Clover Inpaint HQ — technical reference
Quality gate
The release was evaluated on 24 deterministic, held-out, human-rated InpaintCOCO edits. Every output was also reviewed in three visual contact sheets before release.
| Metric | Previous Clover inpaint | HQ release | Change vs. previous Clover | SD 1.5 inpaint teacher |
|---|---|---|---|---|
| Masked prompt CLIP similarity ↑ | 0.2642 | 0.2768 | 4.8% higher | 0.2820 |
| Masked target MAE ↓ | 0.2510 | 0.2231 | 11.1% lower error | 0.2156 |
| Changed pixels outside the mask ↓ | 0 | 0 | Unchanged | 0 |
↑ Higher is better; ↓ lower is better. Bold highlights HQ's improvements over the previous Clover release, not the best score across all models. The strongest measured improvement is 11.1% lower masked target error. The SD 1.5 teacher still scores better on both alignment and target error in this evaluation.
The HQ release improves prompt alignment by 4.8% and reduces masked target error by 11.1% relative to the previous Clover inpainting release. The visual gate showed recognizable buses, dogs, trains, furniture, signs, and scene-consistent lighting where the compact candidates often collapsed into amorphous fills.
Selection provenance
The release process compared the existing checkpoint, a 30,000-step full-U-Net distillation run, two fused context-LoRA refinements, partial weight blends, the full Stable Diffusion inpainting reference, and this Clover-component hybrid. The 30,000-step and context-LoRA candidates were rejected because they did not beat the existing release across both visual and quantitative gates. The published HQ architecture was the only Clover-compatible candidate that materially improved both prompt alignment and reconstruction.
- Inpainting U-Net revision:
stable-diffusion-v1-5/stable-diffusion-inpainting@8a4288a76071f7280aedbdb3253bdb9e9d5d84bb - Clover components:
neonforestmist/Clover-Image-Tiny - Evaluation dataset:
phiyodr/InpaintCOCO@1ffac84be2dfc5ad9afccad868522fad64457435 - Selection platform: Modal H100
- Evaluation seed:
20260813
Core ML and style mixing
The companion iOS resources are published at
neonforestmist/Clover-Image-Tiny-Inpaint-CoreML.
In Diffusers, the published Clover style LoRAs are mechanically compatible with this nine-channel U-Net because they modify attention projections only; those tensor shapes are unchanged from the four-channel model. They were trained for text-to-image, however, so masked-edit quality should be evaluated per style. LoRAs that modify the four-channel input convolution are not compatible.
Dynamic Core ML loading is a separate deployment capability. The shipping iOS inpainting screen currently selects a stateless or chunked U-Net and does not enable styles. An adapter-aware stateful nine-channel export can provide up to three independently weighted slots, but it must include the matching adapter schema and be validated on its target devices. For a stateless deployment, fuse a compatible LoRA before conversion.
Limitations
Small text, hands, faces, exact logos, and masks below latent resolution can still fail. Output quality depends on the source, mask, prompt, scheduler, guidance, seed, and step count. This release inherits the limitations and license obligations of Clover Image Tiny and Stable Diffusion 1.5 inpainting.
Citation
@software{lozadaperez2026cloverimagetinyinpaint,
author = {Lukas Lozada Perez},
title = {Clover Image Tiny Inpaint HQ: Local Context-Aware Image Inpainting},
year = {2026},
url = {https://huggingface.co/neonforestmist/Clover-Image-Tiny-Inpaint}
}
Designed and developed independently by Lukas Lozada Perez. Open weights under the CreativeML Open RAIL-M license; complete local inference is supported.