{ "_class_name": "UNetSpatioTemporalConditionModel", "_diffusers_version": "0.25.1", "_name_or_path": "/data/home/chenhoujiang/.cache/huggingface/hub/models--stabilityai--stable-video-diffusion-img2vid-xt/snapshots/61ebd32cbcf4cb7cbb1422395234e59f1d4adae1/unet", "addition_time_embed_dim": 256, "block_out_channels": [ 320, 640, 1280, 1280 ], "cross_attention_dim": 1024, "down_block_types": [ "CrossAttnDownBlockSpatioTemporal", "CrossAttnDownBlockSpatioTemporal", "CrossAttnDownBlockSpatioTemporal", "DownBlockSpatioTemporal" ], "in_channels": 8, "layers_per_block": 2, "num_attention_heads": [ 5, 10, 20, 20 ], "num_frames": 25, "out_channels": 4, "projection_class_embeddings_input_dim": 768, "sample_size": 96, "transformer_layers_per_block": 1, "up_block_types": [ "UpBlockSpatioTemporal", "CrossAttnUpBlockSpatioTemporal", "CrossAttnUpBlockSpatioTemporal", "CrossAttnUpBlockSpatioTemporal" ] }