The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Text encoder should initially load on the offload_device not the regular.
comfyanonymous1300a1bb4c87
diff --git a/comfy/sd.py b/comfy/sd.pyindex 1edc5fd29..a63a0d1de 100644--- a/comfy/sd.py+++ b/comfy/sd.py@@ -80,7 +80,7 @@ class CLIP:load_device = model_management.text_encoder_device()offload_device = model_management.text_encoder_offload_device()- params['device'] = load_device+ params['device'] = offload_deviceif model_management.should_use_fp16(load_device, prioritize_performance=False):params['dtype'] = torch.float16else: