Commit
·
30bd9c0
1
Parent(s):
887b25f
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,53 @@
|
|
1 |
---
|
2 |
-
license: openrail
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: creativeml-openrail-m
|
3 |
+
thumbnail: "https://huggingface.co/coreml/coreml-anything-v3-1/resolve/main/example-images/thumbnail.png"
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
tags:
|
7 |
+
- coreml
|
8 |
+
- stable-diffusion
|
9 |
+
- stable-diffusion-diffusers
|
10 |
---
|
11 |
+
|
12 |
+
# Core ML Converted Model
|
13 |
+
|
14 |
+
This model was converted to Core ML for use on Apple Silicon devices by following Apple's instructions [here](https://github.com/apple/ml-stable-diffusion#-converting-models-to-core-ml).<br>
|
15 |
+
Provide the model to an app such as [Mochi Diffusion](https://github.com/godly-devotion/MochiDiffusion) to generate images.<br>
|
16 |
+
|
17 |
+
`split_einsum` version is compatible with all compute unit options including Neural Engine.<br>
|
18 |
+
`original` version is only compatible with CPU & GPU option.
|
19 |
+
|
20 |
+
# 🧩 Paper Cut model V1
|
21 |
+
This is the fine-tuned Stable Diffusion model trained on Paper Cut images.
|
22 |
+
|
23 |
+
Use **PaperCut** in your prompts.
|
24 |
+
|
25 |
+
### Sample images:
|
26 |
+
![PaperCut.jpg](https://s3.amazonaws.com/moonup/production/uploads/1667910351389-635749860725c2f190a76e88.jpeg)
|
27 |
+
![PaperCut.jpg](https://s3.amazonaws.com/moonup/production/uploads/1667912285222-635749860725c2f190a76e88.jpeg)
|
28 |
+
Based on StableDiffusion 1.5 model
|
29 |
+
|
30 |
+
### 🧨 Diffusers
|
31 |
+
|
32 |
+
This model can be used just like any other Stable Diffusion model. For more information,
|
33 |
+
please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
|
34 |
+
|
35 |
+
You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX]().
|
36 |
+
|
37 |
+
```python
|
38 |
+
from diffusers import StableDiffusionPipeline
|
39 |
+
import torch
|
40 |
+
|
41 |
+
model_id = "Fictiverse/Stable_Diffusion_PaperCut_Model"
|
42 |
+
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
|
43 |
+
pipe = pipe.to("cuda")
|
44 |
+
|
45 |
+
prompt = "PaperCut R2-D2"
|
46 |
+
image = pipe(prompt).images[0]
|
47 |
+
|
48 |
+
image.save("./R2-D2.png")
|
49 |
+
```
|
50 |
+
|
51 |
+
### ✨ Community spotlight :
|
52 |
+
@PiyarSquare :
|
53 |
+
[![PiyarSquare video](https://img.youtube.com/vi/wQWHnZlxFj8/0.jpg)](https://www.youtube.com/watch?v=wQWHnZlxFj8)
|