---
license: apache-2.0
library_name: diffusers
---
test under this PR https://github.com/huggingface/diffusers/pull/11235

```python
from diffusers.modular_pipelines import ModularPipeline, ComponentsManager
import torch
from diffusers.utils import load_image

repo_id = "YiYiXu/modular-diffdiff"
components = ComponentsManager()

diffdiff_pipeline = ModularPipeline.from_pretrained(repo_id, trust_remote_code=True, component_manager=components, collection="diffdiff")
diffdiff_pipeline.load_componenets(torch_dtype=torch.float16)

components.enable_auto_cpu_offload()

image = load_image( "https://huggingface.co/datasets/OzzyGT/testing-resources/resolve/main/differential/20240329211129_4024911930.png?download=true")
mask = load_image("https://huggingface.co/datasets/OzzyGT/testing-resources/resolve/main/differential/gradient_mask.png?download=true")

prompt = "a green pear"
negative_prompt = "blurry"

image = diffdiff_pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_inference_steps=25,
    diffdiff_map=mask,
    image=image,
    output="images"
)[0]

image.save("yiyi_test_modular_remote_diffdiff_out.png")
```


![image/png](https://cdn-uploads.huggingface.co/production/uploads/624ef9ba9d608e459387b34e/4zqJOz-35Q0i6jyUW3liL.png)