README.md

---
license: openrail
---

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).

You can use it with the pipeline here: https://gist.github.com/carson-katri/f51532b9d5162928d5cacbaee081a799

```python
# class StableDiffusionDepthPipeline: ...

from PIL import Image

model_id = "carsonkatri/stable-diffusion-2-depth-diffusers"

# Use the pipeline from this GH Gist: https://gist.github.com/carson-katri/f51532b9d5162928d5cacbaee081a799
pipe = StableDiffusionDepthPipeline.from_pretrained(model_id)
pipe = pipe.to("cuda")

image = pipe(
    prompt="a photo of a stormtrooper from star wars",
    depth_image=Image.open('depth.png'), # Black and white depth map
    image=Image.open("emad.png"), # Optional init image and strength.
    width=768,
    height=512
).images[0]

image.save('stormtrooper.png')
```