Upload folder using huggingface_hub

.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
+Unet.mlmodelc/model.mil filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,35 @@
+---
+license: creativeml-openrail-m
+base_model: AstraliteHeart/pony-diffusion-v6
+pipeline_tag: text-to-image
+tags:
+  - core-ml
+  - coreml
+  - stable-diffusion
+  - apple-silicon
+  - ios
+  - quantized
+---
+
+# Pony Diffusion V6 XL — Core ML (8-bit)
+
+Core ML conversion of [AstraliteHeart/pony-diffusion-v6](https://huggingface.co/AstraliteHeart/pony-diffusion-v6) for Apple silicon
+(iOS / iPadOS / macOS, Neural Engine). Built with Apple's
+[ml-stable-diffusion](https://github.com/apple/ml-stable-diffusion) for use by
+[mindfire-image](https://github.com/Gatcha-man/mindfire-image).
+
+SDXL fine-tune — 20-35 steps, CFG ~7. Needs its score/rating prompt tags; see the base model card.
+
+## Modifications from the base model
+
+These weights are **modified**: converted from PyTorch/diffusers to Core ML
+(`.mlmodelc`) and **quantized to 8-bit palettized** weights. No fine-tuning was
+performed — behaviour should track the base model, but quantization can shift
+outputs slightly.
+
+## Licence
+
+Inherited from the base model: `creativeml-openrail-m`. This includes the OpenRAIL
+**use-based restrictions (Attachment A)**, which apply to you as a downstream user of
+this conversion exactly as they do to the base model. Read the base model's licence
+before use or redistribution.

TextEncoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0456c891481e04658662983a06d01243219e588d816bc99393b74139b9792a
+size 243

TextEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2bf902cb1f8e45fc5037a7b00543c8bdce14233063f4f5a331ee1e781bb042
+size 978

TextEncoder.mlmodelc/metadata.json

@@ -0,0 +1,89 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text and\/or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 for details.",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 77 × 768)",
+        "shortDescription" : "Hidden states after the encoder layers",
+        "shape" : "[1, 77, 768]",
+        "name" : "hidden_embeds",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 768)",
+        "shortDescription" : "The version of the `last_hidden_state` output after pooling",
+        "shape" : "[1, 768]",
+        "name" : "pooled_outputs",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "stablediffusionapi\/Pony-Diffusion-V6-XL",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stablediffusionapi\/Pony-Diffusion-V6-XL",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Mixed (Float16, Palettized (8 bits))",
+    "license" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 3,
+      "Ios16.mul" : 36,
+      "Ios16.layerNorm" : 25,
+      "Ios16.constexprLutToDense" : 74,
+      "Transpose" : 48,
+      "Stack" : 1,
+      "Ios16.sigmoid" : 12,
+      "Ios16.linear" : 72,
+      "Ios16.add" : 37,
+      "Ios16.softmax" : 12,
+      "Ios16.matmul" : 24,
+      "Ios16.gatherNd" : 1,
+      "Ios16.gather" : 1,
+      "Ios16.reshape" : 48,
+      "Ios16.reduceArgmax" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "stateSchema" : [
+
+    ],
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 77)",
+        "shortDescription" : "The token ids that represent the input text",
+        "shape" : "[1, 77]",
+        "name" : "input_ids",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2026-02-17",
+      "com.github.apple.coremltools.source" : "torch==2.8.0",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stablediffusionapi_Pony_Diffusion_V6_XL_text_encoder",
+    "method" : "predict"
+  }
+]

TextEncoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0117bcc079a3a310e4316f2d3903f955f7e5fc9efa056c933c8b5055445dd73
+size 161188416

TextEncoder2.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d094f6c84e87057a5d3884b420c7fcb17a1a1ef0fb1b537176719ee1c0bcf64
+size 243

TextEncoder2.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0947a3a45593f1f74b127115f1fa81864498047ae4c64e38add436a9a8cdecc
+size 978

TextEncoder2.mlmodelc/metadata.json

@@ -0,0 +1,89 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text and\/or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 for details.",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 77 × 1280)",
+        "shortDescription" : "Hidden states after the encoder layers",
+        "shape" : "[1, 77, 1280]",
+        "name" : "hidden_embeds",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 1280)",
+        "shortDescription" : "The version of the `last_hidden_state` output after pooling",
+        "shape" : "[1, 1280]",
+        "name" : "pooled_outputs",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "stablediffusionapi\/Pony-Diffusion-V6-XL",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stablediffusionapi\/Pony-Diffusion-V6-XL",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Mixed (Float16, Palettized (8 bits))",
+    "license" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.cast" : 3,
+      "Ios16.mul" : 32,
+      "Ios16.layerNorm" : 65,
+      "Ios16.constexprLutToDense" : 195,
+      "Transpose" : 128,
+      "Stack" : 1,
+      "Ios16.linear" : 193,
+      "Ios16.add" : 97,
+      "Ios16.softmax" : 32,
+      "Ios16.gelu" : 32,
+      "Ios16.matmul" : 64,
+      "Ios16.gatherNd" : 1,
+      "Ios16.gather" : 1,
+      "Ios16.reshape" : 128,
+      "Ios16.reduceArgmax" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "stateSchema" : [
+
+    ],
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 77)",
+        "shortDescription" : "The token ids that represent the input text",
+        "shape" : "[1, 77]",
+        "name" : "input_ids",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2026-02-17",
+      "com.github.apple.coremltools.source" : "torch==2.8.0",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stablediffusionapi_Pony_Diffusion_V6_XL_text_encoder_2",
+    "method" : "predict"
+  }
+]

TextEncoder2.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d233edbf5597fca7e492be7258421cdd32337a9de6f3a8b0ade27b73206dd85
+size 758591232

Unet.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87534b6e06468ca53fb48117509edcd1f5244b71041f2b4037a18db35ac68441
+size 243

Unet.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8150af10f6f392a2008888f1f8a3a1f615a8ec97ee455796fb330209e2415235
+size 1734

Unet.mlmodelc/metadata.json

@@ -0,0 +1,130 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 for details.",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 2 × 4 × 128 × 128)",
+        "shortDescription" : "Same shape and dtype as the `sample` input. The predicted noise to facilitate the reverse diffusion (denoising) process",
+        "shape" : "[2, 4, 128, 128]",
+        "name" : "noise_pred",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "stablediffusionapi\/Pony-Diffusion-V6-XL",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stablediffusionapi\/Pony-Diffusion-V6-XL",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Mixed (Float16, Palettized (8 bits))",
+    "license" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)",
+    "mlProgramOperationTypeHistogram" : {
+      "Transpose" : 140,
+      "UpsampleNearestNeighbor" : 2,
+      "Ios16.reduceMean" : 92,
+      "Ios16.sin" : 2,
+      "Ios16.softmax" : 2600,
+      "Split" : 70,
+      "Ios16.add" : 302,
+      "Concat" : 154,
+      "Ios16.realDiv" : 46,
+      "Ios16.square" : 46,
+      "ExpandDims" : 6,
+      "Ios16.sub" : 46,
+      "Ios16.sqrt" : 46,
+      "Ios16.conv" : 794,
+      "Ios16.constexprLutToDense" : 794,
+      "Ios16.einsum" : 5200,
+      "Ios16.layerNorm" : 210,
+      "SliceByIndex" : 7804,
+      "Ios16.batchNorm" : 46,
+      "Ios16.reshape" : 116,
+      "Ios16.silu" : 38,
+      "Ios16.gelu" : 70,
+      "Ios16.mul" : 2672,
+      "Ios16.cos" : 2,
+      "Ios16.cast" : 1
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "stateSchema" : [
+
+    ],
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 4 × 128 × 128)",
+        "shortDescription" : "The low resolution latent feature maps being denoised through reverse diffusion",
+        "shape" : "[2, 4, 128, 128]",
+        "name" : "sample",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2)",
+        "shortDescription" : "A value emitted by the associated scheduler object to condition the model on a given noise schedule",
+        "shape" : "[2]",
+        "name" : "timestep",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 2048 × 1 × 77)",
+        "shortDescription" : "Output embeddings from the associated text_encoder model to condition to generated image on text. A maximum of 77 tokens (~40 words) are allowed. Longer text is truncated. Shorter text does not reduce computation.",
+        "shape" : "[2, 2048, 1, 77]",
+        "name" : "encoder_hidden_states",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 6)",
+        "shortDescription" : "Additional embeddings that if specified are added to the embeddings that are passed along to the UNet blocks.",
+        "shape" : "[2, 6]",
+        "name" : "time_ids",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 2 × 1280)",
+        "shortDescription" : "Additional embeddings from text_encoder_2 that if specified are added to the embeddings that are passed along to the UNet blocks.",
+        "shape" : "[2, 1280]",
+        "name" : "text_embeds",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2026-02-17",
+      "com.github.apple.ml-stable-diffusion.version" : "1.1.0",
+      "com.github.apple.coremltools.source" : "torch==2.8.0",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stablediffusionapi_Pony_Diffusion_V6_XL_unet",
+    "method" : "predict"
+  }
+]

Unet.mlmodelc/model.mil

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7186899965e08074ff635e00cd913d73af9952c19c3904384c8d29077690f4ca
+size 10695585

Unet.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:442f1b70cdfcb3d9dddfebf40d9d774644f23e78fec96d6408b0786c86cd422e
+size 2569644096

VAEDecoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd31e04bfdd9b75ec2f850d34c8a5a28891ca183a9846c23af4bf0ba687be7f1
+size 243

VAEDecoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:012691dcbc911205af7d51aaa600e283680cba44778064cbc51ad5457af1ea1d
+size 929

VAEDecoder.mlmodelc/metadata.json

@@ -0,0 +1,80 @@
+[
+  {
+    "shortDescription" : "Stable Diffusion generates images conditioned on text and\/or other images as input through the diffusion process. Please refer to https:\/\/arxiv.org\/abs\/2112.10752 for details.",
+    "metadataOutputVersion" : "3.0",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 3 × 1024 × 1024)",
+        "shortDescription" : "Generated image normalized to range [-1, 1]",
+        "shape" : "[1, 3, 1024, 1024]",
+        "name" : "image",
+        "type" : "MultiArray"
+      }
+    ],
+    "version" : "stablediffusionapi\/Pony-Diffusion-V6-XL",
+    "modelParameters" : [
+
+    ],
+    "author" : "Please refer to the Model Card available at huggingface.co\/stablediffusionapi\/Pony-Diffusion-V6-XL",
+    "specificationVersion" : 7,
+    "storagePrecision" : "Float32",
+    "license" : "OpenRAIL++-M (https:\/\/huggingface.co\/stabilityai\/stable-diffusion-xl-base-1.0\/blob\/main\/LICENSE.md)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios16.mul" : 2,
+      "Ios16.sub" : 30,
+      "Transpose" : 6,
+      "Ios16.sqrt" : 30,
+      "UpsampleNearestNeighbor" : 3,
+      "Ios16.square" : 30,
+      "Ios16.add" : 46,
+      "Ios16.reduceMean" : 60,
+      "Ios16.realDiv" : 30,
+      "Ios16.conv" : 36,
+      "Ios16.linear" : 4,
+      "Ios16.matmul" : 2,
+      "Ios16.batchNorm" : 29,
+      "Ios16.softmax" : 1,
+      "Ios16.reshape" : 65,
+      "Ios16.silu" : 29
+    },
+    "computePrecision" : "Mixed (Float32, Int32)",
+    "stateSchema" : [
+
+    ],
+    "isUpdatable" : "0",
+    "availability" : {
+      "macOS" : "13.0",
+      "tvOS" : "16.0",
+      "visionOS" : "1.0",
+      "watchOS" : "9.0",
+      "iOS" : "16.0",
+      "macCatalyst" : "16.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float32",
+        "formattedType" : "MultiArray (Float32 1 × 4 × 128 × 128)",
+        "shortDescription" : "The denoised latent embeddings from the unet model after the last step of reverse diffusion",
+        "shape" : "[1, 4, 128, 128]",
+        "name" : "z",
+        "type" : "MultiArray"
+      }
+    ],
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2026-02-17",
+      "com.github.apple.coremltools.source" : "torch==2.8.0",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "generatedClassName" : "Stable_Diffusion_version_stablediffusionapi_Pony_Diffusion_V6_XL_vae_decoder",
+    "method" : "predict"
+  }
+]

VAEDecoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4970a8d07aacc9579344b16c0d0fed5a1e07711a582ab9a7d270f31367e2d9c
+size 197977216