Upload folder using huggingface_hub

model_index.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "WanPipeline",
   "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "Wan-AI/Wan2.1-T2V-1.3B-Diffusers",
   "scheduler": [
     "diffusers",
     "FlowMatchEulerDiscreteScheduler"

scheduler/scheduler_config.json

@@ -1,6 +1,8 @@
 {
-  "_class_name": "UniPCMultistepScheduler",
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
   "_diffusers_version": "0.33.0.dev0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
   "beta_end": 0.02,
   "beta_schedule": "linear",
   "beta_start": 0.0001,
@@ -8,20 +10,27 @@
   "dynamic_thresholding_ratio": 0.995,
   "final_sigmas_type": "zero",
   "flow_shift": 3.0,
+  "invert_sigmas": false,
   "lower_order_final": true,
+  "max_image_seq_len": 4096,
+  "max_shift": 1.15,
   "num_train_timesteps": 1000,
   "predict_x0": true,
   "prediction_type": "flow_prediction",
   "rescale_betas_zero_snr": false,
   "sample_max_value": 1.0,
+  "shift": 1.0,
+  "shift_terminal": null,
   "solver_order": 2,
   "solver_p": null,
   "solver_type": "bh2",
   "steps_offset": 0,
   "thresholding": false,
+  "time_shift_type": "exponential",
   "timestep_spacing": "linspace",
   "trained_betas": null,
   "use_beta_sigmas": false,
+  "use_dynamic_shifting": false,
   "use_exponential_sigmas": false,
   "use_flow_sigmas": true,
   "use_karras_sigmas": false

text_encoder/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/umt5-xxl",
+  "_name_or_path": "/fsx/sayak/.cache/models--Wan-AI--Wan2.1-T2V-1.3B-Diffusers/snapshots/db5905750367e63c271ae4ea34e6ebfd71fba443/text_encoder",
   "architectures": [
     "UMT5EncoderModel"
   ],
@@ -27,8 +27,8 @@
   "scalable_attention": true,
   "tie_word_embeddings": false,
   "tokenizer_class": "T5Tokenizer",
-  "torch_dtype": "float32",
-  "transformers_version": "4.48.0.dev0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.0",
   "use_cache": true,
   "vocab_size": 256384
 }

text_encoder/model.fp16-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b6e021f76fd58d6c25890e72196f5bcc2e50f02f7b648bc77ac172e36b8add0
+size 4986109632

text_encoder/model.fp16-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:410153ea1a0b6193c5bfc7f8776834a420e11c9ac9ffe6b49b303e8f388e2cbd
+size 4932731960

text_encoder/model.fp16-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb2a2e5c23a6dca2db97e0eab7b02b868336890ea022e80cfbf8a07935c09e0
+size 3456275440

text_encoder/model.safetensors.index.fp16.json

@@ -0,0 +1,249 @@
+{
+  "metadata": {
+    "total_size": 13375086592
+  },
+  "weight_map": {
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.10.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.11.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.12.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.13.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.14.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.15.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.16.layer.1.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.17.layer.0.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.17.layer.1.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.18.layer.0.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.18.layer.1.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.19.layer.0.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.19.layer.1.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.20.layer.0.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.20.layer.1.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.0.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.21.layer.1.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.0.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.22.layer.1.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.0.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.23.layer.1.layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.layer_norm.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "model.fp16-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.6.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.6.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.7.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.7.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.8.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.8.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.relative_attention_bias.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.9.layer.0.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.block.9.layer.1.layer_norm.weight": "model.fp16-00002-of-00003.safetensors",
+    "encoder.final_layer_norm.weight": "model.fp16-00003-of-00003.safetensors",
+    "shared.weight": "model.fp16-00001-of-00003.safetensors"
+  }
+}

tokenizer/tokenizer_config.json

@@ -1,4 +1,5 @@
 {
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<pad>",

transformer/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "WanTransformer3DModel",
   "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "/fsx/sayak/.cache/models--Wan-AI--Wan2.1-T2V-1.3B-Diffusers/snapshots/db5905750367e63c271ae4ea34e6ebfd71fba443/transformer",
   "added_kv_proj_dim": null,
   "attention_head_dim": 128,
   "cross_attn_norm": true,

transformer/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26331bbdd5cce5e913d5f5d9cb09826189557ef7137fe23a4d33ee2b3346d36
+size 2844330912

vae/config.json

@@ -1,6 +1,7 @@
 {
   "_class_name": "AutoencoderKLWan",
   "_diffusers_version": "0.33.0.dev0",
+  "_name_or_path": "/fsx/sayak/.cache/models--Wan-AI--Wan2.1-T2V-1.3B-Diffusers/snapshots/db5905750367e63c271ae4ea34e6ebfd71fba443/vae",
   "attn_scales": [],
   "base_dim": 96,
   "dim_mult": [

vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b96fa07bac5d2ec749cc74593c0c1ffce88db2c4fd8652009fe8e6a9cd15b703
+size 253806774