init upload

image_encoder/config.json

@@ -0,0 +1,22 @@
+{
+  "architectures": [
+    "CLIPVisionModel"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 32,
+  "patch_size": 14,
+  "projection_dim": 1024,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0"
+}

image_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb46f477ef5e1859b659014aed6ca56cdc207c12cb7a0f9d61b4d80a1a7bb84
+size 2523128312

image_processor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": false,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

model_index.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "WanI2VPipeline",
+  "_diffusers_version": "0.33.0.dev0",
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModel"
+  ],
+  "image_processor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "scheduler": [
+    "diffusers",
+    "UniPCMultistepScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "UMT5EncoderModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "T5TokenizerFast"
+  ],
+  "transformer": [
+    "diffusers",
+    "WanTransformer3DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKLWan"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "UniPCMultistepScheduler",
+  "_diffusers_version": "0.33.0.dev0",
+  "beta_end": 0.02,
+  "beta_schedule": "linear",
+  "beta_start": 0.0001,
+  "disable_corrector": [],
+  "dynamic_thresholding_ratio": 0.995,
+  "final_sigmas_type": "zero",
+  "flow_shift": 7.0,
+  "lower_order_final": true,
+  "num_train_timesteps": 1000,
+  "predict_x0": true,
+  "prediction_type": "flow_prediction",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "solver_order": 2,
+  "solver_p": null,
+  "solver_type": "bh2",
+  "steps_offset": 0,
+  "thresholding": false,
+  "timestep_spacing": "linspace",
+  "trained_betas": null,
+  "use_beta_sigmas": false,
+  "use_exponential_sigmas": false,
+  "use_flow_sigmas": true,
+  "use_karras_sigmas": false
+}

transformer/config.json

@@ -0,0 +1,26 @@
+{
+  "_class_name": "WanTransformer3DModel",
+  "_diffusers_version": "0.33.0.dev0",
+  "add_img_emb": true,
+  "added_kv_proj_dim": 5120,
+  "attention_head_dim": 128,
+  "cross_attn_norm": true,
+  "eps": 1e-06,
+  "ffn_dim": 13824,
+  "freq_dim": 256,
+  "in_channels": 36,
+  "num_attention_heads": 40,
+  "num_layers": 40,
+  "out_channels": 16,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "qk_norm": true,
+  "text_dim": 4096,
+  "window_size": [
+    -1,
+    -1
+  ]
+}

transformer/diffusion_pytorch_model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457639497b204e838c0b5e7f5955e8b1b0f9f04213bd9853e40cd77771569685
+size 9952163512

transformer/diffusion_pytorch_model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eda5a7f06db0164b852b52fc56db9cb82c502e963f0e7d407af8e13bac31826b
+size 9797226656

transformer/diffusion_pytorch_model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4dfe5a12ac35c857fe307e91899d0f9c473551c2a828e80718f340489b27bd
+size 9975437232

transformer/diffusion_pytorch_model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744a014df498e5b579d34a12e9ea836b2cd9adf9e0ef77b4f7378ad762091573
+size 9975566544

transformer/diffusion_pytorch_model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b49e16fed3592ffc07d65503f39517f3190d8e52130418706ea1ba678f207050
+size 9902022768

transformer/diffusion_pytorch_model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d173bad73ebcdde9fe4efef487d1df9c993dfc3590b041e05e7806418479be52
+size 9902063944

transformer/diffusion_pytorch_model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b4173328f39217e177fe40cf94e509a213955aea842b086f3fd17e6c286832
+size 6075990120