ComfyUI/comfy_extras/nodes/nodes_freelunch.py

"""
Portions of this code are adapted from the repository
https://github.com/ChenyangSi/FreeU

MIT License


Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
"""

import torch
import logging

def Fourier_filter(x, threshold, scale):
    # FFT
    x_freq = torch.fft.fftn(x.float(), dim=(-2, -1))
    x_freq = torch.fft.fftshift(x_freq, dim=(-2, -1))

    B, C, H, W = x_freq.shape
    mask = torch.ones((B, C, H, W), device=x.device)

    crow, ccol = H // 2, W //2
    mask[..., crow - threshold:crow + threshold, ccol - threshold:ccol + threshold] = scale
    x_freq = x_freq * mask

    # IFFT
    x_freq = torch.fft.ifftshift(x_freq, dim=(-2, -1))
    x_filtered = torch.fft.ifftn(x_freq, dim=(-2, -1)).real

    return x_filtered.to(x.dtype)


class FreeU:
    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "model": ("MODEL",),
                             "b1": ("FLOAT", {"default": 1.1, "min": 0.0, "max": 10.0, "step": 0.01}),
                             "b2": ("FLOAT", {"default": 1.2, "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 = "model_patches"

    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:
                h[:,:h.shape[1] // 2] = h[:,:h.shape[1] // 2] * scale[0]
                if hsp.device not in on_cpu_devices:
                    try:
                        hsp = Fourier_filter(hsp, threshold=1, scale=scale[1])
                    except:
                        logging.warning("Device {} does not support the torch.fft functions used in the FreeU node, switching to CPU.".format(hsp.device))
                        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, )

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 = "model_patches"

    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:
                        logging.warning("Device {} does not support the torch.fft functions used in the FreeU node, switching to CPU.".format(hsp.device))
                        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,
}