img2video_576_30f_action/model_index.json

{
  "_class_name": "StableVideoDiffusionPipelineV2",
  "_diffusers_version": "0.27.1",
  "feature_extractor": [
    "transformers",
    "CLIPImageProcessor"
  ],
  "image_encoder": [
    "transformers",
    "CLIPVisionModelWithProjection"
  ],
  "layout_encoder": [
    "src.encoder.unified_encoder",
    "EgoCondEncoder"
  ],
  "scheduler": [
    "diffusers",
    "EulerDiscreteScheduler"
  ],
  "unet": [
    "src.model.unet_spatial_temporal_condition_custom",
    "UNetSpatioTemporalConditionModelV2"
  ],
  "vae": [
    "diffusers",
    "AutoencoderKLTemporalDecoder"
  ]
}