Upload HunyuanVideoPipeline

tokenizer_2/tokenizer_config.json

@@ -23,7 +23,6 @@
   "do_lower_case": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
-  "extra_special_tokens": {},
   "max_length": 77,
   "model_max_length": 77,
   "pad_token": "<|endoftext|>",

transformer/config.json

@@ -12,12 +12,13 @@
   "out_channels": 16,
   "patch_size": 2,
   "patch_size_t": 1,
+  "pooled_projection_dim": 768,
   "qk_norm": "rms_norm",
-  "rope_dim_list": [
+  "rope_axes_dim": [
     16,
     56,
     56
   ],
-  "text_embed_dim": 4096,
-  "text_embed_dim_2": 768
+  "rope_theta": 256.0,
+  "text_embed_dim": 4096
 }

transformer/diffusion_pytorch_model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:260147e5816e920928beedf5bafddb308a3a9c943f560feffe41b6ae44380704
-size 9972080096
+oid sha256:f261f32347ca7cbb88e9d143d6316608c37ddfb5262d829bce63a74679a9a644
+size 9972080536

transformer/diffusion_pytorch_model.safetensors.index.json

@@ -3,10 +3,6 @@
     "total_size": 25642025088
   },
   "weight_map": {
-    "guidance_in.mlp.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "guidance_in.mlp.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "guidance_in.mlp.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "guidance_in.mlp.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "img_in.proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "img_in.proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "norm_out.linear.bias": "diffusion_pytorch_model-00003-of-00003.safetensors",
@@ -573,10 +569,18 @@
     "single_transformer_blocks.9.proj_mlp.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
     "single_transformer_blocks.9.proj_out.bias": "diffusion_pytorch_model-00002-of-00003.safetensors",
     "single_transformer_blocks.9.proj_out.weight": "diffusion_pytorch_model-00002-of-00003.safetensors",
-    "time_in.mlp.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "time_in.mlp.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "time_in.mlp.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "time_in.mlp.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_text_embed.guidance_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_text_embed.guidance_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_text_embed.guidance_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_text_embed.guidance_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_text_embed.text_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_text_embed.text_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_text_embed.text_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_text_embed.text_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_text_embed.timestep_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_text_embed.timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_text_embed.timestep_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "time_text_embed.timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "transformer_blocks.0.attn.add_k_proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "transformer_blocks.0.attn.add_k_proj.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "transformer_blocks.0.attn.add_q_proj.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
@@ -1217,18 +1221,16 @@
     "transformer_blocks.9.norm1.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "transformer_blocks.9.norm1_context.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "transformer_blocks.9.norm1_context.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "txt_in.c_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "txt_in.c_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "txt_in.c_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "txt_in.c_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "txt_in.input_embedder.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "txt_in.input_embedder.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "txt_in.t_embedder.mlp.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "txt_in.t_embedder.mlp.0.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "txt_in.t_embedder.mlp.2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "txt_in.t_embedder.mlp.2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "txt_in.token_refiner.refiner_blocks.0.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "txt_in.token_refiner.refiner_blocks.0.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.proj_in.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.proj_in.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.time_text_embed.text_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.time_text_embed.text_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.time_text_embed.text_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.time_text_embed.text_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.time_text_embed.timestep_embedder.linear_1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.time_text_embed.timestep_embedder.linear_1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.time_text_embed.timestep_embedder.linear_2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.time_text_embed.timestep_embedder.linear_2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "txt_in.token_refiner.refiner_blocks.0.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "txt_in.token_refiner.refiner_blocks.0.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "txt_in.token_refiner.refiner_blocks.0.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
@@ -1245,8 +1247,8 @@
     "txt_in.token_refiner.refiner_blocks.0.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "txt_in.token_refiner.refiner_blocks.0.norm2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "txt_in.token_refiner.refiner_blocks.0.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "txt_in.token_refiner.refiner_blocks.1.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "txt_in.token_refiner.refiner_blocks.1.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.token_refiner.refiner_blocks.0.norm_out.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.token_refiner.refiner_blocks.0.norm_out.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "txt_in.token_refiner.refiner_blocks.1.attn.to_k.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "txt_in.token_refiner.refiner_blocks.1.attn.to_k.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "txt_in.token_refiner.refiner_blocks.1.attn.to_out.0.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
@@ -1263,9 +1265,7 @@
     "txt_in.token_refiner.refiner_blocks.1.norm1.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "txt_in.token_refiner.refiner_blocks.1.norm2.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
     "txt_in.token_refiner.refiner_blocks.1.norm2.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "vector_in.in_layer.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "vector_in.in_layer.weight": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "vector_in.out_layer.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
-    "vector_in.out_layer.weight": "diffusion_pytorch_model-00001-of-00003.safetensors"
+    "txt_in.token_refiner.refiner_blocks.1.norm_out.linear.bias": "diffusion_pytorch_model-00001-of-00003.safetensors",
+    "txt_in.token_refiner.refiner_blocks.1.norm_out.linear.weight": "diffusion_pytorch_model-00001-of-00003.safetensors"
   }
 }