Instructions to use carsonkatri/stable-diffusion-2-depth-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use carsonkatri/stable-diffusion-2-depth-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import AutoPipelineForInpainting from diffusers.utils import load_image # switch to "mps" for apple devices pipe = AutoPipelineForInpainting.from_pretrained("carsonkatri/stable-diffusion-2-depth-diffusers", dtype=torch.float16, device_map="cuda") img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png" mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png" image = load_image(img_url).resize((1024, 1024)) mask_image = load_image(mask_url).resize((1024, 1024)) prompt = "a tiger sitting on a park bench" generator = torch.Generator(device="cuda").manual_seed(0) image = pipe( prompt=prompt, image=image, mask_image=mask_image, guidance_scale=8.0, num_inference_steps=20, # steps between 15 and 30 work well for us strength=0.99, # make sure to use `strength` below 1.0 generator=generator, ).images[0] - Notebooks
- Google Colab
- Kaggle
Commit ·
33780c8
1
Parent(s): adc2b43
Add example code
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
---
|
| 2 |
license: openrail
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: openrail
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
This model is converted from [stable-diffusion-2-depth](https://huggingface.co/stabilityai/stable-diffusion-2-depth) using the [conversion script](https://github.com/huggingface/diffusers/blob/main/scripts/convert_original_stable_diffusion_to_diffusers.py) from [🤗 Diffusers](https://github.com/huggingface/diffusers).
|
| 6 |
+
|
| 7 |
+
You can use it with the pipeline here: https://gist.github.com/carson-katri/f51532b9d5162928d5cacbaee081a799
|
| 8 |
+
|
| 9 |
+
```python
|
| 10 |
+
# class StableDiffusionDepthPipeline: ...
|
| 11 |
+
|
| 12 |
+
from PIL import Image
|
| 13 |
+
|
| 14 |
+
model_id = "carsonkatri/stable-diffusion-2-depth-diffusers"
|
| 15 |
+
|
| 16 |
+
# Use the pipeline from this GH Gist: https://gist.github.com/carson-katri/f51532b9d5162928d5cacbaee081a799
|
| 17 |
+
pipe = StableDiffusionDepthPipeline.from_pretrained(model_id)
|
| 18 |
+
pipe = pipe.to("cuda")
|
| 19 |
+
|
| 20 |
+
image = pipe(
|
| 21 |
+
prompt="a photo of a stormtrooper from star wars",
|
| 22 |
+
depth_image=Image.open('depth.png'), # Black and white depth map
|
| 23 |
+
image=Image.open("emad.png"), # Optional init image and strength.
|
| 24 |
+
width=768,
|
| 25 |
+
height=512
|
| 26 |
+
).images[0]
|
| 27 |
+
|
| 28 |
+
image.save('stormtrooper.png')
|
| 29 |
+
```
|