CyberRealistic V9 (Core ML 6-bit)
Cyberdelia's CyberRealistic V9 as a 6-bit Core ML bundle for making photorealistic pictures on iPhone and iPad with TokForge.
Published by TokForge for on-device inference.
| What it is | Image generator (photorealistic) |
| Format | Core ML resources for Apple's ml-stable-diffusion, 6-bit palettized, split einsum v2 attention, 512 x 512 |
| Runs on | iPhone and iPad (Core ML, Apple Neural Engine); listed in TokForge for iOS |
| Phone class | 4 GB RAM or more, iOS 17 or later (TokForge for iOS catalog) |
| Download | 1.87 GB (23 files); TokForge fetches only the zip (917 MB) |
| Base model | cyberdelia/CyberRealistic |
| License | CreativeML OpenRAIL-M, plus Cyberdelia's Civitai terms |
TokForge
- Website: https://tokforge.ai
- Discord: https://discord.gg/Acv3CBtfVm
- Google Play: https://play.google.com/store/apps/details?id=dev.tokforge
- iOS TestFlight: https://testflight.apple.com/join/jnufjzRr
Runs on-device in the TokForge app.
Use it in TokForge
- Join the iOS TestFlight to install TokForge on iPhone or iPad.
- TokForge for iOS lists it in its image models as CyberRealistic V9 ยท 6-bit (ANE) and uses it for the Cyber-real look. The app marks it as a mature (photoreal) model, so it shows up only after mature models are turned on. Pick it and the app downloads the zip, unpacks it and runs it on the Neural Engine.
- Describe the picture you want and generate it. The model runs on the device; once it is downloaded, making pictures needs no connection.
Collections: TokForge iOS Models.
Files
| File | Size | What it is |
|---|---|---|
CyberRealistic-V9_palettized_split_einsum_v2_compiled.zip |
917 MB | Compiled Core ML resources in one zip (the file TokForge downloads) |
Resources/ |
958 MB in 22 files | The same compiled resources, unzipped: TextEncoder, Unet, VAEDecoder and VAEEncoder (.mlmodelc) plus the CLIP tokenizer files |
The zip and the Resources/ folder hold the same compiled models. The zip expands to the Resources/ layout that
Apple's StableDiffusionPipeline (and the TokForge installer) loads.
About the model
CyberRealistic V9 is cyberdelia's photorealistic Stable Diffusion 1.5 fine-tune with an integrated VAE. This bundle is
made from its CyberRealistic_V9_FP16 checkpoint.
| Architecture | Stable Diffusion 1.5 (UNet, CLIP text encoder, VAE) |
| Weights | UNet and text encoder 6-bit palettized, VAE in fp16 |
| Components | TextEncoder, Unet, VAEDecoder and VAEEncoder (.mlmodelc), plus the CLIP vocab.json and merges.txt |
| UNet batch | 2 (classifier-free guidance works as usual) |
| Output | 512 x 512, fixed in the compiled model |
| Tooling | ml-stable-diffusion 1.1.0, coremltools 9.0, torch 2.8.0 (from each model's metadata.json) |
Render settings
| Setting | Value |
|---|---|
| Attention | split_einsum_v2 (Apple Neural Engine) |
| Compute units | .cpuAndNeuralEngine |
| Steps | 25 to 30 (TokForge starts at 28) |
| Guidance (CFG) | 7.0 |
| Resolution | 512 x 512 (SD 1.5 native; baked into the compiled model) |
How it was made
- Loaded the
CyberRealistic_V9_FP16safetensors checkpoint fromcyberdelia/CyberRealisticvia diffusersStableDiffusionPipeline.from_single_fileand re-exported it to the SD 1.5 diffusers format. - Converted the UNet, text encoder, VAE decoder and VAE encoder to Core ML with Apple
ml-stable-diffusionpython_coreml_stable_diffusion.torch2coreml,--attention-implementation SPLIT_EINSUM_V2. - Applied 6-bit palettization (
--quantize-nbits 6). - Bundled the compiled resources for the Swift CLI (
--bundle-resources-for-swift-cli).
Conversion peaked at about 10.5 GB RAM (no --chunk-unet needed). TokForge uses the 6-bit palettized weights on
iOS 17 or later; on iOS 16 the app falls back to an FP16 model.
Limitations
- Pictures are 512 x 512 only; the size is built into the compiled model.
- 6-bit palettization can show rainbow or banding artifacts on some prompts. The 8-bit build is the higher-precision option.
- This is a Core ML runtime bundle, not a diffusers or PyTorch checkpoint.
License
CyberRealistic V9 and this conversion are under the CreativeML OpenRAIL-M license, and Cyberdelia's Civitai terms apply too (see Credits).
- License: CreativeML OpenRAIL-M, inherited from CyberRealistic / Stable Diffusion 1.5. Use is subject to the OpenRAIL-M restrictions.
- Base model: CyberRealistic V9 by cyberdelia: https://huggingface.co/cyberdelia/CyberRealistic. All credit for the model weights is cyberdelia's.
- Conversion tooling: Apple
ml-stable-diffusion: https://github.com/apple/ml-stable-diffusion (6-bit palettization,SPLIT_EINSUM_V2attention). - Built on top of Stable Diffusion 1.5 (Runway/CompVis/Stability).
This repository is a redistribution for on-device use, a format conversion (PyTorch -> CoreML) and 6-bit palettization of cyberdelia's CyberRealistic V9. No weights were retrained. The original OpenRAIL-M terms and attribution requirements propagate to this conversion and any images generated with it. No additional restrictions are imposed by this repackaging.
Credits
- CyberRealistic V9 by Cyberdelia (Civitai, Hugging Face). Used under the CreativeML OpenRAIL-M license and the creator's Civitai terms. Cyberdelia's Civitai terms allow selling and do not add a credit requirement; the CreativeML OpenRAIL-M terms still apply.
- Stable Diffusion v1.5 by Runway and CompVis (Hugging Face). Used under the CreativeML OpenRAIL-M license.
- Converted to Core ML with ml-stable-diffusion by Apple (MIT).
Model tree for darkmaniac7/TokForge-CyberRealistic-V9-CoreML-6bit
Base model
cyberdelia/CyberRealistic