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.

Implement updated FreeU as _for_testing->FreeU_V2 node

comfyanonymousc2bb34d865a4
diff --git a/comfy_extras/nodes_freelunch.py b/comfy_extras/nodes_freelunch.py
index 07a88bd96..7512b841d 100644
--- a/comfy_extras/nodes_freelunch.py
+++ b/comfy_extras/nodes_freelunch.py
@@ -61,7 +61,53 @@ class FreeU:
m.set_model_output_block_patch(output_block_patch)
return (m, )
+class FreeU_V2:
+ @classmethod
+ def INPUT_TYPES(s):
+ return {"required": { "model": ("MODEL",),
+ "b1": ("FLOAT", {"default": 1.3, "min": 0.0, "max": 10.0, "step": 0.01}),
+ "b2": ("FLOAT", {"default": 1.4, "min": 0.0, "max": 10.0, "step": 0.01}),
+ "s1": ("FLOAT", {"default": 0.9, "min": 0.0, "max": 10.0, "step": 0.01}),
+ "s2": ("FLOAT", {"default": 0.2, "min": 0.0, "max": 10.0, "step": 0.01}),
+ }}
+ RETURN_TYPES = ("MODEL",)
+ FUNCTION = "patch"
+
+ CATEGORY = "_for_testing"
+
+ def patch(self, model, b1, b2, s1, s2):
+ model_channels = model.model.model_config.unet_config["model_channels"]
+ scale_dict = {model_channels * 4: (b1, s1), model_channels * 2: (b2, s2)}
+ on_cpu_devices = {}
+
+ def output_block_patch(h, hsp, transformer_options):
+ scale = scale_dict.get(h.shape[1], None)
+ if scale is not None:
+ hidden_mean = h.mean(1).unsqueeze(1)
+ B = hidden_mean.shape[0]
+ hidden_max, _ = torch.max(hidden_mean.view(B, -1), dim=-1, keepdim=True)
+ hidden_min, _ = torch.min(hidden_mean.view(B, -1), dim=-1, keepdim=True)
+ hidden_mean = (hidden_mean - hidden_min.unsqueeze(2).unsqueeze(3)) / (hidden_max - hidden_min).unsqueeze(2).unsqueeze(3)
+
+ h[:,:h.shape[1] // 2] = h[:,:h.shape[1] // 2] * ((scale[0] - 1 ) * hidden_mean + 1)
+
+ if hsp.device not in on_cpu_devices:
+ try:
+ hsp = Fourier_filter(hsp, threshold=1, scale=scale[1])
+ except:
+ print("Device", hsp.device, "does not support the torch.fft functions used in the FreeU node, switching to CPU.")
+ on_cpu_devices[hsp.device] = True
+ hsp = Fourier_filter(hsp.cpu(), threshold=1, scale=scale[1]).to(hsp.device)
+ else:
+ hsp = Fourier_filter(hsp.cpu(), threshold=1, scale=scale[1]).to(hsp.device)
+
+ return h, hsp
+
+ m = model.clone()
+ m.set_model_output_block_patch(output_block_patch)
+ return (m, )
NODE_CLASS_MAPPINGS = {
"FreeU": FreeU,
+ "FreeU_V2": FreeU_V2,
}