Upload folder using huggingface_hub

checkpoint-epoch-10/config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "SD3Transformer2DModel",
+  "_diffusers_version": "0.37.0",
+  "_name_or_path": "stabilityai/stable-diffusion-3-medium-diffusers",
+  "attention_head_dim": 64,
+  "caption_projection_dim": 1536,
+  "dual_attention_layers": [],
+  "in_channels": 16,
+  "joint_attention_dim": 4096,
+  "num_attention_heads": 24,
+  "num_layers": 24,
+  "out_channels": 16,
+  "patch_size": 2,
+  "pooled_projection_dim": 2048,
+  "pos_embed_max_size": 192,
+  "qk_norm": null,
+  "sample_size": 128
+}

checkpoint-epoch-10/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80c25f3c7c73e3fac20822fed0c19983defff965c3805582b2dd4c39cb1d4e48
+size 4169982088

checkpoint-epoch-2/config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "SD3Transformer2DModel",
+  "_diffusers_version": "0.37.0",
+  "_name_or_path": "stabilityai/stable-diffusion-3-medium-diffusers",
+  "attention_head_dim": 64,
+  "caption_projection_dim": 1536,
+  "dual_attention_layers": [],
+  "in_channels": 16,
+  "joint_attention_dim": 4096,
+  "num_attention_heads": 24,
+  "num_layers": 24,
+  "out_channels": 16,
+  "patch_size": 2,
+  "pooled_projection_dim": 2048,
+  "pos_embed_max_size": 192,
+  "qk_norm": null,
+  "sample_size": 128
+}

checkpoint-epoch-2/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e853b971f8150a48bc42d67f18223da2a748f383014e49b07cf7a209c53882
+size 4169982088

checkpoint-epoch-4/config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "SD3Transformer2DModel",
+  "_diffusers_version": "0.37.0",
+  "_name_or_path": "stabilityai/stable-diffusion-3-medium-diffusers",
+  "attention_head_dim": 64,
+  "caption_projection_dim": 1536,
+  "dual_attention_layers": [],
+  "in_channels": 16,
+  "joint_attention_dim": 4096,
+  "num_attention_heads": 24,
+  "num_layers": 24,
+  "out_channels": 16,
+  "patch_size": 2,
+  "pooled_projection_dim": 2048,
+  "pos_embed_max_size": 192,
+  "qk_norm": null,
+  "sample_size": 128
+}

checkpoint-epoch-4/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6843ee54b600caeb5ede3381662a981ca66f2cfc893e11c8daff7bc759b934c4
+size 4169982088

checkpoint-epoch-6/config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "SD3Transformer2DModel",
+  "_diffusers_version": "0.37.0",
+  "_name_or_path": "stabilityai/stable-diffusion-3-medium-diffusers",
+  "attention_head_dim": 64,
+  "caption_projection_dim": 1536,
+  "dual_attention_layers": [],
+  "in_channels": 16,
+  "joint_attention_dim": 4096,
+  "num_attention_heads": 24,
+  "num_layers": 24,
+  "out_channels": 16,
+  "patch_size": 2,
+  "pooled_projection_dim": 2048,
+  "pos_embed_max_size": 192,
+  "qk_norm": null,
+  "sample_size": 128
+}

checkpoint-epoch-6/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc8727919494f6d7514af06af75f11d158a13577990eacb7417e4f9bcff277e
+size 4169982088

checkpoint-epoch-8/config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "SD3Transformer2DModel",
+  "_diffusers_version": "0.37.0",
+  "_name_or_path": "stabilityai/stable-diffusion-3-medium-diffusers",
+  "attention_head_dim": 64,
+  "caption_projection_dim": 1536,
+  "dual_attention_layers": [],
+  "in_channels": 16,
+  "joint_attention_dim": 4096,
+  "num_attention_heads": 24,
+  "num_layers": 24,
+  "out_channels": 16,
+  "patch_size": 2,
+  "pooled_projection_dim": 2048,
+  "pos_embed_max_size": 192,
+  "qk_norm": null,
+  "sample_size": 128
+}

checkpoint-epoch-8/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d06cb435a78131cd5e492bd1dbc8ec51ac4199e93047527c75a2b31ace668d2f
+size 4169982088

model_index.json

@@ -0,0 +1,49 @@
+{
+  "_class_name": "StableDiffusion3Pipeline",
+  "_diffusers_version": "0.37.0",
+  "_name_or_path": "stabilityai/stable-diffusion-3-medium-diffusers",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "image_encoder": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "text_encoder_3": [
+    "transformers",
+    "T5EncoderModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_3": [
+    "transformers",
+    "T5Tokenizer"
+  ],
+  "transformer": [
+    "diffusers",
+    "SD3Transformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.37.0",
+  "base_image_seq_len": 256,
+  "base_shift": 0.5,
+  "invert_sigmas": false,
+  "max_image_seq_len": 4096,
+  "max_shift": 1.15,
+  "num_train_timesteps": 1000,
+  "shift": 3.0,
+  "shift_terminal": null,
+  "stochastic_sampling": false,
+  "time_shift_type": "exponential",
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "transformers_version": "5.3.0",
+  "vocab_size": 49408
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e183d11db0c6b6282a4d9e0abb74125edc8692393e89ed8ee5571005f35cb1
+size 247323896

text_encoder_2/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "transformers_version": "5.3.0",
+  "vocab_size": 49408
+}

text_encoder_2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec310df2af79c318e24d20511b601a591ca8cd4f1fce1d8dff822a356bcdb1f4
+size 1389382176

text_encoder_3/config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "T5EncoderModel"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "dtype": "float16",
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_decoder": false,
+  "is_encoder_decoder": false,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "scale_decoder_outputs": false,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 32128
+}

text_encoder_3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0921715ce20abcba4d79360b9547e7ce57368d9182860cace910d812c50666f
+size 11537914408

tokenizer/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_2/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_3/tokenizer_config.json

@@ -0,0 +1,116 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "extra_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>"
+  ],
+  "is_local": true,
+  "legacy": true,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

transformer/config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "SD3Transformer2DModel",
+  "_diffusers_version": "0.37.0",
+  "_name_or_path": "stabilityai/stable-diffusion-3-medium-diffusers",
+  "attention_head_dim": 64,
+  "caption_projection_dim": 1536,
+  "dual_attention_layers": [],
+  "in_channels": 16,
+  "joint_attention_dim": 4096,
+  "num_attention_heads": 24,
+  "num_layers": 24,
+  "out_channels": 16,
+  "patch_size": 2,
+  "pooled_projection_dim": 2048,
+  "pos_embed_max_size": 192,
+  "qk_norm": null,
+  "sample_size": 128
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80c25f3c7c73e3fac20822fed0c19983defff965c3805582b2dd4c39cb1d4e48
+size 4169982088

vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.37.0",
+  "_name_or_path": "/root/.cache/huggingface/hub/models--stabilityai--stable-diffusion-3-medium-diffusers/snapshots/ea42f8cef0f178587cf766dc8129abd379c90671/vae",
+  "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,
+  "mid_block_add_attention": true,
+  "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.safetensors

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