Back to the interactive map
Inference Workload

Image / Video Synthesis

Latent diffusion — iterative denoising of a latent image conditioned on text or image prompts. Powers all major text-to-image tools.

Editorial compatibility: these components can be used together in representative deployments. That's not a requirement or a validated implementation. For real deployments, see the sourced reference architectures.

Compatible from earlier layers

Compatible with later layers