Upload folder using huggingface_hub

README.md

@@ -1,3 +1,2 @@
----
-license: cc-by-nc-4.0
----
+# OneDiffusion
+

scheduler/scheduler_config.json

@@ -0,0 +1,12 @@
+{
+    "_class_name": "FlowMatchEulerDiscreteScheduler",
+    "_diffusers_version": "0.29.0.dev0",
+    "base_image_seq_len": 256,
+    "base_shift": 0.5,
+    "max_image_seq_len": 4096,
+    "max_shift": 1.15,
+    "num_train_timesteps": 1000,
+    "shift": 3.0,
+    "use_dynamic_shifting": true
+  }
+  

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/patrick/t5/t5-v1_1-xl",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 5120,
+  "d_kv": 64,
+  "d_model": 2048,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 32,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "vocab_size": 32128
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72be4ab4cb05720c91e72995ad26fb5e2785fc1648c80ad0561c45ce432447fc
+size 11399285345

tokenizer/special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}

tokenizer/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer/tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "name_or_path": "t5-small"}

transformer/config.json

@@ -0,0 +1,41 @@
+{
+  "_class_name": "NextDiT",
+  "_diffusers_version": "0.30.3",
+  "caption_channels": 2048,
+  "decay": 0.9999,
+  "depth": 16,
+  "ffn_dim_multiplier": null,
+  "forward_dtype": "bfloat16",
+  "hidden_size": 3840,
+  "in_channels": 16,
+  "input_size": [
+    1,
+    128,
+    128
+  ],
+  "inv_gamma": 1.0,
+  "min_decay": 0.0,
+  "model_max_length": 512,
+  "multiple_of": 256,
+  "norm_eps": 1e-05,
+  "norm_type": "rms",
+  "num_heads": 32,
+  "num_kv_heads": 8,
+  "optimization_step": 4000,
+  "param_dtype": "float32",
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "power": 0.6666666666666666,
+  "pred_sigma": false,
+  "qk_norm": true,
+  "remat_attention": "",
+  "remat_block": "",
+  "remat_mlp": "",
+  "rotary_max_length": 128,
+  "rotary_max_length_t": null,
+  "update_after_step": 0,
+  "use_ema_warmup": false
+}

transformer/diffusion_pytorch_model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17f844195518e70960b2bc50af3f7aae51ff2e0ba59ce5b6e6b0d922eb74ce29
+size 9951824992

transformer/diffusion_pytorch_model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c8953dc88e536b1bd8de4cdede32fac340a5145fe9b0c7cd6e2400431880333
+size 1249771672

transformer/diffusion_pytorch_model.safetensors.index.json

@@ -0,0 +1,389 @@
+{
+  "metadata": {
+    "total_size": 11201556736
+  },
+  "weight_map": {
+    "final_layer.adaLN_modulation.1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "final_layer.adaLN_modulation.1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "final_layer.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "final_layer.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.0.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.attention_y_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.0.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.attention_y_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.1.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.attention_y_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.10.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.attention_y_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.11.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.attention_y_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.12.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.attention_y_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.13.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.adaLN_modulation.1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.14.adaLN_modulation.1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.14.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.14.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.14.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.14.attention_y_norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.14.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.14.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.14.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.14.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.14.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.adaLN_modulation.1.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.adaLN_modulation.1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention.gate": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention.k_norm.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention.k_norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention.ky_norm.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention.ky_norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention.q_norm.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention.q_norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention.wk.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention.wk_y.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention.wo.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention.wq.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention.wv.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention.wv_y.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.attention_y_norm.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.feed_forward.w1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.feed_forward.w2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.feed_forward.w3.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.ffn_norm1.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.15.ffn_norm2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
+    "layers.2.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.attention_y_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.2.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.attention_y_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.3.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.attention_y_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.4.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.attention_y_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.5.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.attention_y_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.6.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.attention_y_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.7.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.attention_y_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.8.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.gate": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.k_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.k_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.ky_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.ky_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.q_norm.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.q_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.wk.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.wk_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.wo.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.wq.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.wv.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention.wv_y.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.attention_y_norm.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.feed_forward.w1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.feed_forward.w2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.feed_forward.w3.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.ffn_norm1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "layers.9.ffn_norm2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "t_embedder.mlp.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "t_embedder.mlp.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "t_embedder.mlp.2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "t_embedder.mlp.2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "x_embedder.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "x_embedder.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "y_embedder.0.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "y_embedder.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "y_embedder.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
+    "y_embedder.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors"
+  }
+}

vae/config.json

@@ -0,0 +1,36 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.29.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 16,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 1.5305,
+  "shift_factor": 0.0609,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": false,
+  "use_quant_conv": false
+}

vae/diffusion_pytorch_model.fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b67a279283625caee39d61eacb5324243848477b4eb535355eaaa8423d4e09
+size 167666654

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b67a279283625caee39d61eacb5324243848477b4eb535355eaaa8423d4e09
+size 167666654