The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Add some tesla pascal GPUs to the fp16 working but slower list.
comfyanonymousdce3555339a0
diff --git a/comfy/model_management.py b/comfy/model_management.pyindex adcc0e8ac..9f9248831 100644--- a/comfy/model_management.py+++ b/comfy/model_management.py@@ -753,7 +753,7 @@ def should_use_fp16(device=None, model_params=0, prioritize_performance=True, ma#FP16 is confirmed working on a 1080 (GP104) but it's a bit slower than FP32 so it should only be enabled#when the model doesn't actually fit on the card#TODO: actually test if GP106 and others have the same type of behavior- nvidia_10_series = ["1080", "1070", "titan x", "p3000", "p3200", "p4000", "p4200", "p5000", "p5200", "p6000", "1060", "1050"]+ nvidia_10_series = ["1080", "1070", "titan x", "p3000", "p3200", "p4000", "p4200", "p5000", "p5200", "p6000", "1060", "1050", "p40", "p100", "p6", "p4"]for x in nvidia_10_series:if x in props.name.lower():fp16_works = True