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/loaders/single_file.md
+9-210
Original file line number
Diff line number
Diff line change
@@ -10,13 +10,17 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
10
10
specific language governing permissions and limitations under the License.
11
11
-->
12
12
13
-
# Loading Pipelines and Models via `from_single_file`
13
+
# Single files
14
14
15
-
The `from_single_file` method allows you to load supported pipelines using a single checkpoint file as opposed to Diffusers' multiple folders format. This is useful if you are working with Stable Diffusion Web UI's (such as A1111) that rely on a single file format to distribute all the components of a model.
15
+
The [`~loaders.FromSingleFileMixin.from_single_file`] method allows you to load:
16
16
17
-
The `from_single_file` method also supports loading models in their originally distributed format. This means that supported models that have been finetuned with other services can be loaded directly into Diffusers model objects and pipelines.
17
+
* a model stored in a single file, which is useful if you're working with models from the diffusion ecosystem, like Automatic1111, and commonly rely on a single-file layout to store and share models
18
+
* a model stored in their originally distributed layout, which is useful if you're working with models finetuned with other services, and want to load it directly into Diffusers model objects and pipelines
18
19
19
-
## Pipelines that currently support `from_single_file` loading
20
+
> [!TIP]
21
+
> Read the [Model files and layouts](../../using-diffusers/other-formats) guide to learn more about the Diffusers-multifolder layout versus the single-file layout, and how to load models stored in these different layouts.
22
+
23
+
## Supported pipelines
20
24
21
25
-[`StableDiffusionPipeline`]
22
26
-[`StableDiffusionImg2ImgPipeline`]
@@ -39,218 +43,13 @@ The `from_single_file` method also supports loading models in their originally d
39
43
-[`LEditsPPPipelineStableDiffusionXL`]
40
44
-[`PIAPipeline`]
41
45
42
-
## Models that currently support `from_single_file` loading
## Setting components in a Pipeline using `from_single_file`
61
-
62
-
Set components of a pipeline by passing them directly to the `from_single_file` method. For example, here we are swapping out the pipeline's default scheduler with the `DDIMScheduler`.
63
-
64
-
```python
65
-
from diffusers import StableDiffusionXLPipeline, DDIMScheduler
model = StableCascadeUNet.from_single_file(ckpt_path)
93
-
94
-
```
95
-
96
-
## Using a Diffusers model repository to configure single file loading
97
-
98
-
Under the hood, `from_single_file` will try to automatically determine a model repository to use to configure the components of a pipeline. You can also explicitly set the model repository to configure the pipeline with the `config` argument.
In the example above, since we explicitly passed `repo_id="segmind/SSD-1B"` to the `config` argument, it will use this [configuration file](https://huggingface.co/segmind/SSD-1B/blob/main/unet/config.json) from the `unet` subfolder in `"segmind/SSD-1B"` to configure the `unet` component of the pipeline; Similarly, it will use the `config.json` file from `vae` subfolder to configure the `vae` model, `config.json` file from `text_encoder` folder to configure `text_encoder` and so on.
111
-
112
-
<Tip>
113
-
114
-
Most of the time you do not need to explicitly set a `config` argument. `from_single_file` will automatically map the checkpoint to the appropriate model repository. However, this option can be useful in cases where model components in the checkpoint might have been changed from what was originally distributed, or in cases where a checkpoint file might not have the necessary metadata to correctly determine the configuration to use for the pipeline.
115
-
116
-
</Tip>
117
-
118
-
## Override configuration options when using single file loading
119
-
120
-
Override the default model or pipeline configuration options by providing the relevant arguments directly to the `from_single_file` method. Any argument supported by the model or pipeline class can be configured in this way:
121
-
122
-
### Setting a pipeline configuration option
123
-
124
-
```python
125
-
from diffusers import StableDiffusionXLInstructPix2PixPipeline
model = UNet2DConditionModel.from_single_file(ckpt_path, upcast_attention=True)
139
-
140
-
```
141
-
142
-
<Tip>
143
-
144
-
To learn more about how to load single file weights, see the [Load different Stable Diffusion formats](../../using-diffusers/other-formats) loading guide.
145
-
146
-
</Tip>
147
-
148
-
## Working with local files
149
-
150
-
As of `diffusers>=0.28.0` the `from_single_file` method will attempt to configure a pipeline or model by first inferring the model type from the keys in the checkpoint file. This inferred model type is then used to determine the appropriate model repository on the Hugging Face Hub to configure the model or pipeline.
151
-
152
-
For example, any single file checkpoint based on the Stable Diffusion XL base model will use the [`stabilityai/stable-diffusion-xl-base-1.0`](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) model repository to configure the pipeline.
153
-
154
-
If you are working in an environment with restricted internet access, it is recommended that you download the config files and checkpoints for the model to your preferred directory and pass the local paths to the `pretrained_model_link_or_path` and `config` arguments of the `from_single_file` method.
155
-
156
-
```python
157
-
from huggingface_hub import hf_hub_download, snapshot_download
By default this will download the checkpoints and config files to the [Hugging Face Hub cache directory](https://huggingface.co/docs/huggingface_hub/en/guides/manage-cache). You can also specify a local directory to download the files to by passing the `local_dir` argument to the `hf_hub_download` and `snapshot_download` functions.
174
-
175
-
```python
176
-
from huggingface_hub import hf_hub_download, snapshot_download
## Working with local files on file systems that do not support symlinking
195
-
196
-
By default the `from_single_file` method relies on the `huggingface_hub` caching mechanism to fetch and store checkpoints and config files for models and pipelines. If you are working with a file system that does not support symlinking, it is recommended that you first download the checkpoint file to a local directory and disable symlinking by passing the `local_dir_use_symlink=False` argument to the `hf_hub_download` and `snapshot_download` functions.
197
-
198
-
```python
199
-
from huggingface_hub import hf_hub_download, snapshot_download
200
-
201
-
my_local_checkpoint_path = hf_hub_download(
202
-
repo_id="segmind/SSD-1B",
203
-
filename="SSD-1B.safetensors"
204
-
local_dir="my_local_checkpoints",
205
-
local_dir_use_symlinks=False
206
-
)
207
-
print("My local checkpoint: ", my_local_checkpoint_path)
As of `huggingface_hub>=0.23.0` the `local_dir_use_symlinks` argument isn't necessary for the `hf_hub_download` and `snapshot_download` functions.
228
-
229
-
</Tip>
230
-
231
-
## Using the original configuration file of a model
232
-
233
-
If you would like to configure the model components in a pipeline using the orignal YAML configuration file, you can pass a local path or url to the original configuration file via the `original_config` argument.
When using `original_config` with `local_files_only=True`, Diffusers will attempt to infer the components of the pipeline based on the type signatures of pipeline class, rather than attempting to fetch the configuration files from a model repository on the Hugging Face Hub. This is to prevent backward breaking changes in existing code that might not be able to connect to the internet to fetch the necessary configuration files.
248
-
249
-
This is not as reliable as providing a path to a local model repository using the `config` argument and might lead to errors when configuring the pipeline. To avoid this, please run the pipeline with `local_files_only=False` once to download the appropriate pipeline configuration files to the local cache.
0 commit comments