Upload 12 files

TextConditionerA/config.yaml

@@ -0,0 +1,22 @@
+exclude_from_checkpoint: false
+trainable: false
+sentence_config:
+  frozen: false
+  model: roberta-large
+  max_sentence_tokens: 77
+  adopt_n_layers: 0
+  adopt_layer_size: 2048
+  pool_type: eos
+  add_pooling_layer: true
+  hidden_dropout_prob: 0.1
+  attention_probs_dropout_prob: 0.1
+  finetune_n_layers: -1
+last_hidden_state: true
+use_shared_space: false
+normalize_shared_space: true
+freeze_clap: true
+lhs_index: -2
+remove_special_tokens: false
+eval_mode: true
+text_preprocessing: no_op
+shared_representation_size: 1024

TextConditionerA/weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f66e1877efd49e3198068ffac74d00a84df18e53189643373e2e777224856bb
+size 1425689504

TextConditionerV/config.yaml

@@ -0,0 +1,22 @@
+exclude_from_checkpoint: false
+trainable: false
+sentence_config:
+  frozen: false
+  model: roberta-large
+  max_sentence_tokens: 77
+  adopt_n_layers: 0
+  adopt_layer_size: 2048
+  pool_type: eos
+  add_pooling_layer: true
+  hidden_dropout_prob: 0.1
+  attention_probs_dropout_prob: 0.1
+  finetune_n_layers: -1
+last_hidden_state: true
+use_shared_space: false
+normalize_shared_space: true
+freeze_clap: true
+lhs_index: -2
+remove_special_tokens: false
+eval_mode: true
+text_preprocessing: no_op
+shared_representation_size: 1024

TextConditionerV/weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0dd912c322582cb95531de69cf1472c90752e468087a3b0fc461dea49975e80
+size 1425689504

Woosh-DFlow/config.yaml

@@ -0,0 +1,51 @@
+exclude_from_checkpoint: false
+trainable: true
+ldm:
+  exclude_from_checkpoint: false
+  trainable: true
+  model_type: LatentDiffusionModel
+  dit:
+    model_type: mmmssflux
+    rope_len_multiplier: 2
+    max_description_length: 77
+    max_seq_len: 501
+    dim: 1024
+    inter_dim: 4096
+    fixed_timestep_features: false
+    timestep_features_dim: 256
+    n_layers: 12
+    n_heads: 8
+    n_multimodal_layers: 6
+    qk_nope_head_dim: 16
+    qk_rope_head_dim: 112
+    qkv_head_dim: 128
+    n_memory_tokens_rope: 1
+    n_memory_tokens_description: 0
+    original_seq_len: 501
+    rope_theta: 10000.0
+    rope_factor: 40.0
+    beta_fast: 32
+    beta_slow: 1
+    io_channels: 128
+    cond_token_dim: 1024
+    adaln_last_layer: true
+    adaln_last_layer_nomod: false
+    non_checkpoint_layers: 14
+    mask_out_before: -1
+    estimate_logvar: true
+    no_description_mask: true
+    symmetric_attention_init: false
+    patch_size: 1
+    num_sinks: 0
+    mlp_act: gelu
+  conditioners:
+    text:
+      exclude_from_checkpoint: true
+      trainable: false
+      path: D:/ComfyUI_windows_portable_nvidia/ComfyUI_windows_portable_nvidia_cu128/ComfyUI_windows_portable/ComfyUI/models/woosh/TextConditionerA
+  autoencoder:
+    exclude_from_checkpoint: true
+    trainable: false
+    path: D:/ComfyUI_windows_portable_nvidia/ComfyUI_windows_portable_nvidia_cu128/ComfyUI_windows_portable/ComfyUI/models/woosh/Woosh-AE
+  sigma_data: 1.0
+  pred_type: v_pred

Woosh-DFlow/weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fc4a2220fa4ba54e01611afe58e061854a58ad559eb56de2cca39112f7c8ef
+size 1378890620

Woosh-DVFlow-8s/config.yaml

@@ -0,0 +1,64 @@
+exclude_from_checkpoint: false
+trainable: true
+pretrained_model_type: videokontext
+ldm:
+  exclude_from_checkpoint: false
+  trainable: true
+  model_type: VideoKontextLDM
+  ldm:
+    exclude_from_checkpoint: false
+    trainable: true
+    dit:
+      model_type: mmmssflux
+      max_description_length: 77
+      max_seq_len: 501
+      rope_len_multiplier: 2
+      dim: 1024
+      inter_dim: 4096
+      fixed_timestep_features: false
+      timestep_features_dim: 256
+      n_layers: 12
+      n_heads: 8
+      n_multimodal_layers: 6
+      qk_nope_head_dim: 16
+      qk_rope_head_dim: 112
+      qkv_head_dim: 128
+      n_memory_tokens_rope: 1
+      n_memory_tokens_description: 0
+      original_seq_len: 501
+      rope_theta: 10000.0
+      rope_factor: 40.0
+      beta_fast: 32
+      beta_slow: 1
+      io_channels: 128
+      cond_token_dim: 1024
+      adaln_last_layer: true
+      adaln_last_layer_nomod: false
+      non_checkpoint_layers: 14
+      mask_out_before: -1
+      estimate_logvar: true
+      no_description_mask: true
+      symmetric_attention_init: false
+      patch_size: 1
+      num_sinks: 0
+      mlp_act: gelu
+    conditioners:
+      text:
+        exclude_from_checkpoint: true
+        trainable: false
+        path: checkpoints/TextConditionerV
+    autoencoder:
+      exclude_from_checkpoint: true
+      trainable: false
+      path: checkpoints/Woosh-AE
+    sigma_data: 1.0
+    pred_type: v_pred
+  audio_fps: 100
+  video_fps: 24
+  embed_dim: 768
+  embed_key: synch_out
+  pts_seconds_key: synch_pts_seconds
+  non_checkpoint_layers: 14
+  n_layers_encoder: 0
+  trainable_no_cond: false
+  use_batch_mask: true

Woosh-DVFlow-8s/weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c87b796798fd96a4a3b1deeb70ccd05c6dc782fe546b622ce1368a05e441cd30
+size 1684261500

Woosh-Flow/config.yaml

@@ -0,0 +1,48 @@
+exclude_from_checkpoint: false
+trainable: true
+model_type: LatentDiffusionModel
+dit:
+  model_type: mmmssflux
+  rope_len_multiplier: 2
+  max_description_length: 77
+  max_seq_len: 501
+  dim: 1024
+  inter_dim: 4096
+  fixed_timestep_features: false
+  timestep_features_dim: 256
+  n_layers: 12
+  n_heads: 8
+  n_multimodal_layers: 6
+  qk_nope_head_dim: 16
+  qk_rope_head_dim: 112
+  qkv_head_dim: 128
+  n_memory_tokens_rope: 1
+  n_memory_tokens_description: 0
+  original_seq_len: 501
+  rope_theta: 10000.0
+  rope_factor: 40.0
+  beta_fast: 32
+  beta_slow: 1
+  io_channels: 128
+  cond_token_dim: 1024
+  adaln_last_layer: true
+  adaln_last_layer_nomod: false
+  non_checkpoint_layers: 14
+  mask_out_before: -1
+  estimate_logvar: true
+  no_description_mask: true
+  symmetric_attention_init: false
+  patch_size: 1
+  num_sinks: 0
+  mlp_act: gelu
+conditioners:
+  text:
+    exclude_from_checkpoint: true
+    trainable: false
+    path: D:/ComfyUI_windows_portable_nvidia/ComfyUI_windows_portable_nvidia_cu128/ComfyUI_windows_portable/ComfyUI/models/woosh/TextConditionerA
+autoencoder:
+  exclude_from_checkpoint: true
+  trainable: false
+  path: D:/ComfyUI_windows_portable_nvidia/ComfyUI_windows_portable_nvidia_cu128/ComfyUI_windows_portable/ComfyUI/models/woosh/Woosh-AE
+sigma_data: 1.0
+pred_type: v_pred

Woosh-Flow/weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e2eafa2f9063934859888a2edd25ad4485f82dca4caaa7720f98d832f7ca39b
+size 1348979404

Woosh-VFlow-8s/config.yaml

@@ -0,0 +1,60 @@
+exclude_from_checkpoint: false
+trainable: true
+model_type: VideoKontextLDM
+ldm:
+  exclude_from_checkpoint: false
+  trainable: true
+  dit:
+    model_type: mmmssflux
+    max_description_length: 77
+    max_seq_len: 501
+    rope_len_multiplier: 2
+    dim: 1024
+    inter_dim: 4096
+    fixed_timestep_features: false
+    timestep_features_dim: 256
+    n_layers: 12
+    n_heads: 8
+    n_multimodal_layers: 6
+    qk_nope_head_dim: 16
+    qk_rope_head_dim: 112
+    qkv_head_dim: 128
+    n_memory_tokens_rope: 1
+    n_memory_tokens_description: 0
+    original_seq_len: 501
+    rope_theta: 10000.0
+    rope_factor: 40.0
+    beta_fast: 32
+    beta_slow: 1
+    io_channels: 128
+    cond_token_dim: 1024
+    adaln_last_layer: true
+    adaln_last_layer_nomod: false
+    non_checkpoint_layers: 14
+    mask_out_before: -1
+    estimate_logvar: true
+    no_description_mask: true
+    symmetric_attention_init: false
+    patch_size: 1
+    num_sinks: 0
+    mlp_act: gelu
+  conditioners:
+    text:
+      exclude_from_checkpoint: true
+      trainable: false
+      path: D:/ComfyUI_windows_portable_nvidia/ComfyUI_windows_portable_nvidia_cu128/ComfyUI_windows_portable/ComfyUI/models/woosh/TextConditionerV
+  autoencoder:
+    exclude_from_checkpoint: true
+    trainable: false
+    path: D:/ComfyUI_windows_portable_nvidia/ComfyUI_windows_portable_nvidia_cu128/ComfyUI_windows_portable/ComfyUI/models/woosh/Woosh-AE
+  sigma_data: 1.0
+  pred_type: v_pred
+audio_fps: 100
+video_fps: 24
+embed_dim: 768
+embed_key: synch_out
+pts_seconds_key: synch_pts_seconds
+non_checkpoint_layers: 14
+n_layers_encoder: 0
+trainable_no_cond: false
+use_batch_mask: true

Woosh-VFlow-8s/weights.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2e7639e830060e532c955d4b4dc23869c8574605267846fa326c28730fcc7d
+size 1654350276