Upload 12 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "SanaPipeline",
+  "_diffusers_version": "0.32.1",
+  "scheduler": [
+    "diffusers",
+    "FlowMatchEulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "Gemma2Model"
+  ],
+  "tokenizer": [
+    "transformers",
+    "GemmaTokenizer"
+  ],
+  "transformer": [
+    "diffusers",
+    "SanaTransformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderDC"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,16 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.32.1",
+  "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": 7.0,
+  "shift_terminal": null,
+  "use_beta_sigmas": false,
+  "use_dynamic_shifting": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "Gemma2Model"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 16,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 8,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 224,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 256000
+}

text_encoder/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4b97a4752fe2b5752f57a719674799c95d1c6b1c6a6222a4f294c8a7f0c4e8
+size 8203696

tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
+size 34362873

tokenizer/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6969e64047744a44bb3abfb5c50f8de0f7ed8b571d5444426ef931f651d1a0ef
+size 4241111

tokenizer/tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

transformer/config.json

@@ -0,0 +1,21 @@
+{
+  "_class_name": "SanaTransformer2DModel",
+  "_diffusers_version": "0.32.1",
+  "attention_bias": false,
+  "attention_head_dim": 4,
+  "caption_channels": 8,
+  "cross_attention_dim": 8,
+  "cross_attention_head_dim": 4,
+  "dropout": 0.0,
+  "in_channels": 4,
+  "interpolation_scale": null,
+  "mlp_ratio": 2.5,
+  "norm_elementwise_affine": false,
+  "norm_eps": 1e-06,
+  "num_attention_heads": 2,
+  "num_cross_attention_heads": 2,
+  "num_layers": 2,
+  "out_channels": 4,
+  "patch_size": 2,
+  "sample_size": 32
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:290dbea496c321c14a6d6eff1e8700b98236e81ffddbc55257723cba98f1d3fe
+size 29504

vae/config.json

@@ -0,0 +1,48 @@
+{
+  "_class_name": "AutoencoderDC",
+  "_diffusers_version": "0.32.1",
+  "attention_head_dim": 4,
+  "decoder_act_fns": "silu",
+  "decoder_block_out_channels": [
+    8,
+    8
+  ],
+  "decoder_block_types": [
+    "ResBlock",
+    "EfficientViTBlock"
+  ],
+  "decoder_layers_per_block": [
+    1,
+    1
+  ],
+  "decoder_norm_types": "rms_norm",
+  "decoder_qkv_multiscales": [
+    [],
+    [
+      5
+    ]
+  ],
+  "downsample_block_type": "conv",
+  "encoder_block_out_channels": [
+    8,
+    8
+  ],
+  "encoder_block_types": [
+    "ResBlock",
+    "EfficientViTBlock"
+  ],
+  "encoder_layers_per_block": [
+    1,
+    1
+  ],
+  "encoder_qkv_multiscales": [
+    [],
+    [
+      5
+    ]
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "scaling_factor": 0.41407,
+  "upsample_block_type": "interpolate"
+}

vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec48485ff48bac9b212007be0398bf69fe296bda1b7538030636aaeacd463ad
+size 43900