Initial Upload

README.md

@@ -0,0 +1,26 @@
+# Fluently v4 LCM - Onnx Olive DirectML Optimized 
+
+## Original Model
+https://huggingface.co/fluently/Fluently-v4-LCM
+
+## C# Inference Demo
+https://github.com/TensorStack-AI/OnnxStack
+
+```csharp
+// Create Pipeline
+var pipeline = LatentConsistencyPipeline.CreatePipeline("D:\\Models\\Fluently-v4-LCM-onnx");
+
+// Prompt
+var promptOptions = new PromptOptions
+{
+    Prompt = "Illustrate a cheerful barista preparing a cup of coffee behind the counter of a cozy cafe."
+};
+
+// Run pipeline
+var result = await pipeline.GenerateImageAsync(promptOptions);
+
+// Save Image Result
+await result.SaveAsync("Result.png");
+```
+## Inference Result
+![Intro Image](Sample.png)

controlnet/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffeda6aa8ea2af08f2291585693a78e94e360e4a4fc490b6bdffe63106e8892a
+size 1719495908

model_index.json

@@ -0,0 +1,37 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.27.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "image_encoder": [
+    null,
+    null
+  ],
+  "requires_safety_checker": true,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

model_template.json

@@ -0,0 +1,77 @@
+{
+  "Id": "AB13DC2A-7F4E-43B1-9BA3-85039D544D18",
+  "FileVersion": "1",
+  "Created": "2024-06-17T00:00:00",
+  "Name": "Fluently v4 LCM",
+  "ImageIcon": "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/Icon.png",
+  "Author": "fluently",
+  "Description": "Latent Consistency Model - This model combines multiple checkpoints and various LoRAs to deliver exceptional results. It focuses on producing high-quality eye rendering and correct anatomical details, while simplifying prompts for better outcomes. The model generates beautifully detailed faces and eyes without additional tools, and activates stunning artistic effects when needed. It excels at inpainting and outpainting, and is particularly adept at creating impressive Anime and Comic Book art.",
+  "Rank": 300,
+  "Group": "Online",
+  "Template": "LCM",
+  "Category": "StableDiffusion",
+  "StableDiffusionTemplate": {
+    "PipelineType": "LatentConsistency",
+    "ModelType": "Base",
+    "SampleSize": 512,
+    "TokenizerLength": 768,
+    "DiffuserTypes": [
+      "TextToImage",
+      "ImageToImage",
+      "ImageInpaintLegacy",
+      "ControlNet",
+      "ControlNetImage"
+    ],
+    "SchedulerDefaults": {
+      "SchedulerType": "LCM",
+      "Steps": 6,
+      "StepsMin": 1,
+      "StepsMax": 100,
+      "Guidance": 1,
+      "GuidanceMin": 0,
+      "GuidanceMax": 2,
+      "TimestepSpacing": "Linspace",
+      "BetaSchedule": "ScaledLinear",
+      "BetaStart": 0.00085,
+      "BetaEnd": 0.01,
+      "DisableNegativePrompt": true
+    }
+  },
+  "Precision": "F16",
+  "MemoryMin": 2.1,
+  "MemoryMax": 4.6,
+  "DownloadSize": 4.2,
+  "Website": "https://huggingface.co/fluently/Fluently-v4-LCM",
+  "Repository": "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx",
+  "RepositoryFiles": [
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/controlnet/model.onnx",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/controlnet/config.json",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/scheduler/scheduler_config.json",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/text_encoder/model.onnx",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/text_encoder/config.json",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/tokenizer/merges.txt",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/tokenizer/model.onnx",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/tokenizer/special_tokens_map.json",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/tokenizer/tokenizer_config.json",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/tokenizer/vocab.json",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/unet/model.onnx",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/unet/config.json",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/vae_decoder/model.onnx",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/vae_decoder/config.json",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/vae_encoder/model.onnx",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/vae_encoder/config.json",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/model_index.json",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/model_template.json",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/README.md"
+  ],
+  "PreviewImages": [
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/Sample.png",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/Sample2.png",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/Sample3.png",
+    "https://huggingface.co/TensorStack/Fluently-v4-LCM-onnx/resolve/main/Sample4.png"
+  ],
+  "Tags": [
+    "GPU",
+    "F16"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.27.0.dev0",
+  "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",
+  "rescale_betas_zero_snr": false,
+  "set_alpha_to_one": false,
+  "sigma_max": null,
+  "sigma_min": null,
+  "steps_offset": 1,
+  "timestep_spacing": "linspace",
+  "timestep_type": "discrete",
+  "trained_betas": null,
+  "use_karras_sigmas": false
+}

text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "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",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "vocab_size": 49408
+}

text_encoder/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc364c607b9efe000bde1d9395bee54c3c647ef2bdd32e0eae01ddc1f87bd0db
+size 246481009

tokenizer/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b7618c80a5bd8d1ee6fe92b28e7b72dde7aaa522963ff083f284501a9ec7df
+size 1683233

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|>"
+}

unet/config.json

@@ -0,0 +1,67 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.27.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": false
+}

unet/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf5a54b4481bac0083d6162a7535942b4c0811fea29c608b1ef4a53aed9e20d
+size 1719492909

vae_decoder/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.27.0.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": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae_decoder/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce3158522f3939ab69a62be36cc524a82676285361ab0bebf09b6f540a12483
+size 99039207

vae_encoder/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.27.0.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": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae_encoder/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d04393869dc0f12e75c022b55d0e30c9c9ace2ff9274dda513719d6cdb060d
+size 68391734