Initial Upload

.gitattributes

@@ -33,3 +33,12 @@ 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
+Sample.png filter=lfs diff=lfs merge=lfs -text
+Sample2.png filter=lfs diff=lfs merge=lfs -text
+Sample3.png filter=lfs diff=lfs merge=lfs -text
+Sample4.png filter=lfs diff=lfs merge=lfs -text
+text_encoder_2/model.onnx.data filter=lfs diff=lfs merge=lfs -text
+text_encoder/model.onnx.data filter=lfs diff=lfs merge=lfs -text
+unet/model.onnx.data filter=lfs diff=lfs merge=lfs -text
+vae_decoder/model.onnx.data filter=lfs diff=lfs merge=lfs -text
+vae_encoder/model.onnx.data filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,30 @@
+# Stable-Diffusion 3 Lite
+
+## Original Model
+https://huggingface.co/stabilityai/stable-diffusion-3-medium
+### This conversion does not include the T5 models so is defined as "lite" not "medium"
+
+## C# Inference Demo
+https://github.com/TensorStack-AI/OnnxStack
+
+
+
+
+```csharp
+// Create Pipeline
+var pipeline = StableDiffusion3Pipeline.CreatePipeline("D:\\Models\\stable-diffusion-3-lite-onnx");
+
+// Prompt
+var promptOptions = new PromptOptions
+{
+    Prompt = "A cat holding a sign that says OnnxStack Stable Diffusion 3"
+};
+
+// Run pipeline
+var result = await pipeline.GenerateImageAsync(promptOptions);
+
+// Save Image Result
+await result.SaveAsync("Result.png");
+```
+## Inference Result
+![Intro Image](Sample.png)

model_index.json

@@ -0,0 +1,40 @@
+{
+  "_class_name": "StableDiffusion3Pipeline",
+  "_diffusers_version": "0.29.0.dev0",
+  "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",
+    "T5TokenizerFast"
+  ],
+  "transformer": [
+    "diffusers",
+    "SD3Transformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,6 @@
+{
+  "_class_name": "FlowMatchEulerDiscreteScheduler",
+  "_diffusers_version": "0.29.0.dev0",
+  "num_train_timesteps": 1000,
+  "shift": 3.0
+}

text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "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",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "vocab_size": 49408
+}

text_encoder/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa553e25a5b293966fd831fbd69f3a391acd59be04b85c416330809e4b07233
+size 313594

text_encoder/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2015263f98ae9f6e0ea233756bd5ea51ddb1f36ec6a2dd862e59d82611d1db7
+size 246120960

text_encoder_2/config.json

@@ -0,0 +1,24 @@
+{
+  "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",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "vocab_size": 49408
+}

text_encoder_2/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ab7cb4e45259a817da89a220f8e0653efdbc2c3c4574294dc25baea9993b3b7
+size 844646

text_encoder_2/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9ebbe8113df16739ba900f349dd81c32365a78c1d416cc0598b5705eedf4ec
+size 1389319680

tokenizer/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f1c80c1b99a57f9b952a2f6727dd833edebdbbb55e9be075bb772ba7797aa0
+size 1584928

tokenizer/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_2/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9f1c80c1b99a57f9b952a2f6727dd833edebdbbb55e9be075bb772ba7797aa0
+size 1584928

tokenizer_2/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "!",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_2/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

unet/config.json

@@ -0,0 +1,15 @@
+{
+  "_class_name": "SD3Transformer2DModel",
+  "_diffusers_version": "0.29.0.dev0",
+  "attention_head_dim": 64,
+  "caption_projection_dim": 1536,
+  "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,
+  "sample_size": 128
+}

unet/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1a87379c5a58f21e4feec4fc2b02fcb2c36d5de186e6454f0dea8e447547295
+size 1829471

unet/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428201c4e626c8fa723d075ff12aa614cffee5bfa8e764ebe3f585c3cd924ec2
+size 4169902080

vae_decoder/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_decoder/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9299db050be394467df9ad6b85404029299adc053a62c8d99c816d1fcc88129
+size 134446

vae_decoder/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f864ce1c3dc17572e7bb5c71f527ab53489045aaefd35b95fe628f2bbd7555b
+size 99075840

vae_encoder/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_encoder/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c755832857f062e04a041440d4e5479d2c2fb9280161bf0b34c8da4579bcb7
+size 118617

vae_encoder/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eaa49776fea993b99b5b44ceb0ab166e632bc4c4a86ceb8ef90f918792142fe
+size 68537088