Cubric Vision - Models

Models

Image and video models, what each one supports, and where they show up in the app.

A "model" in Cubric is more than a safetensors file. Each model ships with structural context describing the operations it can run, so the UI only exposes what the model can actually do.

Model install state

The Models panel can show a model as partially installed when some required files are present and others are missing. A partially installed model is visible, but Cubric Vision will only enable operations once the files needed for that operation are installed.

Cubric Vision Models panel showing a partially installed model with missing required files — Partial install states make missing model files visible before you try to run an operation.

Image models

Image models support operations documented in Image Tools:

Text-to-image (T2I). Base generation.
Image-to-image (I2I). Restyling, recomposing.
Detailer / masking. Faces, hands, and masked region edits.
Upscale. Latent upscales for resolution.

Video models

Video models add temporal-consistency operations documented in Video Tools:

Text-to-video (T2V). Base generation from a prompt.
Image-to-video (I2V). Animate a static base.