Initial Upload

.gitattributes

@@ -33,3 +33,10 @@ 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
+controlnet/model.onnx.data filter=lfs diff=lfs merge=lfs -text
+Icon.png 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
+unet/model.onnx.data filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,26 @@
+# Midgard Pony v3 - Onnx Olive DirectML Optimized 
+
+## Original Model
+https://civitai.com/models/470287?modelVersionId=561310
+
+## C# Inference Demo
+https://github.com/TensorStack-AI/OnnxStack
+
+```csharp
+// Create Pipeline
+var pipeline = StableDiffusionXLPipeline.CreatePipeline("D:\\Models\\MidgardPony-XL");
+
+// Prompt
+var promptOptions = new PromptOptions
+{
+    Prompt = "Craft an image of a gallant furry prince, with a charming smile and a sword at his side, ready to embark on a quest"
+};
+
+// Run pipeline
+var result = await pipeline.GenerateImageAsync(promptOptions);
+
+// Save Image Result
+await result.SaveAsync("Result.png");
+```
+## Inference Result
+![Intro Image](Sample.png)

controlnet/config.json

@@ -0,0 +1,72 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.29.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "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": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 128,
+  "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,
+    2,
+    10
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

controlnet/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c5ca20f6a883406ea4d3a54175d3084d1ea4a2fc8fa0c8deeab658c9f59a07c
+size 1244445

controlnet/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1ce7d1b7e4322e9a303a9e596285ec714daa985cb2e3f7d111e7756afb2401a
+size 5134903040

model_index.json

@@ -0,0 +1,41 @@
+{
+  "_class_name": "StableDiffusionXLPipeline",
+  "_diffusers_version": "0.29.0.dev0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "force_zeros_for_empty_prompt": true,
+  "image_encoder": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

model_template.json

@@ -0,0 +1,83 @@
+{
+    "Id": "FEF994D2-7156-4BB7-9CC6-C8DFD449D26A",
+    "FileVersion": "1",
+    "Created": "2024-06-016T00:00:00",
+    "Name": "Midgard Pony XL",
+    "ImageIcon": "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/Icon.png",
+    "Author": "freek22",
+    "Description": "This is a subvariant based on my General Use model Midgard made for Animals/Creatures and Furry Art but can do way more\nMidgard, in Norse mythology, the Middle Earth, the abode of mankind, made from the body of the first created being, the giant Aurgelmir (Ymir). According to legend, the gods killed Aurgelmir, rolled his body into the central void of the universe, and began fashioning the Midgard our earth....",
+    "Rank": 311,
+    "Group": "Online",
+    "Template": "SDXL",
+    "Category": "StableDiffusion",
+    "StableDiffusionTemplate": {
+      "PipelineType": "StableDiffusionXL",
+      "ModelType": "Base",
+      "SampleSize": 1024,
+      "TokenizerLength": 768,
+      "DiffuserTypes": [
+        "TextToImage",
+        "ImageToImage",
+        "ImageInpaintLegacy"
+      ],
+      "SchedulerDefaults": {
+        "SchedulerType": "EulerAncestral",
+        "Steps": 30,
+        "StepsMin": 4,
+        "StepsMax": 100,
+        "Guidance": 5,
+        "GuidanceMin": 0,
+        "GuidanceMax": 30,
+        "TimestepSpacing": "Linspace",
+        "BetaSchedule": "ScaledLinear",
+        "BetaStart": 0.00085,
+        "BetaEnd": 0.011
+      }
+    },
+    "Precision": "F16",
+    "MemoryMin": 6,
+    "MemoryMax": 16.4,
+    "DownloadSize": 11.2,
+    "Website": "https://civitai.com/models/470287",
+    "Repository": "https://huggingface.co/TensorStack/MidgardPony-XL-onnx",
+    "RepositoryFiles": [
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/controlnet/model.onnx",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/controlnet/model.onnx.data",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/controlnet/config.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/scheduler/scheduler_config.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/text_encoder/model.onnx",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/text_encoder/config.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/text_encoder_2/model.onnx",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/text_encoder_2/config.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/tokenizer/merges.txt",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/tokenizer/model.onnx",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/tokenizer/special_tokens_map.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/tokenizer/tokenizer_config.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/tokenizer/vocab.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/tokenizer_2/merges.txt",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/tokenizer_2/model.onnx",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/tokenizer_2/special_tokens_map.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/tokenizer_2/tokenizer_config.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/tokenizer_2/vocab.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/unet/model.onnx",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/unet/model.onnx.data",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/unet/config.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/vae_decoder/model.onnx",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/vae_decoder/config.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/vae_encoder/model.onnx",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/vae_encoder/config.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/model_index.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/model_template.json",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/README.md"
+    ],
+    "PreviewImages": [
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/Sample.png",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/Sample2.png",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/Sample3.png",
+      "https://huggingface.co/TensorStack/MidgardPony-XL-onnx/resolve/main/Sample4.png"
+    ],
+    "Tags": [
+      "GPU",
+      "F16"
+    ]
+  }

scheduler/scheduler_config.json

@@ -0,0 +1,23 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.29.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "final_sigmas_type": "zero",
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "sigma_max": null,
+  "sigma_min": null,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "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": "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 sha256:7480e0f7040a404c1d5b978a14fd7d79916c6467e337a366ca3f3f909344a50b
+size 246481009

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:ee9bc5012970ff2320c1908ecf739aa36d5ab404082a7dd3c73abfc10672ca9f
+size 1390289338

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 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+      "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 sha256:63b7618c80a5bd8d1ee6fe92b28e7b72dde7aaa522963ff083f284501a9ec7df
+size 1683233

tokenizer_2/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+      "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 +1,72 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.29.0.dev0",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    5,
+    10,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "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": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 128,
+  "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,
+    2,
+    10
+  ],
+  "up_block_types": [
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

unet/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f68ab74bb6f7b0f3f2f179c92fef7b18e54c0e64fa7a92bb46315bf66551f20d
+size 1242150

unet/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1ce7d1b7e4322e9a303a9e596285ec714daa985cb2e3f7d111e7756afb2401a
+size 5134903040

vae_decoder/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.20.0.dev0",
+  "_name_or_path": "../sdxl-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": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae_decoder/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20aae7848dcd708f4dfa562eda63a5df6a4434859f74b7e11dfd9553cf0fceb1
+size 99039207

vae_encoder/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.20.0.dev0",
+  "_name_or_path": "../sdxl-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": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae_encoder/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f3cc0532c41f52760353218f5c20c9c19b3d056c038d51c7b71c053ce57e599
+size 68391734