Add model card with upstream attribution

README.md

@@ -0,0 +1,77 @@
+---
+license: creativeml-openrail-m
+tags:
+- text-to-image
+- stable-diffusion
+- cyberrealistic
+- photorealistic
+- coreml
+- apple-neural-engine
+- palettized
+- tokforge
+base_model:
+- cyberdelia/CyberRealistic
+pipeline_tag: text-to-image
+library_name: ml-stable-diffusion
+---
+
+# TokForge — CyberRealistic V9 · CoreML 6-bit (Apple Neural Engine)
+
+A **6-bit palettized Apple CoreML** conversion of **CyberRealistic V9**
+([cyberdelia/CyberRealistic](https://huggingface.co/cyberdelia/CyberRealistic), the
+`CyberRealistic_V9_FP16` checkpoint by **cyberdelia** — an SD-1.5 photorealistic finetune
+with best-in-class faces and an integrated VAE), 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:        25-30  (CyberRealistic photoreal sweet spot)
+cfg-scale:    7.0
+resolution:   512x512  (SD-1.5 native; baked into the compiled model)
+```
+
+## How this was built
+
+1. Loaded `CyberRealistic_V9_FP16.safetensors` from `cyberdelia/CyberRealistic` via diffusers
+   `StableDiffusionPipeline.from_single_file` and re-exported to 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 ~10.5 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 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 cyberdelias.
+- **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 cyberdelias 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.