CogVideo/sat/configs/cogvideox_5b_i2v_lora.yaml

model:
  scale_factor: 0.7
  disable_first_stage_autocast: true
  latent_input: false
  noised_image_input: true
  noised_image_dropout: 0.05
  not_trainable_prefixes: ['all'] ## Using Lora
  log_keys:
    - txt

  denoiser_config:
    target: sgm.modules.diffusionmodules.denoiser.DiscreteDenoiser
    params:
      num_idx: 1000
      quantize_c_noise: False

      weighting_config:
        target: sgm.modules.diffusionmodules.denoiser_weighting.EpsWeighting
      scaling_config:
        target: sgm.modules.diffusionmodules.denoiser_scaling.VideoScaling
      discretization_config:
        target: sgm.modules.diffusionmodules.discretizer.ZeroSNRDDPMDiscretization
        params:
          shift_scale: 1.0 # different from cogvideox_2b_infer.yaml

  network_config:
    target: dit_video_concat.DiffusionTransformer
    params:
      time_embed_dim: 512
      elementwise_affine: True
      num_frames: 49
      time_compressed_rate: 4
      latent_width: 90
      latent_height: 60
      num_layers: 42
      patch_size: 2
      in_channels: 32
      out_channels: 16
      hidden_size: 3072
      adm_in_channels: 256
      num_attention_heads: 48

      transformer_args:
        checkpoint_activations: True
        vocab_size: 1
        max_sequence_length: 64
        layernorm_order: pre
        skip_init: false
        model_parallel_size: 1
        is_decoder: false

      modules:
        pos_embed_config:
          target: dit_video_concat.Rotary3DPositionEmbeddingMixin
          params:
            learnable_pos_embed: True
            hidden_size_head: 64
            text_length: 226

        lora_config:
          target: sat.model.finetune.lora2.LoraMixin
          params:
            r: 256

        patch_embed_config:
          target: dit_video_concat.ImagePatchEmbeddingMixin
          params:
            text_hidden_size: 4096

        adaln_layer_config:
          target: dit_video_concat.AdaLNMixin
          params:
            qk_ln: True

        final_layer_config:
          target: dit_video_concat.FinalLayerMixin

  conditioner_config:
    target: sgm.modules.GeneralConditioner
    params:
      emb_models:
          - is_trainable: false
            input_key: txt
            ucg_rate: 0.1
            target: sgm.modules.encoders.modules.FrozenT5Embedder
            params:
              model_dir: "t5-v1_1-xxl"
              max_length: 226

  first_stage_config:
    target: vae_modules.autoencoder.VideoAutoencoderInferenceWrapper
    params:
      cp_size: 1
      ckpt_path: "cogvideox-5b-i2v-sat/vae/3d-vae.pt"
      ignore_keys: [ 'loss' ]

      loss_config:
        target: torch.nn.Identity

      regularizer_config:
        target: vae_modules.regularizers.DiagonalGaussianRegularizer

      encoder_config:
        target: vae_modules.cp_enc_dec.ContextParallelEncoder3D
        params:
          double_z: true
          z_channels: 16
          resolution: 256
          in_channels: 3
          out_ch: 3
          ch: 128
          ch_mult: [ 1, 2, 2, 4 ]
          attn_resolutions: [ ]
          num_res_blocks: 3
          dropout: 0.0
          gather_norm: True

      decoder_config:
        target: vae_modules.cp_enc_dec.ContextParallelDecoder3D
        params:
          double_z: True
          z_channels: 16
          resolution: 256
          in_channels: 3
          out_ch: 3
          ch: 128
          ch_mult: [ 1, 2, 2, 4 ]
          attn_resolutions: [ ]
          num_res_blocks: 3
          dropout: 0.0
          gather_norm: True

  loss_fn_config:
    target: sgm.modules.diffusionmodules.loss.VideoDiffusionLoss
    params:
      fixed_frames: 0
      offset_noise_level: 0
      sigma_sampler_config:
        target: sgm.modules.diffusionmodules.sigma_sampling.DiscreteSampling
        params:
          uniform_sampling: True
          num_idx: 1000
          discretization_config:
            target: sgm.modules.diffusionmodules.discretizer.ZeroSNRDDPMDiscretization
            params:
              shift_scale: 1.0

  sampler_config:
    target: sgm.modules.diffusionmodules.sampling.VPSDEDPMPP2MSampler
    params:
      fixed_frames: 0
      num_steps: 50
      verbose: True

      discretization_config:
        target: sgm.modules.diffusionmodules.discretizer.ZeroSNRDDPMDiscretization
        params:
          shift_scale: 1.0

      guider_config:
        target: sgm.modules.diffusionmodules.guiders.DynamicCFG
        params:
          scale: 6
          exp: 5
          num_steps: 50