RTX 3090 ComfyUI Tuning: xformers + sage-attention
RTX 3090 ComfyUI Tuning: xformers + sage-attention Default PyTorch attention is safe and predictable. It is not fast. On the RTX 3090 with SDXL, switching from vanilla attention to xformers cut per-image generation time by roughly 25%. Adding sage-attention on top trimmed another 10–15% on longer diffusion runs. Neither change requires touching a single ComfyUI […]
Read →
