Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

No need for scale_input when fp8 matrix mult is disabled.

comfyanonymous70e15fd743e8
diff --git a/comfy/ops.py b/comfy/ops.py
index 3303c6fcd..ced461011 100644
--- a/comfy/ops.py
+++ b/comfy/ops.py
@@ -360,7 +360,7 @@ def scaled_fp8_ops(fp8_matrix_mult=False, scale_input=False, override_dtype=None
def pick_operations(weight_dtype, compute_dtype, load_device=None, disable_fast_fp8=False, fp8_optimizations=False, scaled_fp8=None):
fp8_compute = comfy.model_management.supports_fp8_compute(load_device)
if scaled_fp8 is not None:
- return scaled_fp8_ops(fp8_matrix_mult=fp8_compute and fp8_optimizations, scale_input=True, override_dtype=scaled_fp8)
+ return scaled_fp8_ops(fp8_matrix_mult=fp8_compute and fp8_optimizations, scale_input=fp8_optimizations, override_dtype=scaled_fp8)
if (
fp8_compute and