Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+__assets__/banner.gif filter=lfs diff=lfs merge=lfs -text
+third_party/BFM_model_front.mat filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,35 @@
+---
+license: apache-2.0
+---
+
+# FaceAdapter Model Card
+
+<div align="center">
+
+[**Project Page**](https://faceadapter.github.io/face-adapter.github.io/) **|** [**Paper**](https://arxiv.org/pdf/2405.12970) **|** [**Code**](https://github.com/FaceAdapter/Face-Adapter) **|** [🤗 **Gradio demo**](https://huggingface.co/spaces/FaceAdapter/FaceAdapter)
+
+
+</div>
+
+## Introduction
+
+Face-Adapter is an efficient and effective face editing adapter for pre-trained diffusion models, specifically targeting face reenactment and swapping tasks. 
+
+
+<div  align="center">
+<img src='__assets__/banner.gif'>
+</div>
+
+
+## Usage
+
+You can directly download the model in this repository or download in python script:
+
+```python
+# Download a specific file
+from huggingface_hub import hf_hub_download
+hf_hub_download(repo_id="FaceAdapter/FaceAdapter", filename="controlnet/config.json", local_dir="./checkpoints")
+# Download all files 
+from huggingface_hub import snapshot_download
+snapshot_download(repo_id="FaceAdapter/FaceAdapter", local_dir="./checkpoints")
+```

controlnet/config.json

@@ -0,0 +1,52 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.26.0",
+  "_name_or_path": "exps/facedrive_faceswap_facelora128_ftclip/controlnet/",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "global_pool_conditions": false,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": 1,
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

controlnet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:804a9ada677cac97f12eb2651fe226ab4c92ab6d025c893482e4a29a19d0f609
+size 1445157120

net_id2token.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5167d894e592b94f518e4465da233397737047ee5cb8424a22bddec54029f9a7
+size 48184531

net_image2token.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ffcd587de77a34924da6e3532d83ec5e96fc8af8735355fd25e3debb750e96
+size 98717322

net_seg_res18.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041ab78a4f8f756cd7e93df0d2840d03162e46b9c463c144f7fdf3ee3e6c4233
+size 57429148

pretrained_unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.26.0",
+  "_name_or_path": "facelora",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

pretrained_unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d196563bfa563d70eca3357e8df5ab6242178f8990510699e5b81f87700ed7
+size 1719125992

third_party/79999_iter.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:468e13ca13a9b43cc0881a9f99083a430e9c0a38abd935431d1c28ee94b26567
+size 53289463

third_party/BFM_model_front.mat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f127eb18c3d022acbdbfcf1b6b353d01a6e01785d675a67cc31a3826a5be0f
+size 127170280

third_party/d3dfr_res50_nofc.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c54b90304a06c16b6813910c26faff1a907d4f8bd69a71ad4ecff43b41a090
+size 96449126

third_party/insightface_glint360k.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f631718e783448b41631e15073bdc622eaeef56509bbad4e5085f23bd32db83
+size 261223796

third_party/models/antelopev2/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

third_party/models/antelopev2/1k3d68.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df5c06b8a0c12e422b2ed8947b8869faa4105387f199c477af038aa01f9a45cc
+size 143607619

third_party/models/antelopev2/2d106det.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f001b856447c413801ef5c42091ed0cd516fcd21f2d6b79635b1e733a7109dbf
+size 5030888

third_party/models/antelopev2/README.md

@@ -0,0 +1,5 @@
+## Inference
+
+```bash 
+python inference.py
+```

third_party/models/antelopev2/genderage.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fde69b1c810857b88c64a335084f1c3fe8f01246c9a191b48c7bb756d6652fb
+size 1322532

third_party/models/antelopev2/glintr100.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fe1b5874b96c1025efdc8a9cf4152511384dcb1282c79290d5ed3241692297
+size 260694151

third_party/models/antelopev2/inference.py

@@ -0,0 +1,22 @@
+from resnet import get_model
+import torch
+from PIL import Image
+from torchvision.transforms.functional import pil_to_tensor
+
+
+model = get_model("r100", dropout=0.0, fp16=True, num_features=512).cuda()
+model.load_state_dict(torch.load("model.pt"))
+model.eval()
+img = pil_to_tensor(Image.open("test.jpg").resize((112,112))).permute(0, 1, 2).to("cuda", torch.float16).unsqueeze(dim = 0)
+embeddings = model(img)
+
+from insightface.app import FaceAnalysis
+import insightface 
+from huggingface_hub import snapshot_download
+snapshot_download('Warlord-K/resnet100', local_dir='models/antelopev2')
+app = FaceAnalysis(
+            name='antelopev2', root='.', providers=['CUDAExecutionProvider', 'CPUExecutionProvider']
+        )
+app.prepare(ctx_id=0, det_size=(640, 640))
+handler_ante = insightface.model_zoo.get_model('models/antelopev2/glintr100.onnx')
+handler_ante.prepare(ctx_id=0)

third_party/models/antelopev2/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2fe1b5874b96c1025efdc8a9cf4152511384dcb1282c79290d5ed3241692297
+size 260694151

third_party/models/antelopev2/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c1d9f2ca1d152743e8c9588aa2b888434b66848ad68f941c0c2cf4f884755f4
+size 261152502

third_party/models/antelopev2/resnet.py

@@ -0,0 +1,209 @@
+import torch
+from torch import nn
+from torch.utils.checkpoint import checkpoint
+
+__all__ = ['iresnet18', 'iresnet34', 'iresnet50', 'iresnet100', 'iresnet200']
+using_ckpt = False
+
+def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
+    """3x3 convolution with padding"""
+    return nn.Conv2d(in_planes,
+                     out_planes,
+                     kernel_size=3,
+                     stride=stride,
+                     padding=dilation,
+                     groups=groups,
+                     bias=False,
+                     dilation=dilation)
+
+
+def conv1x1(in_planes, out_planes, stride=1):
+    """1x1 convolution"""
+    return nn.Conv2d(in_planes,
+                     out_planes,
+                     kernel_size=1,
+                     stride=stride,
+                     bias=False)
+
+
+class IBasicBlock(nn.Module):
+    expansion = 1
+    def __init__(self, inplanes, planes, stride=1, downsample=None,
+                 groups=1, base_width=64, dilation=1):
+        super(IBasicBlock, self).__init__()
+        if groups != 1 or base_width != 64:
+            raise ValueError('BasicBlock only supports groups=1 and base_width=64')
+        if dilation > 1:
+            raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
+        self.bn1 = nn.BatchNorm2d(inplanes, eps=1e-05,)
+        self.conv1 = conv3x3(inplanes, planes)
+        self.bn2 = nn.BatchNorm2d(planes, eps=1e-05,)
+        self.prelu = nn.PReLU(planes)
+        self.conv2 = conv3x3(planes, planes, stride)
+        self.bn3 = nn.BatchNorm2d(planes, eps=1e-05,)
+        self.downsample = downsample
+        self.stride = stride
+
+    def forward_impl(self, x):
+        identity = x
+        out = self.bn1(x)
+        out = self.conv1(out)
+        out = self.bn2(out)
+        out = self.prelu(out)
+        out = self.conv2(out)
+        out = self.bn3(out)
+        if self.downsample is not None:
+            identity = self.downsample(x)
+        out += identity
+        return out        
+
+    def forward(self, x):
+        if self.training and using_ckpt:
+            return checkpoint(self.forward_impl, x)
+        else:
+            return self.forward_impl(x)
+
+
+class IResNet(nn.Module):
+    fc_scale = 7 * 7
+    def __init__(self,
+                 block, layers, dropout=0, num_features=512, zero_init_residual=False,
+                 groups=1, width_per_group=64, replace_stride_with_dilation=None, fp16=False):
+        super(IResNet, self).__init__()
+        self.extra_gflops = 0.0
+        self.fp16 = fp16
+        self.inplanes = 64
+        self.dilation = 1
+        if replace_stride_with_dilation is None:
+            replace_stride_with_dilation = [False, False, False]
+        if len(replace_stride_with_dilation) != 3:
+            raise ValueError("replace_stride_with_dilation should be None "
+                             "or a 3-element tuple, got {}".format(replace_stride_with_dilation))
+        self.groups = groups
+        self.base_width = width_per_group
+        self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=3, stride=1, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(self.inplanes, eps=1e-05)
+        self.prelu = nn.PReLU(self.inplanes)
+        self.layer1 = self._make_layer(block, 64, layers[0], stride=2)
+        self.layer2 = self._make_layer(block,
+                                       128,
+                                       layers[1],
+                                       stride=2,
+                                       dilate=replace_stride_with_dilation[0])
+        self.layer3 = self._make_layer(block,
+                                       256,
+                                       layers[2],
+                                       stride=2,
+                                       dilate=replace_stride_with_dilation[1])
+        self.layer4 = self._make_layer(block,
+                                       512,
+                                       layers[3],
+                                       stride=2,
+                                       dilate=replace_stride_with_dilation[2])
+        self.bn2 = nn.BatchNorm2d(512 * block.expansion, eps=1e-05,)
+        self.dropout = nn.Dropout(p=dropout, inplace=True)
+        self.fc = nn.Linear(512 * block.expansion * self.fc_scale, num_features)
+        self.features = nn.BatchNorm1d(num_features, eps=1e-05)
+        nn.init.constant_(self.features.weight, 1.0)
+        self.features.weight.requires_grad = False
+
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                nn.init.normal_(m.weight, 0, 0.1)
+            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
+                nn.init.constant_(m.weight, 1)
+                nn.init.constant_(m.bias, 0)
+
+        if zero_init_residual:
+            for m in self.modules():
+                if isinstance(m, IBasicBlock):
+                    nn.init.constant_(m.bn2.weight, 0)
+
+    def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
+        downsample = None
+        previous_dilation = self.dilation
+        if dilate:
+            self.dilation *= stride
+            stride = 1
+        if stride != 1 or self.inplanes != planes * block.expansion:
+            downsample = nn.Sequential(
+                conv1x1(self.inplanes, planes * block.expansion, stride),
+                nn.BatchNorm2d(planes * block.expansion, eps=1e-05, ),
+            )
+        layers = []
+        layers.append(
+            block(self.inplanes, planes, stride, downsample, self.groups,
+                  self.base_width, previous_dilation))
+        self.inplanes = planes * block.expansion
+        for _ in range(1, blocks):
+            layers.append(
+                block(self.inplanes,
+                      planes,
+                      groups=self.groups,
+                      base_width=self.base_width,
+                      dilation=self.dilation))
+
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        with torch.cuda.amp.autocast(self.fp16):
+            x = self.conv1(x)
+            x = self.bn1(x)
+            x = self.prelu(x)
+            x = self.layer1(x)
+            x = self.layer2(x)
+            x = self.layer3(x)
+            x = self.layer4(x)
+            x = self.bn2(x)
+            x = torch.flatten(x, 1)
+            x = self.dropout(x)
+        x = self.fc(x.float() if self.fp16 else x)
+        x = self.features(x)
+        return x
+
+
+def _iresnet(arch, block, layers, pretrained, progress, **kwargs):
+    model = IResNet(block, layers, **kwargs)
+    if pretrained:
+        raise ValueError()
+    return model
+
+
+def iresnet18(pretrained=False, progress=True, **kwargs):
+    return _iresnet('iresnet18', IBasicBlock, [2, 2, 2, 2], pretrained,
+                    progress, **kwargs)
+
+
+def iresnet34(pretrained=False, progress=True, **kwargs):
+    return _iresnet('iresnet34', IBasicBlock, [3, 4, 6, 3], pretrained,
+                    progress, **kwargs)
+
+
+def iresnet50(pretrained=False, progress=True, **kwargs):
+    return _iresnet('iresnet50', IBasicBlock, [3, 4, 14, 3], pretrained,
+                    progress, **kwargs)
+
+
+def iresnet100(pretrained=False, progress=True, **kwargs):
+    return _iresnet('iresnet100', IBasicBlock, [3, 13, 30, 3], pretrained,
+                    progress, **kwargs)
+
+
+def iresnet200(pretrained=False, progress=True, **kwargs):
+    return _iresnet('iresnet200', IBasicBlock, [6, 26, 60, 6], pretrained,
+                    progress, **kwargs)
+
+def get_model(name, **kwargs):
+    # resnet
+    if name == "r18":
+        return iresnet18(False, **kwargs)
+    elif name == "r34":
+        return iresnet34(False, **kwargs)
+    elif name == "r50":
+        return iresnet50(False, **kwargs)
+    elif name == "r100":
+        return iresnet100(False, **kwargs)
+    elif name == "r200":
+        return iresnet200(False, **kwargs)
+    else:
+        raise ValueError

third_party/models/antelopev2/scrfd_10g_bnkps.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5838f7fe053675b1c7a08b633df49e7af5495cee0493c7dcf6697200b85b5b91
+size 16923827

third_party/resnet18-5c106cde.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c106cde386e87d4033832f2996f5493238eda96ccf559d1d62760c4de0613f8
+size 46827520

vision_encoder/config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "exps/facedrive_faceswap_facelora128_ftclip/vision_encoder/",
+  "architectures": [
+    "CLIPVisionModel"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 32,
+  "patch_size": 14,
+  "projection_dim": 1024,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2"
+}

vision_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7445201beeb55edb415ed542c3ddfebd020e5ad0cce31930239a92313b7771
+size 2523246442