several short variations of the same idea.

Kling 3.0 Turbo

How to Choose a Model

Four questions that narrow the list quickly.

Are you starting from text or a file?

Text-first briefs and image-first briefs suit different models. Matching the input avoids fighting the model later.

Does the output need readable text?

Text inside generated images varies a lot between models. If labels matter, choose a model known for prompt precision and check the first result.

How many attempts do you expect?

Credit cost per run is stated on each model page. For heavy iteration, a cheaper run lets you test more versions.

Do you need one long shot or several short ones?

Clip length limits differ by model. Check the length a model supports before planning a scene around it.

AI Models Directory FAQ

Common questions about choosing between the available models.

Which AI models are available in ClipCanva?

The browser above lists the image and video models currently connected to ClipCanva workflows. Each entry links to a model page with its inputs, outputs, controls, and credit cost.

How do I know what a model costs?

Credit cost per run is shown on the individual model page and in the generator before you submit. Costs differ between image and video models, and longer video runs cost more than stills.

Is a newer model always better?

No. Newer versions often improve motion or prompt handling, but an older model may still fit your brief better or cost less per attempt. Compare on the dimension that matters for your project.

Can I compare two models directly?

Yes. The comparison hub puts two models side by side on capability, workflow fit, output review, and cost. Running the same prompt through both is the most reliable test.

Does ClipCanva run these models itself?

ClipCanva is an independent platform that connects to these models through their providers. It is not affiliated with the companies that build them, and availability can change when a provider changes access.

Pick a model for your brief

Filter the AI models by image or video work, open a model page, and check its inputs and cost before generating.

Browse the models