| --- |
| license: creativeml-openrail-m |
| tags: |
| - text-to-image |
| - stable-diffusion |
| - epicrealism |
| - photorealistic |
| - coreml |
| - apple-neural-engine |
| - palettized |
| - tokforge |
| base_model: |
| - emilianJR/epiCRealism |
| pipeline_tag: text-to-image |
| library_name: ml-stable-diffusion |
| --- |
| |
| ## LocalMuseAI distribution mirror |
|
|
| This repository is an unmodified distribution mirror of [`darkmaniac7/TokForge-epiCRealism-CoreML-6bit`](https://huggingface.co/darkmaniac7/TokForge-epiCRealism-CoreML-6bit) for the LocalMuse iOS app. The compiled Core ML binary artifacts are preserved unchanged. Model authorship, conversion credit, license terms, and the original model card are retained below. |
|
|
|
|
| ## 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. |
|
|
| # TokForge — epiCRealism · CoreML 6-bit (Apple Neural Engine) |
|
|
| A **6-bit palettized Apple CoreML** conversion of **epiCRealism** |
| ([emilianJR/epiCRealism](https://huggingface.co/emilianJR/epiCRealism), an SD-1.5 cinematic |
| photoreal finetune with 1M+ downloads), built for on-device image generation in the |
| **[TokForge](https://tokforge.ai)** iOS app. Converted with Apple |
| **[`ml-stable-diffusion`](https://github.com/apple/ml-stable-diffusion)** (`torch2coreml`) |
| using **`SPLIT_EINSUM_V2`** attention and **`--quantize-nbits 6`** (6-bit palettized weights), |
| so it compiles **fast on the Apple Neural Engine**. |
|
|
| Part of the **[TokForge iOS · CoreML Image Models](https://huggingface.co/collections/darkmaniac7/tokforge-ios-coreml-image-models-6a38cca9b57803e6168ce232)** collection. |
|
|
| ## Files |
|
|
| | File | Size | Contents | |
| |------|------|----------| |
| | `Resources/` | ~913 MB | `TextEncoder.mlmodelc` / `Unet.mlmodelc` / `VAEDecoder.mlmodelc` / `VAEEncoder.mlmodelc` + `vocab.json` + `merges.txt` | |
|
|
| The `Resources/` tree holds the compiled `.mlmodelc` models plus the CLIP `vocab.json` + |
| `merges.txt` — the exact layout Apples `StableDiffusionPipeline` (and the TokForge installer) |
| loads. |
|
|
| ## Recommended render settings |
|
|
| ``` |
| attention: split_einsum_v2 (Apple Neural Engine) |
| compute: .cpuAndNeuralEngine (palettized -> fast ANE compile) |
| steps: 20-30 (epiCRealism cinematic-portrait range) |
| cfg-scale: 7.0 |
| resolution: 512x512 (SD-1.5 native; baked into the compiled model) |
| ``` |
|
|
| ## How this was built |
|
|
| 1. Loaded `emilianJR/epiCRealism` (SD-1.5 diffusers format). |
| 2. Converted UNet + text encoder + VAE decoder + VAE encoder to CoreML with Apple |
| `ml-stable-diffusion` `python_coreml_stable_diffusion.torch2coreml`, |
| `--attention-implementation SPLIT_EINSUM_V2`. |
| 3. Applied **6-bit palettization** (`--quantize-nbits 6`). |
| 4. Bundled the compiled resources for the Swift CLI (`--bundle-resources-for-swift-cli`). |
|
|
| Conversion peaked at ~9.8 GB RAM (no `--chunk-unet` needed). Runs on iOS **17+** (6-bit |
| palettized weights require the iOS-17 ANE runtime); on iOS-16 the app falls back to an FP16 model. |
|
|
| ## License & attribution |
|
|
| - **License:** [CreativeML OpenRAIL-M](https://huggingface.co/spaces/CompVis/stable-diffusion-license), |
| inherited from epiCRealism / Stable Diffusion 1.5. Use is subject to the OpenRAIL-M restrictions. |
| - **Base model:** **epiCRealism** by **emilianJR** — |
| https://huggingface.co/emilianJR/epiCRealism. All credit for the model weights is emilianJRs. |
| - **Conversion tooling:** Apple **`ml-stable-diffusion`** — |
| https://github.com/apple/ml-stable-diffusion (6-bit palettization, `SPLIT_EINSUM_V2` attention). |
| - 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 emilianJRs epiCRealism. 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. |
|
|
