neonforestmist/Clover-Image-Tiny-Inpaint-CoreML

Clover Image Tiny Inpaint HQ — Core ML

Core ML resources for the high-quality Clover Image Tiny inpainting pipeline. The iOS 18 batch-one U-Net accepts [1, 9, 64, 64], runs classifier-free guidance as two serial passes, and exposes 144 mutable Core ML states for exact runtime composition of up to three Clover styles.

The production U-Net is under hq-v4-int8/Unet.mlmodelc. Its immutable weights use per-channel symmetric int8 compression, reducing the complete inpainting add-on from about 1.79 GB to 931 MB while leaving mutable LoRA state in FP16. Shared tokenizer, text encoder, and VAE decoder resources are hard-linked from the required main Clover installation instead of downloaded again. hq-v4-int8/adapter-schema.json maps each small .safetensors style into one of three independent state slots.

Validation

PyTorch/Core ML parity on deterministic inputs:

Configuration	FP16	Int8 production
Base HQ inpainting U-Net	78.56 dB	59.32 dB
Monet 0.70 + Pointillism 0.45 + Watercolor Anime 1.10	78.47 dB	59.30 dB

The release gate is 35 dB. The three-style result validates the exact block-concatenated LoRA sum rather than a UI-only approximation.

Held-out 24-case inpainting quality relative to the previous Diffusers release:

Metric	Previous	HQ
Masked prompt CLIP similarity	0.2642	0.2768
Masked target MAE	0.2510	0.2231
Changed pixels outside the mask	0	0

Runtime contract

• Minimum OS: iOS 18
• Resolution: 512×512
• U-Net input: noisy latent (4) + mask (1) + masked image latent (4)
• Mask: white regenerates, black preserves
• Maximum simultaneous styles: 3
• Safety checker: not constructed by the Clover iOS pipeline

Citation

@software{lozadaperez2026cloverimagetinyinpaintcoreml,
  author = {Lukas Lozada Perez},
  title = {Clover Image Tiny Inpaint HQ Core ML},
  year = {2026},
  url = {https://huggingface.co/neonforestmist/Clover-Image-Tiny-Inpaint-CoreML}
}

Designed and developed independently by Lukas Lozada Perez. Open weights under the CreativeML Open RAIL-M license; inference runs completely on device.