You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/source/en/api/image_processor.md
+6Lines changed: 6 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -20,6 +20,12 @@ All pipelines with [`VaeImageProcessor`] accept PIL Image, PyTorch tensor, or Nu
20
20
21
21
[[autodoc]] image_processor.VaeImageProcessor
22
22
23
+
## InpaintProcessor
24
+
25
+
The [`InpaintProcessor`] accepts `mask` and `image` inputs and process them together. Optionally, it can accept padding_mask_crop and apply mask overlay.
26
+
27
+
[[autodoc]] image_processor.InpaintProcessor
28
+
23
29
## VaeImageProcessorLDM3D
24
30
25
31
The [`VaeImageProcessorLDM3D`] accepts RGB and depth inputs and returns RGB and depth outputs.
Components are only loaded and registered when using [`~ModularPipeline.load_components`] or [`~ModularPipeline.load_default_components`]. The example below uses [`~ModularPipeline.load_default_components`] to create a second pipeline that reuses all the components from the first one, and assigns it to a different collection
54
+
Components are only loaded and registered when using [`~ModularPipeline.load_components`] or [`~ModularPipeline.load_components`]. The example below uses [`~ModularPipeline.load_components`] to create a second pipeline that reuses all the components from the first one, and assigns it to a different collection
All models begin on the CPU and [`ComponentsManager`] moves them to the appropriate device right before they're needed, and moves other models back to the CPU when GPU memory is low.
189
189
190
-
You can set your own rules for which models to offload first.
190
+
You can set your own rules for which models to offload first.
Copy file name to clipboardExpand all lines: docs/source/en/modular_diffusers/guiders.md
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -75,13 +75,13 @@ Guiders that are already saved on the Hub with a `modular_model_index.json` file
75
75
}
76
76
```
77
77
78
-
The guider is only created after calling [`~ModularPipeline.load_default_components`] based on the loading specification in `modular_model_index.json`.
78
+
The guider is only created after calling [`~ModularPipeline.load_components`] based on the loading specification in `modular_model_index.json`.
A [`ModularPipeline`] doesn't automatically instantiate with components. It only loads the configuration and component specifications. You can load all components with [`~ModularPipeline.load_default_components`] or only load specific components with [`~ModularPipeline.load_components`].
179
+
A [`ModularPipeline`] doesn't automatically instantiate with components. It only loads the configuration and component specifications. You can load all components with [`~ModularPipeline.load_components`] or only load specific components with [`~ModularPipeline.load_components`].
Copy file name to clipboardExpand all lines: docs/source/en/modular_diffusers/quickstart.md
+9-9Lines changed: 9 additions & 9 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -173,9 +173,9 @@ print(dd_blocks)
173
173
174
174
## ModularPipeline
175
175
176
-
Convert the [`SequentialPipelineBlocks`] into a [`ModularPipeline`] with the [`ModularPipeline.init_pipeline`] method. This initializes the expected components to load from a `modular_model_index.json` file. Explicitly load the components by calling [`ModularPipeline.load_default_components`].
176
+
Convert the [`SequentialPipelineBlocks`] into a [`ModularPipeline`] with the [`ModularPipeline.init_pipeline`] method. This initializes the expected components to load from a `modular_model_index.json` file. Explicitly load the components by calling [`ModularPipeline.load_components`].
177
177
178
-
It is a good idea to initialize the [`ComponentManager`] with the pipeline to help manage the different components. Once you call [`~ModularPipeline.load_default_components`], the components are registered to the [`ComponentManager`] and can be shared between workflows. The example below uses the `collection` argument to assign the components a `"diffdiff"` label for better organization.
178
+
It is a good idea to initialize the [`ComponentManager`] with the pipeline to help manage the different components. Once you call [`~ModularPipeline.load_components`], the components are registered to the [`ComponentManager`] and can be shared between workflows. The example below uses the `collection` argument to assign the components a `"diffdiff"` label for better organization.
179
179
180
180
```py
181
181
from diffusers.modular_pipelines import ComponentsManager
@@ -209,11 +209,11 @@ Use the [`sub_blocks.insert`] method to insert it into the [`ModularPipeline`].
Call [`~ModularPipeline.init_pipeline`] to initialize a [`ModularPipeline`] and use [`~ModularPipeline.load_default_components`] to load the model components. Load and set the IP-Adapter to run the pipeline.
212
+
Call [`~ModularPipeline.init_pipeline`] to initialize a [`ModularPipeline`] and use [`~ModularPipeline.load_components`] to load the model components. Load and set the IP-Adapter to run the pipeline.
Insert the `controlnet_input` block and replace the `denoise` block with the new `controlnet_denoise_block`. Initialize a [`ModularPipeline`] and [`~ModularPipeline.load_default_components`] into it.
263
+
Insert the `controlnet_input` block and replace the `denoise` block with the new `controlnet_denoise_block`. Initialize a [`ModularPipeline`] and [`~ModularPipeline.load_components`] into it.
0 commit comments