Skip to content

Commit c0930fe

Browse files
authored
Merge pull request #19 from cuchoco/jihwan/depth2img
depth2img translation
2 parents e4a79fd + 50a48d9 commit c0930fe

File tree

1 file changed

+57
-0
lines changed

1 file changed

+57
-0
lines changed
Lines changed: 57 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,57 @@
1+
<!--Copyright 2023 The HuggingFace Team. All rights reserved.
2+
3+
Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
4+
the License. You may obtain a copy of the License at
5+
6+
http://www.apache.org/licenses/LICENSE-2.0
7+
8+
Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
9+
an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
10+
specific language governing permissions and limitations under the License.
11+
-->
12+
13+
# Text-guided depth-to-image 생성
14+
15+
[[open-in-colab]]
16+
17+
[`StableDiffusionDepth2ImgPipeline`]을 사용하면 텍스트 프롬프트와 초기 이미지를 전달하여 이미지의 생성을 조절할 있습니다. 또한 이미지 구조를 보존하기 위해 `depth_map`을 전달할 수도 있습니다. `depth_map`이 제공되지 않으면 파이프라인은 통합된 [depth-estimation model](https://github.com/isl-org/MiDaS)을 통해 자동으로 깊이를 예측합니다.
18+
19+
20+
먼저 [`StableDiffusionDepth2ImgPipeline`]의 인스턴스를 생성합니다:
21+
22+
```python
23+
import torch
24+
import requests
25+
from PIL import Image
26+
27+
from diffusers import StableDiffusionDepth2ImgPipeline
28+
29+
pipe = StableDiffusionDepth2ImgPipeline.from_pretrained(
30+
"stabilityai/stable-diffusion-2-depth",
31+
torch_dtype=torch.float16,
32+
).to("cuda")
33+
```
34+
35+
이제 프롬프트를 파이프라인에 전달합니다. 특정 단어가 이미지 생성을 가이드 하는것을 방지하기 위해 `negative_prompt`를 전달할 수도 있습니다:
36+
37+
```python
38+
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
39+
init_image = Image.open(requests.get(url, stream=True).raw)
40+
prompt = "two tigers"
41+
n_prompt = "bad, deformed, ugly, bad anatomy"
42+
image = pipe(prompt=prompt, image=init_image, negative_prompt=n_prompt, strength=0.7).images[0]
43+
image
44+
```
45+
46+
| Input | Output |
47+
|---------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------|
48+
| <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/coco-cats.png" width="500"/> | <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/depth2img-tigers.png" width="500"/> |
49+
50+
아래의 스페이스를 가지고 놀며 depth map이 있는 이미지와 없는 이미지의 차이가 있는지 확인해 보세요!
51+
52+
<iframe
53+
src="https://radames-stable-diffusion-depth2img.hf.space"
54+
frameborder="0"
55+
width="850"
56+
height="500"
57+
></iframe>

0 commit comments

Comments
 (0)