Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
local-ai
image-generation
lora
apple-silicon
clover-image
diffusion
stable-diffusion
knowledge-distillation
compact
small-model
local-inference
edge-inference
mobile-inference
core-ml
iphone
sd-1.4-class
Instructions to use neonforestmist/Clover-Image-Tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use neonforestmist/Clover-Image-Tiny with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nota-ai/bk-sdm-tiny-2m", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("neonforestmist/Clover-Image-Tiny") prompt = "a glass of red wine" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Add inpainting examples and citation
Browse files
coreml-tools/README-INPAINTING.md
CHANGED
|
@@ -7,7 +7,6 @@ tags:
|
|
| 7 |
- clover-image
|
| 8 |
- inpainting
|
| 9 |
- coreml
|
| 10 |
-
- iphone
|
| 11 |
---
|
| 12 |
|
| 13 |
# Clover Image Tiny Inpaint — Core ML
|
|
@@ -36,6 +35,11 @@ masked-image latent. The VAE encoder is required to create the final four
|
|
| 36 |
channels on device. White mask pixels are regenerated and black pixels are
|
| 37 |
preserved.
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
## Convert and validate
|
| 40 |
|
| 41 |
```bash
|
|
@@ -53,3 +57,14 @@ Neural Engine-capable path is valid.
|
|
| 53 |
|
| 54 |
The resulting `Resources` directory can be published as the companion model
|
| 55 |
repo [`neonforestmist/Clover-Image-Tiny-Inpaint-CoreML`](https://huggingface.co/neonforestmist/Clover-Image-Tiny-Inpaint-CoreML).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
- clover-image
|
| 8 |
- inpainting
|
| 9 |
- coreml
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
# Clover Image Tiny Inpaint — Core ML
|
|
|
|
| 35 |
channels on device. White mask pixels are regenerated and black pixels are
|
| 36 |
preserved.
|
| 37 |
|
| 38 |
+
Example edits include replacing a masked object with a tiny greenhouse,
|
| 39 |
+
removing a person while continuing the background, or adding a red kettle to a
|
| 40 |
+
masked countertop. Use a grayscale mask where white means “regenerate” and
|
| 41 |
+
black means “preserve.”
|
| 42 |
+
|
| 43 |
## Convert and validate
|
| 44 |
|
| 45 |
```bash
|
|
|
|
| 57 |
|
| 58 |
The resulting `Resources` directory can be published as the companion model
|
| 59 |
repo [`neonforestmist/Clover-Image-Tiny-Inpaint-CoreML`](https://huggingface.co/neonforestmist/Clover-Image-Tiny-Inpaint-CoreML).
|
| 60 |
+
|
| 61 |
+
## Citation
|
| 62 |
+
|
| 63 |
+
```bibtex
|
| 64 |
+
@software{lozadaperez2026cloverimagetinyinpaint,
|
| 65 |
+
author = {Lukas Lozada Perez},
|
| 66 |
+
title = {Clover Image Tiny Inpaint: Compact SD 1.4-Class Image Inpainting},
|
| 67 |
+
year = {2026},
|
| 68 |
+
url = {https://huggingface.co/neonforestmist/Clover-Image-Tiny-Inpaint}
|
| 69 |
+
}
|
| 70 |
+
```
|