The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Fix Flux FP64 math on XPU (#4210)
a-One-Fana178e25912b0
diff --git a/comfy/ldm/flux/math.py b/comfy/ldm/flux/math.pyindex 88c2b6bb4..136ce2aa8 100644--- a/comfy/ldm/flux/math.py+++ b/comfy/ldm/flux/math.py@@ -14,7 +14,7 @@ def attention(q: Tensor, k: Tensor, v: Tensor, pe: Tensor) -> Tensor:def rope(pos: Tensor, dim: int, theta: int) -> Tensor:assert dim % 2 == 0- if comfy.model_management.is_device_mps(pos.device):+ if comfy.model_management.is_device_mps(pos.device) or comfy.model_management.is_intel_xpu():device = torch.device("cpu")else:device = pos.device