From 72de57d2b07029aed43d546a071c4e13357f8269 Mon Sep 17 00:00:00 2001 From: kijai <40791699+kijai@users.noreply.github.com> Date: Sat, 4 May 2024 19:17:14 +0300 Subject: [PATCH] Possible optimizations and add DownloadInstanceDiffusionModels -node --- __init__.py | 5 +- modules/convnext.py | 14 ++--- modules/text_grounding_net.py | 20 +++---- nodes/download_and_load_models.py | 72 +++++++++++++++++++++++++ nodes/load_instance_positionnet_node.py | 6 ++- requirements.txt | 1 + 6 files changed, 100 insertions(+), 18 deletions(-) create mode 100644 nodes/download_and_load_models.py diff --git a/__init__.py b/__init__.py index ec86e01..f61d71f 100644 --- a/__init__.py +++ b/__init__.py @@ -3,6 +3,7 @@ from .nodes.load_instance_scaleu_node import LoadInstanceScaleUNode from .nodes.load_instance_fusers_node import LoadInstanceFusersNode from .nodes.load_instance_positionnet_node import LoadInstancePositionNetNode from .nodes.instance_diffusion_tracking_prompt_node import InstanceDiffusionTrackingPromptNode +from .nodes.download_and_load_models import DownloadInstanceDiffusionModels NODE_CLASS_MAPPINGS = { @@ -11,6 +12,7 @@ NODE_CLASS_MAPPINGS = { "LoadInstancePositionNetModel": LoadInstancePositionNetNode, "LoadInstanceFusersNode": LoadInstanceFusersNode, "InstanceDiffusionTrackingPrompt": InstanceDiffusionTrackingPromptNode, + "DownloadInstanceDiffusionModels": DownloadInstanceDiffusionModels } NODE_DISPLAY_NAME_MAPPINGS = { @@ -18,5 +20,6 @@ NODE_DISPLAY_NAME_MAPPINGS = { "LoadInstancePositionNetModel": "Load Instance PositionNet Model", "LoadInstanceScaleUModel": "Load Instance ScaleU Model", "LoadInstanceFusersNode": "Load Instance Fusers Model", - "InstanceDiffusionTrackingPrompt": "Instance Diffusion Tracking Prompt" + "InstanceDiffusionTrackingPrompt": "Instance Diffusion Tracking Prompt", + "DownloadInstanceDiffusionModels": "(Down)Load Instance Diffusion Models" } diff --git a/modules/convnext.py b/modules/convnext.py index 9c3fe83..8771527 100644 --- a/modules/convnext.py +++ b/modules/convnext.py @@ -12,6 +12,8 @@ import torch.nn.functional as F from timm.models.layers import trunc_normal_, DropPath from timm.models.registry import register_model +import comfy.ops +ops = comfy.ops.manual_cast class Block(nn.Module): r""" ConvNeXt Block. There are two equivalent implementations: @@ -27,13 +29,13 @@ class Block(nn.Module): def __init__(self, dim, drop_path=0., layer_scale_init_value=1e-6): super().__init__() - self.dwconv = nn.Conv2d(dim, dim, kernel_size=7, + self.dwconv = ops.Conv2d(dim, dim, kernel_size=7, padding=3, groups=dim) # depthwise conv self.norm = LayerNorm(dim, eps=1e-6) # pointwise/1x1 convs, implemented with linear layers - self.pwconv1 = nn.Linear(dim, 4 * dim) + self.pwconv1 = ops.Linear(dim, 4 * dim) self.act = nn.GELU() - self.pwconv2 = nn.Linear(4 * dim, dim) + self.pwconv2 = ops.Linear(4 * dim, dim) self.gamma = nn.Parameter(layer_scale_init_value * torch.ones((dim)), requires_grad=True) if layer_scale_init_value > 0 else None self.drop_path = DropPath( @@ -79,14 +81,14 @@ class ConvNeXt(nn.Module): # stem and 3 intermediate downsampling conv layers self.downsample_layers = nn.ModuleList() stem = nn.Sequential( - nn.Conv2d(in_chans, dims[0], kernel_size=4, stride=4), + ops.Conv2d(in_chans, dims[0], kernel_size=4, stride=4), LayerNorm(dims[0], eps=1e-6, data_format="channels_first") ) self.downsample_layers.append(stem) for i in range(3): downsample_layer = nn.Sequential( LayerNorm(dims[i], eps=1e-6, data_format="channels_first"), - nn.Conv2d(dims[i], dims[i + 1], kernel_size=2, stride=2), + ops.Conv2d(dims[i], dims[i + 1], kernel_size=2, stride=2), ) self.downsample_layers.append(downsample_layer) @@ -104,7 +106,7 @@ class ConvNeXt(nn.Module): cur += depths[i] def _init_weights(self, m): - if isinstance(m, (nn.Conv2d, nn.Linear)): + if isinstance(m, (ops.Conv2d, ops.Linear)): trunc_normal_(m.weight, std=.02) nn.init.constant_(m.bias, 0) diff --git a/modules/text_grounding_net.py b/modules/text_grounding_net.py index b84d057..3302226 100644 --- a/modules/text_grounding_net.py +++ b/modules/text_grounding_net.py @@ -3,12 +3,14 @@ import torch.nn as nn from .util import FourierEmbedder from .convnext import convnext_tiny +import comfy.ops +ops = comfy.ops.manual_cast class UniFusion(nn.Module): def __init__(self, in_dim, out_dim, mid_dim=3072, fourier_freqs=8, train_add_boxes=True, train_add_points=True, train_add_scribbles=True, train_add_masks=True, test_drop_boxes=False, test_drop_points=False, test_drop_scribbles=True, test_drop_masks=False, - use_seperate_tokenizer=True): + use_seperate_tokenizer=True, use_segs=True): super().__init__() self.in_dim = in_dim self.out_dim = out_dim @@ -27,14 +29,14 @@ class UniFusion(nn.Module): # Use instance masks as additional model inputs for mask conditioned image generation #self.use_segs = True if self.add_masks else False - self.use_segs = False + self.use_segs = use_segs if self.use_segs: in_dim = 30 self.resize_input = 512 self.down_factor = 64 # determined by the convnext backbone # from num_sem to 3 channels - self.in_conv = nn.Conv2d(in_dim, 3, 3, 1, 1) + self.in_conv = ops.Conv2d(in_dim, 3, 3, 1, 1) self.convnext_tiny_backbone = convnext_tiny(pretrained=True) self.num_tokens = (self.resize_input // self.down_factor) ** 2 self.convnext_feature_dim = 3072 @@ -80,19 +82,19 @@ class UniFusion(nn.Module): for idx, input_dim_ in enumerate(input_dim_list): mid_dim = self.mid_dim self.linears_list.append(nn.Sequential( - nn.Linear(input_dim_, mid_dim), + ops.Linear(input_dim_, mid_dim), nn.SiLU(), - nn.Linear(mid_dim, mid_dim), + ops.Linear(mid_dim, mid_dim), nn.SiLU(), - nn.Linear(mid_dim, out_dim), + ops.Linear(mid_dim, out_dim), )) else: self.linears = nn.Sequential( - nn.Linear(input_dim, self.mid_dim), + ops.Linear(input_dim, self.mid_dim), nn.SiLU(), - nn.Linear(self.mid_dim, self.mid_dim), + ops.Linear(self.mid_dim, self.mid_dim), nn.SiLU(), - nn.Linear(self.mid_dim, out_dim), + ops.Linear(self.mid_dim, out_dim), ) self.null_positive_feature = torch.nn.Parameter( diff --git a/nodes/download_and_load_models.py b/nodes/download_and_load_models.py new file mode 100644 index 0000000..052e129 --- /dev/null +++ b/nodes/download_and_load_models.py @@ -0,0 +1,72 @@ +import os +import folder_paths +import comfy.utils +from .. import constants as constants +from ..model_helpers.prepare_positionnet import prepare_positionnet, get_positionnet_default_params +from ..model_helpers.prepare_scaleu import prepare_scaleu_nets +from ..model_helpers.prepare_fusers import prepare_fusers +from huggingface_hub import snapshot_download + +INSTANCE_FUSERS_DIR = "fuser_models" + +INSTANCE_SCALEU_DIR = "scaleu_models" + +class DownloadInstanceDiffusionModels: + @classmethod + def INPUT_TYPES(s): + return {"required": { + "use_segs": ("BOOLEAN", {"default": True}), + }} + + RETURN_TYPES = ("POSITIONNET", "FUSERS", "SCALEU", ) + FUNCTION = "load_model" + + CATEGORY = "instance/loaders" + + def load_model(self, use_segs: bool): + repo_id = "logtd/instance_diffusion" + instance_models_folder = os.path.join(folder_paths.models_dir, constants.INSTANCE_MODELS_DIR) + + models_to_download = [ + ("position_net", constants.INSTANCE_POSITIONNET_DIR, "position_net.ckpt"), + ("fusers", constants.INSTANCE_FUSERS_DIR, "fusers.ckpt"), + ("scaleu", constants.INSTANCE_SCALEU_DIR, "scaleu.ckpt") + ] + + for model_name, model_folder, model_file in models_to_download: + model_folder_path = os.path.join(instance_models_folder, model_folder) + model_file_path = os.path.join(model_folder_path, model_file) + + if not os.path.exists(model_file_path): + print(f"Selected model: {model_file_path} not found, downloading...") + allow_patterns = [f"*{model_name}*"] + snapshot_download(repo_id=repo_id, + allow_patterns=allow_patterns, + local_dir=model_folder_path, + local_dir_use_symlinks=False + ) + + positionnet_file = os.path.join(instance_models_folder, constants.INSTANCE_POSITIONNET_DIR, "position_net.ckpt") + fusers_file = os.path.join(instance_models_folder, constants.INSTANCE_FUSERS_DIR, "fusers.ckpt") + scaleu_file = os.path.join(instance_models_folder, constants.INSTANCE_SCALEU_DIR, "scaleu.ckpt") + + pos_checkpoint = comfy.utils.load_torch_file(positionnet_file, safe_load=True) + params = get_positionnet_default_params() + params["use_segs"] = use_segs + model = prepare_positionnet(pos_checkpoint, params) + positionnet = { + 'model': model, + } + + fusers_checkpoint = comfy.utils.load_torch_file(fusers_file, safe_load=True) + fusers_list = prepare_fusers(fusers_checkpoint) + fusers = { + 'model_list': fusers_list + } + scaleu_checkpoint = comfy.utils.load_torch_file(scaleu_file, safe_load=True) + scaleu_list = prepare_scaleu_nets(scaleu_checkpoint) + scaleu = { + 'model_list': scaleu_list + } + return (positionnet, fusers, scaleu) + diff --git a/nodes/load_instance_positionnet_node.py b/nodes/load_instance_positionnet_node.py index 5ee8b9d..7548607 100644 --- a/nodes/load_instance_positionnet_node.py +++ b/nodes/load_instance_positionnet_node.py @@ -8,17 +8,19 @@ class LoadInstancePositionNetNode: def INPUT_TYPES(s): return {"required": { "model_filename": (get_model_list(constants.INSTANCE_POSITIONNET_DIR),), + "use_segs": ("BOOLEAN", {"default": True}), }} - RETURN_TYPES = ("POSITIONNET",) + RETURN_TYPES = ("POSITIONNET", "FUSERS", "SCALEU",) FUNCTION = "load_model" CATEGORY = "instance/loaders" - def load_model(self, model_filename: str): + def load_model(self, model_filename: str, use_segs: bool): checkpoint = load_checkpoint( constants.INSTANCE_POSITIONNET_DIR, model_filename) params = get_positionnet_default_params() + params["use_segs"] = use_segs model = prepare_positionnet(checkpoint, params) positionnet = { 'model': model, diff --git a/requirements.txt b/requirements.txt index e69de29..b2642b3 100644 --- a/requirements.txt +++ b/requirements.txt @@ -0,0 +1 @@ +huggingface_hub \ No newline at end of file