The models behind pictures, videos and vectors.
Pictures
Every picture, post and story is made with GPT Image, so there is no image model to pick - you choose the format, shape, quality and number of pictures instead. Every plan includes every model the studio offers.
Videos
Video models differ in the lengths and shapes they make, so the studio lets you choose: Kling 4.0, Wan 3.0, Seedance 2.5, Veo 3.1, Gemini Omni Flash and Grok Imagine make videos, and Happy Horse changes an existing one. Auto chooses a model for your prompt and tells you why.
The longest-running models make clips of up to 30 seconds.
Vectors, and seeing what was used
Vector graphics and picture-to-SVG conversion use Recraft vector models. Every result has a details view showing the models used, the settings, the prompt and the credits it cost.