load safetensor locally

checkpoints/config.json

@@ -0,0 +1,57 @@
+{
+  "_class_name": "ControlNetModel",
+  "_diffusers_version": "0.21.2",
+  "_name_or_path": "/mnt/nj-aigc/usr/guiwan/workspace/diffusion_output/face_xl_ipc_v4_2_XiezhenAnimeForeigner/checkpoint-150000/ControlNetModel",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 2048,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "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,
+  "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": 2816,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": [
+    1,
+    2,
+    10
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

checkpoints/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8127be9f174101ebdafee9964d856b49b634435cf6daa396d3f593cf0bbbb05
+size 2502139136

checkpoints/ip-adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b3618e36d803784166660520098089a81388e61a93ef8002aa79a5b1c546e1
+size 1691134141

depth_anything/dpt.py

@@ -146,7 +146,7 @@ class DPT_DINOv2(nn.Module):
         if localhub:
             self.pretrained = torch.hub.load('../torchhub/facebookresearch_dinov2_main', 'dinov2_{:}14'.format(encoder), source='local', pretrained=False)
         else:
-            self.pretrained = torch.hub.load('../facebookresearch/dinov2', 'dinov2_{:}14'.format(encoder))
+            self.pretrained = torch.hub.load('facebookresearch/dinov2', 'dinov2_{:}14'.format(encoder))
         
         dim = self.pretrained.blocks[0].attn.qkv.in_features
         

handler.py

@@ -32,7 +32,6 @@ from depth_anything.util.transform import Resize, NormalizeImage, PrepareForNet
 from insightface.app import FaceAnalysis
 from pipeline_stable_diffusion_xl_instantid_full import StableDiffusionXLInstantIDPipeline, draw_kps
 from controlnet_aux import OpenposeDetector
-from huggingface_hub import hf_hub_download
 
 
 # end_test
@@ -45,14 +44,6 @@ dtype = torch.float16 if str(device).__contains__("cuda") else torch.float32
 
 class EndpointHandler():
     def __init__(self, model_dir):
-        hf_hub_download(repo_id="InstantX/InstantID", filename="ControlNetModel/config.json", local_dir="./checkpoints")
-        hf_hub_download(
-            repo_id="InstantX/InstantID",
-            filename="ControlNetModel/diffusion_pytorch_model.safetensors",
-            local_dir="./checkpoints",
-        )
-        hf_hub_download(repo_id="InstantX/InstantID", filename="ip-adapter.bin", local_dir="./checkpoints")
-
         print("Model dir: ", model_dir)
         face_adapter = f"./checkpoints/ip-adapter.bin"
         controlnet_path = f"./checkpoints/ControlNetModel"

requirements.txt

@@ -8,7 +8,6 @@ einops
 onnxruntime-gpu
 spaces==0.19.4
 omegaconf
-huggingface-hub==0.20.2
 opencv-python
 insightface
 gradio