Get a weekly rundown of the latest AI models and research... subscribe!




The Kandinsky_v2_2 model is a Text-to-Image AI model that generates images based on a provided text prompt. The model takes inputs such as text prompt, image dimensions (width and height), image guidance scales (positive and negative), number of outputs required, and the number of iterations or steps required for inference. The model generates a URL directing to the generated image as output. It's designed to mix texts and images, which can be useful in AI art creation or visual interpretation of descriptive texts.

Use cases

Kandinsky_v2_2 is an AI model designed to generate images using text and images as inputs. It can potentially be used in several different sectors, depending on the specific needs of the user. For example, in the entertainment industry, it could be used to create concept art for films or video games based on textual descriptions, reducing the time required for manual sketching. It could similarly be employed in advertising to dynamically generate unique and eye-catching imagery based on a given marketing message. Another possible use could be in education, where it could help visually illustrate complex concepts described in text. Graphic designers and digital artists could also leverage this model to experiment with new ideas or create rough drafts to further refine manually. Products based off this model could include software applications for automatic artwork or design generation, with potential uses ranging from hobbyist art creation to professional design work.


Cost per run
Avg run time

Creator Models


Similar Models

No similar models found

Try it!

You can use this area to play around with demo applications that incorporate the Kandinsky_v2_2 model. These demos are maintained and hosted externally by third-party creators. If you see an error, message me on Twitter.

Currently, there are no demos available for this model.


Summary of this model and related resources.

Model NameKandinsky_v2_2
Generate images with Kandinsky 2.2 - Mix text and images
Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkNo paper link provided


How popular is this model, by number of runs? How popular is the creator, by the sum of all their runs?

Model Rank
Creator Rank


How much does it cost to run this model? How long, on average, does it take to complete a run?

Cost per Run$-
Prediction Hardware-
Average Completion Time-