#vram
-
ComfyUI GPU Requirements: How Much VRAM You Need
Published weight sizes for SD 1.5, SDXL and Flux mapped to real VRAM tiers, plus the system RAM, disk and runtime flags that lower the floor.
-
ComfyUI Out of Memory Errors: Causes and Fixes
Read the allocator message, work out which graph stage overflowed, then apply the ComfyUI and PyTorch settings that actually lower peak VRAM.
-
ComfyUI vs Automatic1111 vs Forge: Which to Run
Release cadence, memory architecture, extension risk and automation compared across ComfyUI, the AUTOMATIC1111 WebUI and Forge, with a decision table.
-
How ComfyUI Graphs Execute and Where VRAM Goes
Node graph execution order, result caching, VRAM pressure across the three failure stages, and custom node dependency management in ComfyUI.