Skip to page content
SAVRN
Search Plan a project

Open-weight model · Text to image

coreaiimages

by Privacy AI flyingfishinwater/coreaiimages

coreaiimages is an open-weight model for text to image from Privacy AI, released under other. Its published files total 14.6 GB.

Apple Core AI builds of open text-to-image models, mirrored for on-device generation in Privacy AI (iOS 27 / macOS 27, Core AI diffusion pipeline).

Parameters—
Context—
Weights14.6 GB
Licenseother
AccessOpen weights
Monthly Downloads—

Model Card

Apple Core AI builds of open text-to-image models, mirrored for on-device generation in Privacy AI (iOS 27 / macOS 27, Core AI diffusion pipeline). Nothing here is original work: each subfolder is a redistributed model, converted with Apple's coreai.diffusion.export and, where stated, quantized. Each subfolder has its own licence. The licence text, a NOTICE, and MIRROR-NOTES.md (source repository and revision, exact export command, what was changed and dropped) sit inside every /source/ leaf, so they travel with the files to every device. Use of the Stable Diffusion v1-5 and v2-1 subfolders is subject to the use-based restrictions in Attachment A of their licences. Stable Diffusion 3.5…

Excerpt from the card by Privacy AI, licensed other.

Identity and Version

Repository
flyingfishinwater/coreaiimages
Publisher
Privacy AI
Task
Text to image
Modality
Image
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
9e28553415384d374c675d4a35ce956e83c9e962
First published
2026-10-07
Last updated
2026-10-08

Files and Weights

103 files, 14.6 GB in total.

Configuration27 files · 14.0 KB
Tokenizer16 files · 29.2 MB
Documentation21 files · 72.8 KB
Other38 files · 14.6 GB
Repository1 file · 3.2 KB
Every file
FileTypeSizeSHA-256
flux2-klein-4b-ios-512/source/TextEncoder.aimodel/metadata.jsonConfiguration396 B —
flux2-klein-4b-ios-512/source/Transformer_512.aimodel/metadata.jsonConfiguration400 B —
flux2-klein-4b-ios-512/source/VAEDecoder_half.aimodel/metadata.jsonConfiguration400 B —
flux2-klein-4b-ios-512/source/metadata.jsonConfiguration885 B —
flux2-klein-4b-ios-512/source/tokenizer/config.jsonConfiguration374 B —
flux2-klein-4b-macos-1024/source/TextEncoder.aimodel/metadata.jsonConfiguration396 B —
flux2-klein-4b-macos-1024/source/Transformer.aimodel/metadata.jsonConfiguration396 B —
flux2-klein-4b-macos-1024/source/VAEDecoder.aimodel/metadata.jsonConfiguration395 B —
flux2-klein-4b-macos-1024/source/metadata.jsonConfiguration867 B —
flux2-klein-4b-macos-1024/source/tokenizer/config.jsonConfiguration374 B —
sd15-fp16/source/TextEncoder.aimodel/metadata.jsonConfiguration461 B —
sd15-fp16/source/Unet.aimodel/metadata.jsonConfiguration454 B —
sd15-fp16/source/VAEDecoder.aimodel/metadata.jsonConfiguration460 B —
sd15-fp16/source/metadata.jsonConfiguration862 B —
sd15-fp16/source/tokenizer/special_tokens_map.jsonConfiguration472 B —
sd21-768-fp16/source/TextEncoder.aimodel/metadata.jsonConfiguration435 B —
sd21-768-fp16/source/Unet.aimodel/metadata.jsonConfiguration428 B —
sd21-768-fp16/source/VAEDecoder.aimodel/metadata.jsonConfiguration434 B —
sd21-768-fp16/source/metadata.jsonConfiguration872 B —
sd21-768-fp16/source/tokenizer/special_tokens_map.jsonConfiguration460 B —
sd35m-1024-4bit-fp16/source/MMDiT.aimodel/metadata.jsonConfiguration414 B —
sd35m-1024-4bit-fp16/source/TextEncoder.aimodel/metadata.jsonConfiguration420 B —
sd35m-1024-4bit-fp16/source/TextEncoder2.aimodel/metadata.jsonConfiguration421 B —
sd35m-1024-4bit-fp16/source/VAEDecoder.aimodel/metadata.jsonConfiguration419 B —
sd35m-1024-4bit-fp16/source/metadata.jsonConfiguration934 B —
sd35m-1024-4bit-fp16/source/tokenizer/special_tokens_map.jsonConfiguration588 B —
sd35m-1024-4bit-fp16/source/tokenizer_2/special_tokens_map.jsonConfiguration576 B —
README.mdDocumentation2.0 KB —
flux2-klein-4b-ios-512/source/LICENSEDocumentation9.6 KB —
flux2-klein-4b-ios-512/source/MIRROR-NOTES.mdDocumentation1.0 KB —
flux2-klein-4b-ios-512/source/NOTICE.mdDocumentation578 B —
flux2-klein-4b-ios-512/source/README.mdDocumentation550 B —
flux2-klein-4b-macos-1024/source/LICENSEDocumentation9.6 KB —
flux2-klein-4b-macos-1024/source/MIRROR-NOTES.mdDocumentation1.0 KB —
flux2-klein-4b-macos-1024/source/NOTICE.mdDocumentation578 B —
flux2-klein-4b-macos-1024/source/README.mdDocumentation553 B —
sd15-fp16/source/LICENSEDocumentation14.4 KB —
sd15-fp16/source/MIRROR-NOTES.mdDocumentation1.0 KB —
sd15-fp16/source/NOTICE.mdDocumentation665 B —
sd15-fp16/source/README.mdDocumentation545 B —
sd21-768-fp16/source/LICENSEDocumentation14.2 KB —
sd21-768-fp16/source/MIRROR-NOTES.mdDocumentation1.2 KB —
sd21-768-fp16/source/NOTICE.mdDocumentation628 B —
sd21-768-fp16/source/README.mdDocumentation549 B —
sd35m-1024-4bit-fp16/source/LICENSE.mdDocumentation11.7 KB —
sd35m-1024-4bit-fp16/source/MIRROR-NOTES.mdDocumentation1.0 KB —
sd35m-1024-4bit-fp16/source/NOTICE.mdDocumentation797 B —
sd35m-1024-4bit-fp16/source/README.mdDocumentation571 B —
flux2-klein-4b-ios-512/source/TextEncoder.aimodel/main.hashOther32 B —
flux2-klein-4b-ios-512/source/TextEncoder.aimodel/main.mlirbOther1.8 GB 9da9d4eebef3
flux2-klein-4b-ios-512/source/Transformer_512.aimodel/main.hashOther32 B —
flux2-klein-4b-ios-512/source/Transformer_512.aimodel/main.mlirbOther2.2 GB 7363a00994f6
flux2-klein-4b-ios-512/source/VAEDecoder_half.aimodel/main.hashOther32 B —
flux2-klein-4b-ios-512/source/VAEDecoder_half.aimodel/main.mlirbOther99.3 MB aceb28deb854
flux2-klein-4b-ios-512/source/tokenizer/chat_template.jinjaOther4.2 KB —
flux2-klein-4b-ios-512/source/vae_bn_mean.npyOther640 B b2e3b98b3b14
flux2-klein-4b-ios-512/source/vae_bn_var.npyOther640 B 9418da87092c
flux2-klein-4b-macos-1024/source/TextEncoder.aimodel/main.hashOther32 B —
flux2-klein-4b-macos-1024/source/TextEncoder.aimodel/main.mlirbOther1.8 GB 2c9b4b484ef9
flux2-klein-4b-macos-1024/source/Transformer.aimodel/main.hashOther32 B —
flux2-klein-4b-macos-1024/source/Transformer.aimodel/main.mlirbOther2.2 GB ec1e47d9f8b0
flux2-klein-4b-macos-1024/source/VAEDecoder.aimodel/main.hashOther32 B —
flux2-klein-4b-macos-1024/source/VAEDecoder.aimodel/main.mlirbOther99.3 MB 332a19cf9164
flux2-klein-4b-macos-1024/source/tokenizer/chat_template.jinjaOther4.2 KB —
flux2-klein-4b-macos-1024/source/vae_bn_mean.npyOther640 B b2e3b98b3b14
flux2-klein-4b-macos-1024/source/vae_bn_var.npyOther640 B 9418da87092c
sd15-fp16/source/TextEncoder.aimodel/main.hashOther32 B —
sd15-fp16/source/TextEncoder.aimodel/main.mlirbOther246.2 MB 6b90d40c03c6
sd15-fp16/source/Unet.aimodel/main.hashOther32 B —
sd15-fp16/source/Unet.aimodel/main.mlirbOther1.7 GB 0aef76c2a399
sd15-fp16/source/VAEDecoder.aimodel/main.hashOther32 B —
sd15-fp16/source/VAEDecoder.aimodel/main.mlirbOther99.0 MB 0bbf96913344
sd21-768-fp16/source/TextEncoder.aimodel/main.hashOther32 B —
sd21-768-fp16/source/TextEncoder.aimodel/main.mlirbOther680.9 MB 36813845b524
sd21-768-fp16/source/Unet.aimodel/main.hashOther32 B —
sd21-768-fp16/source/Unet.aimodel/main.mlirbOther1.7 GB b2662202b49a
sd21-768-fp16/source/VAEDecoder.aimodel/main.hashOther32 B —
sd21-768-fp16/source/VAEDecoder.aimodel/main.mlirbOther99.0 MB 7647530a6d2a
sd35m-1024-4bit-fp16/source/MMDiT.aimodel/main.hashOther32 B —
sd35m-1024-4bit-fp16/source/MMDiT.aimodel/main.mlirbOther1.3 GB 75a1fbe06c00
sd35m-1024-4bit-fp16/source/TextEncoder.aimodel/main.hashOther32 B —
sd35m-1024-4bit-fp16/source/TextEncoder.aimodel/main.mlirbOther69.9 MB 72fcf7e643d4
sd35m-1024-4bit-fp16/source/TextEncoder2.aimodel/main.hashOther32 B —
sd35m-1024-4bit-fp16/source/TextEncoder2.aimodel/main.mlirbOther391.8 MB 8284c9afa9c0
sd35m-1024-4bit-fp16/source/VAEDecoder.aimodel/main.hashOther32 B —
sd35m-1024-4bit-fp16/source/VAEDecoder.aimodel/main.mlirbOther198.2 MB 038c2b3c7e9f
.gitattributesRepository3.2 KB —
flux2-klein-4b-ios-512/source/tokenizer/tokenizer.jsonTokenizer11.4 MB be75606093db
flux2-klein-4b-ios-512/source/tokenizer/tokenizer_config.jsonTokenizer374 B —
flux2-klein-4b-macos-1024/source/tokenizer/tokenizer.jsonTokenizer11.4 MB be75606093db
flux2-klein-4b-macos-1024/source/tokenizer/tokenizer_config.jsonTokenizer374 B —
sd15-fp16/source/tokenizer/merges.txtTokenizer524.6 KB —
sd15-fp16/source/tokenizer/tokenizer_config.jsonTokenizer806 B —
sd15-fp16/source/tokenizer/vocab.jsonTokenizer1.1 MB —
sd21-768-fp16/source/tokenizer/merges.txtTokenizer524.6 KB —
sd21-768-fp16/source/tokenizer/tokenizer_config.jsonTokenizer824 B —
sd21-768-fp16/source/tokenizer/vocab.jsonTokenizer1.1 MB —
sd35m-1024-4bit-fp16/source/tokenizer/merges.txtTokenizer524.6 KB —
sd35m-1024-4bit-fp16/source/tokenizer/tokenizer_config.jsonTokenizer705 B —
sd35m-1024-4bit-fp16/source/tokenizer/vocab.jsonTokenizer1.1 MB —
sd35m-1024-4bit-fp16/source/tokenizer_2/merges.txtTokenizer524.6 KB —
sd35m-1024-4bit-fp16/source/tokenizer_2/tokenizer_config.jsonTokenizer856 B —
sd35m-1024-4bit-fp16/source/tokenizer_2/vocab.jsonTokenizer1.1 MB —

License and Download

License
other
Access
Open weights, no gate
Download from Privacy AI

Released by Privacy AI through its official repository on Hugging Face.

Questions About coreaiimages

What license is coreaiimages released under?

other, as its publisher declares it. Read the license text before commercial use.

Similar Models

GGUF, Safetensors, and MLX quantized formats of Qwen/Qwen-Image-2.1 for local image generation using the original upstream base weights. Q4KM is recommended for the best balance of size and quality for GGUF. INT8 ConvRot and NVFP4 offer high performance on supported GPUs, while MLX formats are optimized for Apple Silicon. Companion model files packaged for ComfyUI: Use the model with ComfyUI and ComfyUI-GGUF. All required companion files (GGUF transformer, text encoder, and VAE) are hosted directly in this repository. Download the files and place them in their respective ComfyUI directories: 1. Install ComfyUI-GGUF: Use the maintained fork with native Qwen-Image 2.1 support by cloning…

Open weights other gguf
View model

GGUF quantizations of Qwen/Qwen-Image-2.1 for local image generation using the original upstream base weights. Q4KM is recommended for the best balance of size and quality. Companion model files packaged for ComfyUI: Use the model with ComfyUI and ComfyUI-GGUF. All required companion files (GGUF transformer, text encoder, and VAE) are hosted directly in this repository. Download the files and place them in their respective ComfyUI directories: 1. Install ComfyUI-GGUF: Use the maintained fork with native Qwen-Image 2.1 support by cloning leejet/ComfyUI-GGUF into your custom nodes: (Note: If you have the older city96/ComfyUI-GGUF installed and encounter an Unknown model architecture! error…

Open weights other gguf
View model

Model · Text to image

Qwen-Image-2.1-GGUF

Unsloth AI

This is a GGUF quantized version of Qwen-Image-2.1. unsloth/Qwen-Image-2.1-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. - Important layers are upcasted to higher precision, per tensor, from a measured sensitivity scan. - Run these with Unsloth Desktop, stable-diffusion.cpp and more. A GGUF is the denoiser only, so it needs the VAE and the Qwen3-VL text encoder alongside it. See below for image editing operating inside of Unsloth Desktop: Rendered with the Q4KM denoiser and the Q4KM text encoder, 1024x1024, 20 steps, cfg 6.0, euler. We are excited to open-source Qwen-Image-2.1, a unified text-to-image generation and image editing model in the Qwen family. With just 7B…

Open weights other
View model

Model · Text to image

Z-Image-Turbo-GGUF

Unsloth AI

Welcome to the official repository for the Z-Image（造相）project! Z-Image is a powerful and highly efficient image generation model with 6B parameters. Currently there are three variants: - Z-Image-Turbo – A distilled version of Z-Image that matches or exceeds leading competitors with only 8 NFEs (Number of Function Evaluations). It offers sub-second inference latency on enterprise-grade H800 GPUs and fits comfortably within 16G VRAM consumer devices. It excels in photorealistic image generation, bilingual text rendering (English & Chinese), and robust instruction adherence. - Z-Image-Base – The non-distilled foundation model. By releasing this checkpoint, we aim to unlock the full potential…

Open weights apache-2.0 ggml
View model

Model · Text to image

Juggernaut-XL-v9

RunDiffusion

The SDXL ecosystem is the single most mature corner of open image generation, and v9 is its most refined photorealism checkpoint. Choose Juggernaut XL v9 when you want: - Photorealism that holds up under scrutiny — skin texture, micro-contrast, and natural lighting that translates from concept to print. - Reasonable hardware — runs comfortably on 8 GB of VRAM, unlike newer DiT-based models that demand 16+ GB. - The full SDXL toolbox — drop-in compatibility with the thousands of SDXL ControlNets, IP-Adapter variants, AnimateDiff, regional prompting tools, and LoRAs already in your workflow. - Battle-tested reliability — 26+ months in production, used in agencies, studios, and shipping…

Open weights creativeml-openrail-m diffusers
View model

Model · Text to image

Qwen-Image-Lightning

Lightx2v

Please refer to Qwen-Image-Lightning github to learn how to use the models. make sure to install diffusers from main (pip install git+https://github.com/huggingface/diffusers.git)

Open weights apache-2.0 diffusers
View model