| --- |
| library_name: coreml |
| pipeline_tag: text-to-image |
| license: creativeml-openrail-m |
| tags: |
| - coreml |
| - stable-diffusion |
| - ios |
| - clover-image |
| --- |
| |
| # Clover Image Tiny — Core ML |
|
|
| Versioned Core ML resources for the Clover iPhone app. |
|
|
| `manifest.json` is the public download contract. The iOS 18 release uses one |
| stateful U-Net. Clover's base weights are stored once; each optional style is |
| its original 6,927,128-byte rank-16 safetensors LoRA. The Swift pipeline loads |
| the selected adapter into Core ML mutable state without replacing the U-Net. |
|
|
| The base checkpoint and fused style variants are derivatives of |
| `neonforestmist/Clover-Image-Tiny` and retain the CreativeML Open RAIL-M |
| license. Style training datasets are Apache-2.0 and are linked by the manifest. |
|
|
| ## Citation |
|
|
| If the Core ML release is useful in your work, please cite it separately: |
|
|
| ```bibtex |
| @software{lozadaperez2026cloverimagetinycoreml, |
| author = {Lukas Lozada Perez}, |
| title = {Clover Image Tiny Core ML: On-Device Text-to-Image Resources for iPhone}, |
| year = {2026}, |
| url = {https://huggingface.co/neonforestmist/Clover-Image-Tiny-CoreML} |
| } |
| ``` |
|
|
