a2ee0201bf7701e699196a6a787b08a7a1b9d890dec9e0299541689f0b740139

.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
+text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text

model_index.json

@@ -0,0 +1,37 @@
+{
+  "_class_name": "NeuronStableDiffusionXLPipeline",
+  "_diffusers_version": "0.23.0",
+  "force_zeros_for_empty_prompt": true,
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "optimum",
+    "NeuronModelTextEncoder"
+  ],
+  "text_encoder_2": [
+    "optimum",
+    "NeuronModelTextEncoder"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "optimum",
+    "NeuronModelUnet"
+  ],
+  "vae_decoder": [
+    "optimum",
+    "NeuronModelVaeDecoder"
+  ],
+  "vae_encoder": [
+    "optimum",
+    "NeuronModelVaeEncoder"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.23.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "trained_betas": null,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--ThinkDiffusion--ThinkDiffusionXL/snapshots/e31c4693b7f87128fee02fa6b16c4dc2ada13721/text_encoder",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "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",
+  "neuron": {
+    "auto_cast": "all",
+    "auto_cast_type": "bf16",
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.12.54.0+f631c2365",
+    "disable_fallback": false,
+    "disable_fast_relayout": false,
+    "dynamic_batch_size": false,
+    "input_names": [
+      "input_ids"
+    ],
+    "model_type": "clip-text-model",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_names": [
+      "last_hidden_state",
+      "pooler_output",
+      "hidden_states"
+    ],
+    "static_batch_size": 1,
+    "static_num_beams": 1,
+    "static_sequence_length": 77
+  },
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_hidden_states": true,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "task": "feature-extraction",
+  "torch_dtype": "float16",
+  "torchscript": true,
+  "transformers_version": "4.36.2",
+  "vocab_size": 49408
+}

text_encoder/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f676fb689abc2fe7068c0617655ab6c5dcbf3c8929ea80db6fc6fc75398d27
+size 375884546

text_encoder_2/config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--ThinkDiffusion--ThinkDiffusionXL/snapshots/e31c4693b7f87128fee02fa6b16c4dc2ada13721/text_encoder_2",
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "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",
+  "neuron": {
+    "auto_cast": "all",
+    "auto_cast_type": "bf16",
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.12.54.0+f631c2365",
+    "disable_fallback": false,
+    "disable_fast_relayout": false,
+    "dynamic_batch_size": false,
+    "input_names": [
+      "input_ids"
+    ],
+    "model_type": "clip-text-model",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_names": [
+      "text_embeds",
+      "last_hidden_state",
+      "hidden_states"
+    ],
+    "static_batch_size": 1,
+    "static_num_beams": 1,
+    "static_sequence_length": 77
+  },
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "output_hidden_states": true,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "task": "feature-extraction",
+  "torch_dtype": "float16",
+  "torchscript": true,
+  "transformers_version": "4.36.2",
+  "vocab_size": 49408
+}