CONTENTS
About The Project
Enhance the functionality of diffusers.
- Search models from Hugging Face and Civitai.
- Officially listed in the Hugging Face Diffusers Community Projects documentation.
Image of the listing location on Hugging Face
Regarding the Civitai API bug
The previously reported Civitai API issue has largely been resolved.
Previous issue description
Due to recent specification changes in the Civitai API, we were aware of the following issues:
- Reduced search accuracy
- Some search results not being returned
A temporary workaround has been implemented for the above issues, but since certain search results are still not returned, there is a possibility that some models may not be found.
link： civitai/civitai#1757
How to use
pip install --quiet auto_diffusers
import torch
from auto_diffusers import EasyPipelineForText2Image
# Load an official Hugging Face model
pipe = EasyPipelineForText2Image.from_huggingface(
"stabilityai/stable-diffusion-xl-base-1.0",
dtype=torch.float16,
).to("cuda")
img = pipe("cat").images[0]
img.save("cat.png")
# Search for Civitai
pipe = EasyPipelineForText2Image.from_civitai(
"search_word",
dtype=torch.float16,
).to("cuda")
image = pipe("cat").images[0]
image.save("cat.png")
Use dtype for new code. torch_dtype remains supported for compatibility, but do not pass both arguments at the same time.
Search Civitai and Huggingface
# Load Lora into the pipeline.
pipe.auto_load_lora_weights("Detail Tweaker")
# Load TextualInversion into the pipeline.
pipe.auto_load_textual_inversion("EasyNegative", token="EasyNegative")
Search Civitai
[!TIP] If an error occurs, insert the
tokenand run again.
EasyPipeline.from_civitai parameters
| Name | Type | Default | Description |
|---|---|---|---|
| search_word | string, Path | required | The search query string. Can be a keyword, Civitai URL, local directory or file path. |
| model_type | string | Checkpoint |
The type of model to search for. (for example Checkpoint, TextualInversion, Controlnet, LORA, Hypernetwork, AestheticGradient, Poses) |
| base_model | string | None | Trained model tag (for example SD 1.5, SD 3.5, SDXL 1.0) |
| dtype | string, torch.dtype | None | Override the default torch.dtype and load the model with another dtype. |
| force_download | bool | False | Whether or not to force the (re-)download of the model weights and configuration files, overriding the cached versions if they exist. |
| cache_dir | string, Path | None | Path to the folder where cached files are stored. |
| resume | bool | False | Whether to resume an incomplete download. |
| token | string | None | API token for Civitai authentication. |
search_civitai parameters
| Name | Type | Default | Description |
|---|---|---|---|
| search_word | string, Path | required | The search query string. Can be a keyword, Civitai URL, local directory or file path. |
| model_type | string | Checkpoint |
The type of model to search for. (for example Checkpoint, TextualInversion, Controlnet, LORA, Hypernetwork, AestheticGradient, Poses) |
| base_model | string | None | Trained model tag (for example SD 1.5, SD 3.5, SDXL 1.0) |
| download | bool | False | Whether to download the model. |
| force_download | bool | False | Whether to force the download if the model already exists. |
| cache_dir | string, Path | None | Path to the folder where cached files are stored. |
| resume | bool | False | Whether to resume an incomplete download. |
| token | string | None | API token for Civitai authentication. |
| include_params | bool | False | Whether to include parameters in the returned data. |
| skip_error | bool | False | Whether to skip errors and return None. |
Search Huggingface
[!TIP] If an error occurs, insert the
tokenand run again.
EasyPipeline.from_huggingface parameters
| Name | Type | Default | Description |
|---|---|---|---|
| search_word | string, Path | required | The search query string. Can be a keyword, Hugging Face URL, local directory or file path, or a Hugging Face path (<creator>/<repo>). |
| checkpoint_format | string | single_file |
The format of the model checkpoint. - single_file to search for single file checkpoint - diffusers to search for multifolder diffusers format checkpoint |
| dtype | string, torch.dtype | None | Override the default torch.dtype and load the model with another dtype. |
| force_download | bool | False | Whether or not to force the (re-)download of the model weights and configuration files, overriding the cached versions if they exist. |
| cache_dir | string, Path | None | Path to a directory where a downloaded pretrained model configuration is cached if the standard cache is not used. |
| token | string, bool | None | The token to use as HTTP bearer authorization for remote files. |
search_huggingface parameters
| Name | Type | Default | Description |
|---|---|---|---|
| search_word | string, Path | required | The search query string. Can be a keyword, Hugging Face URL, local directory or file path, or a Hugging Face path (<creator>/<repo>). |
| checkpoint_format | string | single_file |
The format of the model checkpoint. - single_file to search for single file checkpoint - diffusers to search for multifolder diffusers format checkpoint |
| pipeline_tag | string | None | Tag to filter models by pipeline. |
| download | bool | False | Whether to download the model. |
| force_download | bool | False | Whether or not to force the (re-)download of the model weights and configuration files, overriding the cached versions if they exist. |
| cache_dir | string, Path | None | Path to a directory where a downloaded pretrained model configuration is cached if the standard cache is not used. |
| token | string, bool | None | The token to use as HTTP bearer authorization for remote files. |
| include_params | bool | False | Whether to include parameters in the returned data. |
| skip_error | bool | False | Whether to skip errors and return None. |
License
In accordance with Apache-2.0 license
Acknowledgement
I have used open source resources and free tools in the creation of this project.
I would like to take this opportunity to thank the open source community and those who provided free tools.
1 maintainer
Release files for auto-diffusers 2.0.37
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| auto_diffusers-2.0.37.tar.gz | 32.7 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| auto_diffusers-2.0.37-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 61.5 kB
Release files / auto_diffusers-2.0.37.tar.gz
| Download URL | auto_diffusers-2.0.37.tar.gz |
|---|---|
| Size | 32.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7f23e27ff230ab75cf04b156a658d0df37bd2b6e23e7fff8eaac38f6db1ee66a
|
|
BLAKE2b-256 checksum How to use checksums |
60c4d36ec12e37c4e685ab4687451f4001e29c0abe9601c4e7c9e51107a0b28c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Release files / auto_diffusers-2.0.37-py3-none-any.whl
| Download URL | auto_diffusers-2.0.37-py3-none-any.whl |
|---|---|
| Size | 28.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d248cc710b16d655f32d0dc00729e97c731c7360eb2f534b6636f2423cab91f6
|
|
BLAKE2b-256 checksum How to use checksums |
dc0be5cffe60209a33066e4c01250d849b38bc0f65ab8a50e2171f58ced88df3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
