Model Terminal

Stable Cascade

Stable Cascade is Stability AI's text-to-image diffusion model built on the Würstchen architecture, using a three-stage cascade pipeline (Stages C, B, and A) to generate images from text prompts in a highly compressed latent space. Released as a non-commercial research preview, it is designed to be easier to fine-tune on consumer hardware than prior Stable Diffusion models. Source: supabase.

Value score
Not scored
Context
tokens
Max output
tokens
Price

Capability radar

Identity

Developer
stabilityai
Openness
Modalities
Release
Knowledge cutoff
Deprecation
API docs

Benchmarks

No benchmark scores yet.

Compare nearby

Pricing

Input / 1M
Output / 1M
Speed