File size: 1,278 Bytes
f2bedf9
 
 
 
2474882
f2bedf9
 
 
d83032b
f2bedf9
d83032b
f2bedf9
 
d83032b
 
 
f2bedf9
d83032b
 
 
 
 
f2bedf9
 
d83032b
 
 
f2bedf9
d83032b
 
 
f2bedf9
d83032b
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37


## Examples

Using the [🤗's Diffusers library](https://github.com/huggingface/diffusers) in a simple and efficient manner.

```python
from PIL import Image
import os
import torch
from diffusers import StableDiffusionUpscaleLDM3DPipeline,  StableDiffusionLDM3DPipeline


#Generate a rgb/depth output from LDM3D
pipe_ldm3d = StableDiffusionLDM3DPipeline.from_pretrained("Intel/ldm3d-4c")
pipe_ldm3d.to("cuda")

prompt =f"A picture of some lemons on a table"
output = pipe_ldm3d(prompt)
rgb_image, depth_image = output.rgb, output.depth
rgb_image[0].save(f"lemons_ldm3d_rgb.jpg")
depth_image[0].save(f"lemons_ldm3d_depth.png")


#Upscale the previous output to a resolution of (1024, 1024)
pipe_ldm3d_upscale = StableDiffusionUpscaleLDM3DPipeline.from_pretrained("Intel/ldm3d-sr")
pipe_ldm3d_upscale.to("cuda")

low_res_img = Image.open(f"lemons_ldm3d_rgb.jpg").convert("RGB")
low_res_depth = Image.open(f"lemons_ldm3d_depth.png").convert("L")
outputs = pipe_ldm3d_upscale(prompt="high quality high resolution uhd 4k image", rgb=low_res_img, depth=low_res_depth, num_inference_steps=50, target_res=[1024, 1024])

upscaled_rgb, upscaled_depth =outputs.rgb[0], outputs.depth[0]
upscaled_rgb.save(f"upscaled_lemons_rgb.png")
upscaled_depth.save(f"upscaled_lemons_depth.png")
```