Upload folder using huggingface_hub

handler.py

@@ -12,8 +12,8 @@ import torchvision
 
 import numpy as np
 
+from diffusers import AutoPipelineForText2Image
 
-from animatediff.pipelines.pipeline_animation import AnimationPipeline
 from animatediff.models.unet import UNet3DConditionModel
 from animatediff.pipelines.pipeline_animation import AnimationPipeline
 from animatediff.utils.util import save_videos_grid
@@ -23,7 +23,10 @@ from animatediff.utils.util import load_weights
 class EndpointHandler():
     def __init__(self, model_path: str = "models/StableDiffusion/", inference_config_path: str = "configs/inference/inference-v3.yaml", motion_module: str = "models/Motion_Module/mm_sd_v15.ckpt"):
         
-        inference_config = OmegaConf.load(inference_config_path)
+        # inference_config = OmegaConf.load(inference_config_path)
+        
+        inference_config = {'unet_additional_kwargs': {'unet_use_cross_frame_attention': False, 'unet_use_temporal_attention': False, 'use_motion_module': True, 'motion_module_resolutions': [1, 2, 4, 8], 'motion_module_mid_block': False, 'motion_module_decoder_only': False, 'motion_module_type': 'Vanilla', 'motion_module_kwargs': {'num_attention_heads': 8, 'num_transformer_block': 1, 'attention_block_types': ['Temporal_Self', 'Temporal_Self'], 'temporal_position_encoding': True, 'temporal_position_encoding_max_len': 24, 'temporal_attention_dim_div': 1}}, 'noise_scheduler_kwargs': {'DDIMScheduler': {'num_train_timesteps': 1000, 'beta_start': 0.00085, 'beta_end': 0.012, 'beta_schedule': 'linear', 'steps_offset': 1, 'clip_sample': False}, 'EulerAncestralDiscreteScheduler': {'num_train_timesteps': 1000, 'beta_start': 0.00085, 'beta_end': 0.012, 'beta_schedule': 'linear'}, 'KDPM2AncestralDiscreteScheduler': {'num_train_timesteps': 1000, 'beta_start': 0.00085, 'beta_end': 0.012, 'beta_schedule': 'linear'}}}
+        
         ### >>> create validation pipeline >>> ###
         tokenizer    = CLIPTokenizer.from_pretrained(model_path, subfolder="tokenizer")
         text_encoder = CLIPTextModel.from_pretrained(model_path, subfolder="text_encoder")
@@ -88,4 +91,4 @@ class EndpointHandler():
 # This function will be called during inference time.
 
 
-new_handler = EndpointHandler()
+# new_handler = EndpointHandler()