Skip to main content

Image Generation

generation workload

Curated

Diffusion or transformer image models. Iterative denoising is compute-heavy; VRAM scales with resolution and batch.

Classification

Category
generation
Compute profile
compute-bound
Scaling
horizontal

Infrastructure considerations

Qualitative — no fabricated numbers
Interconnect sensitivity
low
Network sensitivity
low

Curated · Memory · Model weights + activations scaling with resolution and batch size.

Curated · Storage · Model weights plus generated-image output storage.

Typical frameworks

Curated — not a catalog relationship
PyTorchTensorRTDiffusers

Relevant models

Models that run this workload

Data class

Curated · The workload taxonomy is authored qualitative reference, not an ingested source. Sensitivities and profiles are classifications, not measurements; a workload's concrete VRAM comes from the specific model it runs.