Image-to-Image
Diffusers
Safetensors
Core ML
StableDiffusionInpaintPipeline
clover-image
inpainting
stable-diffusion
Instructions to use neonforestmist/Clover-Image-Tiny-Inpaint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use neonforestmist/Clover-Image-Tiny-Inpaint with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("neonforestmist/Clover-Image-Tiny-Inpaint", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Add blue sunglasses inpainting example
Browse files
README.md
CHANGED
|
@@ -15,8 +15,9 @@ tags:
|
|
| 15 |
# Clover Image Tiny Inpaint HQ
|
| 16 |
|
| 17 |
Clover Image Tiny Inpaint HQ is the high-quality, context-aware inpainting
|
| 18 |
-
|
| 19 |
-
|
|
|
|
| 20 |
This preserves Clover compatibility while replacing the compact inpainting
|
| 21 |
denoiser that frequently produced blurry or unrecognizable masked objects.
|
| 22 |
|
|
@@ -55,6 +56,16 @@ Recommended interactive defaults are DPM-Solver++, 20 steps, CFG 6.0, and a
|
|
| 55 |
96-pixel context crop. Composite the generated result through the exact binary
|
| 56 |
mask when unchanged source pixels must remain byte-for-byte untouched.
|
| 57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
## Quality gate
|
| 59 |
|
| 60 |
The release was evaluated on 24 deterministic, held-out, human-rated
|
|
|
|
| 15 |
# Clover Image Tiny Inpaint HQ
|
| 16 |
|
| 17 |
Clover Image Tiny Inpaint HQ is the high-quality, context-aware inpainting
|
| 18 |
+
companion to [Clover Image Tiny](https://huggingface.co/neonforestmist/Clover-Image-Tiny).
|
| 19 |
+
It combines the complete Stable Diffusion 1.5 inpainting U-Net with Clover
|
| 20 |
+
Image Tiny's tokenizer, text encoder, VAE, and scheduler.
|
| 21 |
This preserves Clover compatibility while replacing the compact inpainting
|
| 22 |
denoiser that frequently produced blurry or unrecognizable masked objects.
|
| 23 |
|
|
|
|
| 56 |
96-pixel context crop. Composite the generated result through the exact binary
|
| 57 |
mask when unchanged source pixels must remain byte-for-byte untouched.
|
| 58 |
|
| 59 |
+
## Inpainting example
|
| 60 |
+
|
| 61 |
+
This edit starts from the Clover Image Tiny artwork below and uses the prompt
|
| 62 |
+
`add blue sunglasses`. The source and result are included so the masked edit
|
| 63 |
+
can be compared directly.
|
| 64 |
+
|
| 65 |
+
| Source image | Inpainted result |
|
| 66 |
+
|:---:|:---:|
|
| 67 |
+
|  |  |
|
| 68 |
+
|
| 69 |
## Quality gate
|
| 70 |
|
| 71 |
The release was evaluated on 24 deterministic, held-out, human-rated
|