Aller au contenu
ModelPrésentéExterne
Télécharger

SD v1 5 Inpainting Coreml

creativeml-openrail-m

Sourcehuggingface.co/jc-builds/sd-v1-5-inpainting-coreml/tree/d64d94387e72a444f910f7bb83ea76fc6d7fb984
TypeOtherModèle de baserunwayml/stable-diffusion-inpaintingVersionCoremldataCClasse

Source du modèle

Type
Other
Taille du fichier
243 B–1,60 GB
Modèle de base
runwayml/stable-diffusion-inpainting
Version
vCoremldata
Mis à jour
19 oct. 2026
Source
Hugging Face

Description de la source

Stable Diffusion 1.5 Inpainting (Core ML)

This is a Core ML conversion of Stable Diffusion v1.5 Inpainting optimized for on-device inference on Apple Silicon.

Model Details

PropertyValue
Original ModelStable Diffusion v1.5 Inpainting
Parameters860 million
Resolution512x512
FormatCore ML (.mlmodelc)
Compute UnitsCPU + Neural Engine

Intended Use

This model is optimized for:

  • iOS/macOS Deployment: Native Apple Silicon inference
  • Inpainting Tasks: Fill in masked areas of images
  • Object Removal: Remove unwanted objects from photos
  • Creative Editing: Artistic transformations of image regions

Capabilities

  • Mask-based Editing: Paint areas to regenerate
  • Seamless Blending: Natural integration with original content
  • Artistic Styles: Works well with stylized content
  • Fast Inference: Lighter than SD 2.1, quicker iterations

Bundle Contents

  • TextEncoder.mlmodelc - CLIP text encoder
  • Unet.mlmodelc - 9-channel UNet (latent + masked image + mask)
  • VAEDecoder.mlmodelc - Variational autoencoder decoder
  • VAEEncoder.mlmodelc - Variational autoencoder encoder
  • vocab.json - Tokenizer vocabulary
  • merges.txt - BPE merges

Usage

Compatible with Apple's ml-stable-diffusion framework and iOS apps using Core ML.

License

This model is released under the CreativeML Open RAIL-M license.

Attribution

Sources

1 source
Hugging FacePrincipalVersion d64d94387e72a444f910f7bb83ea76fc6d7fb984
huggingface.co/jc-builds/sd-v1-5-inpainting-coreml/tree/d64d94387e72a444f910f7bb83ea76fc6d7fb984

Vérifié 19 oct.

Artefacts du modèle

12 artefacts

TextEncoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 66c84098c4bc…2dfe · Hugging Face

Télécharger

TextEncoder.mlmodelc/coremldata.bin

bin · 994 B · SHA-256 a700f7ce3317…e62a · Hugging Face

Télécharger

TextEncoder.mlmodelc/weights/weight.bin

bin · 235 MB · SHA-256 b3e8699e18a3…2ddb · Hugging Face

Télécharger

Unet.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 f15a626ca227…78bf · Hugging Face

Télécharger

Unet.mlmodelc/coremldata.bin

bin · 1,39 KB · SHA-256 7d98619511aa…081a · Hugging Face

Télécharger

Unet.mlmodelc/weights/weight.bin

bin · 1,60 GB · SHA-256 0f6a88bcd1ae…0826 · Hugging Face

Télécharger

VAEDecoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 3e8795c9ebea…9e2b · Hugging Face

Télécharger

VAEDecoder.mlmodelc/coremldata.bin

bin · 921 B · SHA-256 a29fa6aec131…2299 · Hugging Face

Télécharger

VAEDecoder.mlmodelc/weights/weight.bin

bin · 94,4 MB · SHA-256 ca45a093443d…c752 · Hugging Face

Télécharger

VAEEncoder.mlmodelc/analytics/coremldata.bin

bin · 243 B · SHA-256 11bc30df398e…b4ea · Hugging Face

Télécharger

VAEEncoder.mlmodelc/coremldata.bin

bin · 925 B · SHA-256 e46c66121242…c12d · Hugging Face

Télécharger

VAEEncoder.mlmodelc/weights/weight.bin

bin · 65,2 MB · SHA-256 71bf826e5ee1…dc64 · Hugging Face

Télécharger

Extraits de sources

2 extraits
Readme3 aoûthuggingface.co/jc-builds/sd-v1-5-inpainting-coreml

--- license: other license_name: creativeml-openrail-m license_link: https://huggingface.co/runwayml/stable-diffusion-inpainting/blob/main/LICENSE base_model: runwayml/stable-diffusion-inpainting pipeline_tag: image-to-image tags: - coreml - stable-diffusion - inpainting - ios - macos - apple-silicon - image-editing --- # Stable Diffusion 1.5 Inpainting (Core ML) This is a **Core ML conversion** of [Stable Diffusion v1.5 Inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting) optimized for on-device inference on Apple Silicon. ## Model Details | Property | Value | |----------|-------| | **Original Model** | Stable Diffusion v1.5 Inpainting | | **Parameters** | 860 million | | **Resolution** | 512x512 | | **Format** | Core ML (.mlmodelc) | | **Compute Units** | CPU + Neural Engine | ## Intended Use This model is optimized for: - **iOS/macOS Deployment**: Native Apple Silicon inference - **Inpainting Tasks**: Fill in masked areas of images - **Object Removal**: Remove unwanted objects from photos - **Creative Editing**: Artistic transformations of image regions ## Capabilities - **Mask-based Editing**: Paint areas to regenerate - **Seamless Blending**: Natural integration with original content - **Artistic Styles**: Works well with stylized content - **Fast Inference**: Lighter than SD 2.1, quicker iterations ## Bundle Contents - `TextEncoder.mlmodelc` - CLIP text encoder - `Unet.mlmodelc` - 9-channel UNet (latent + masked image + mask) - `VAEDecoder.mlmodelc` - Variational autoencoder decoder - `VAEEncoder.mlmodelc` - Variational autoencoder encoder - `vocab.json` - Tokenizer vocabulary - `merges.txt` - BPE merges ## Usage Compatible with Apple's [ml-stable-diffusion](https://github.com/apple/ml-stable-diffusion) framework and iOS apps using Core ML. ## License This model is released under the **CreativeML Open RAIL-M** license. ## Attribution - **Original Model**: [Stable Diffusion v1.5 Inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting) by Runway ML - **Core ML Conversion**: jc-builds

Note3 aoûthuggingface.co/jc-builds/sd-v1-5-inpainting-coreml

Source context: 0 downloads · 2 likes · Pipeline image-to-image · Repo jc-builds/sd-v1-5-inpainting-coreml