auto-diffusers 2.0.13__tar.gz → 2.0.16__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,160 @@
1
+ Metadata-Version: 2.1
2
+ Name: auto_diffusers
3
+ Version: 2.0.16
4
+ Summary: Customized diffusers with model search and other functions.
5
+ Home-page: https://github.com/suzukimain/auto_diffusers
6
+ Author: suzukimain
7
+ Author-email: subarucosmosmain@gmail.com
8
+ License: Apache 2.0 License
9
+ Keywords: huggingface civitai diffusers model search deep learning diffusion pytorch stable diffusion
10
+ Classifier: Development Status :: 5 - Production/Stable
11
+ Classifier: Intended Audience :: Developers
12
+ Classifier: Intended Audience :: Education
13
+ Classifier: Intended Audience :: Science/Research
14
+ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
15
+ Classifier: Programming Language :: Python :: 3
16
+ Classifier: Programming Language :: Python :: 3.8
17
+ Classifier: Programming Language :: Python :: 3.9
18
+ Classifier: Programming Language :: Python :: 3.10
19
+ Classifier: Programming Language :: Python :: 3.11
20
+ Classifier: Programming Language :: Python :: 3.12
21
+ Description-Content-Type: text/markdown
22
+ License-File: LICENSE
23
+ Requires-Dist: torch
24
+ Requires-Dist: diffusers
25
+ Requires-Dist: huggingface-hub>=0.26.2
26
+
27
+ # auto_diffusers
28
+
29
+
30
+ <p>
31
+ <a href="https://github.com/suzukimain/auto_diffusers/blob/main/LICENSE"><img alt="GitHub release" src="https://img.shields.io/badge/license-Apache%202.0-blue.svg?style=social"></a>
32
+ </p>
33
+ <p>
34
+ <a href="https://pepy.tech/project/auto_diffusers"><img alt="GitHub release" src="https://static.pepy.tech/badge/auto_diffusers"></a>
35
+ <a href="https://github.com/suzukimain/auto_diffusers/releases"><img alt="GitHub release" src="https://img.shields.io/github/release/suzukimain/auto_diffusers.svg"></a>
36
+ <img src="https://visitor-badge.laobi.icu/badge?page_id=suzukimain.auto_diffusers" alt="Visitor Badge">
37
+ </p>
38
+
39
+
40
+ >CONTENTS
41
+ + [About The Project](#About_The_Project)
42
+ + [How to use](#How_to_use)
43
+ + [Search Hubs](#Search_Civitai_and_Huggingfacee)
44
+ - [Search Civitai](#Search_Civitai)
45
+ - [Search Huggingface](#Search_Huggingface)
46
+ + [License](#License)
47
+ + [Acknowledgement](#Acknowledgement)
48
+
49
+ ## About The Project<a name = "About_The_Project"></a>
50
+ Enhance the functionality of diffusers.
51
+ * Search models from huggingface and Civitai.
52
+
53
+
54
+ ## How to use<a name = "How_to_use"></a>
55
+
56
+ ```python
57
+ pip install --quiet auto_diffusers
58
+ ```
59
+
60
+ ```python
61
+ from auto_diffusers import EasyPipelineForText2Image
62
+
63
+ # Search for Huggingface
64
+ pipe = EasyPipelineForText2Image.from_huggingface("search_word").to("cuda")
65
+ img = pipe("cat").images[0]
66
+ img.save("cat.png")
67
+
68
+
69
+ # Search for Civitai
70
+ pipe = EasyPipelineForText2Image.from_civitai("search_word").to("cuda")
71
+ image = pipe("cat").images[0]
72
+ image.save("cat.png")
73
+
74
+ ```
75
+
76
+ ## Search Civitai and Huggingfacee<a name = "Search_Civitai_and_Huggingface"></a>
77
+
78
+ ```python
79
+ # Load Lora into the pipeline.
80
+ pipe.auto_load_lora_weights("Detail Tweaker")
81
+
82
+ # Load TextualInversion into the pipeline.
83
+ pipe.auto_load_textual_inversion("EasyNegative", token="EasyNegative")
84
+ ```
85
+
86
+ ### Search Civitai<a name = "Search_Civitai"></a>
87
+
88
+ > [!TIP]
89
+ > **If an error occurs, insert the `token` and run again.**
90
+
91
+ #### `EasyPipeline.from_civitai` parameters
92
+
93
+ | Name | Type | Default | Description |
94
+ |:---------------:|:----------------------:|:-------------:|:-----------------------------------------------------------------------------------:|
95
+ | search_word | string, Path | ー | The search query string. Can be a keyword, Civitai URL, local directory or file path. |
96
+ | model_type | string | `Checkpoint` | The type of model to search for. <br>(for example `Checkpoint`, `TextualInversion`, `Controlnet`, `LORA`, `Hypernetwork`, `AestheticGradient`, `Poses`) |
97
+ | base_model | string | None | Trained model tag (for example `SD 1.5`, `SD 3.5`, `SDXL 1.0`) |
98
+ | torch_dtype | string, torch.dtype | None | Override the default `torch.dtype` and load the model with another dtype. |
99
+ | 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. |
100
+ | cache_dir | string, Path | None | Path to the folder where cached files are stored. |
101
+ | resume | bool | False | Whether to resume an incomplete download. |
102
+ | token | string | None | API token for Civitai authentication. |
103
+
104
+
105
+ #### `search_civitai` parameters
106
+
107
+ | Name | Type | Default | Description |
108
+ |:---------------:|:--------------:|:-------------:|:-----------------------------------------------------------------------------------:|
109
+ | search_word | string, Path | ー | The search query string. Can be a keyword, Civitai URL, local directory or file path. |
110
+ | model_type | string | `Checkpoint` | The type of model to search for. <br>(for example `Checkpoint`, `TextualInversion`, `Controlnet`, `LORA`, `Hypernetwork`, `AestheticGradient`, `Poses`) |
111
+ | base_model | string | None | Trained model tag (for example `SD 1.5`, `SD 3.5`, `SDXL 1.0`) |
112
+ | download | bool | False | Whether to download the model. |
113
+ | force_download | bool | False | Whether to force the download if the model already exists. |
114
+ | cache_dir | string, Path | None | Path to the folder where cached files are stored. |
115
+ | resume | bool | False | Whether to resume an incomplete download. |
116
+ | token | string | None | API token for Civitai authentication. |
117
+ | include_params | bool | False | Whether to include parameters in the returned data. |
118
+ | skip_error | bool | False | Whether to skip errors and return None. |
119
+
120
+ ### Search Huggingface<a name = "Search_Huggingface"></a>
121
+
122
+ > [!TIP]
123
+ > **If an error occurs, insert the `token` and run again.**
124
+
125
+ #### `EasyPipeline.from_huggingface` parameters
126
+
127
+ | Name | Type | Default | Description |
128
+ |:---------------------:|:-------------------:|:--------------:|:----------------------------------------------------------------:|
129
+ | search_word | string, Path | ー | The search query string. Can be a keyword, Hugging Face URL, local directory or file path, or a Hugging Face path (`<creator>/<repo>`). |
130
+ | checkpoint_format | string | `single_file` | The format of the model checkpoint.<br>● `single_file` to search for `single file checkpoint` <br>●`diffusers` to search for `multifolder diffusers format checkpoint` |
131
+ | torch_dtype | string, torch.dtype | None | Override the default `torch.dtype` and load the model with another dtype. |
132
+ | 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. |
133
+ | cache_dir | string, Path | None | Path to a directory where a downloaded pretrained model configuration is cached if the standard cache is not used. |
134
+ | token | string, bool | None | The token to use as HTTP bearer authorization for remote files. |
135
+
136
+
137
+ #### `search_huggingface` parameters
138
+
139
+ | Name | Type | Default | Description |
140
+ |:---------------------:|:-------------------:|:--------------:|:----------------------------------------------------------------:|
141
+ | search_word | string, Path | ー | The search query string. Can be a keyword, Hugging Face URL, local directory or file path, or a Hugging Face path (`<creator>/<repo>`). |
142
+ | checkpoint_format | string | `single_file` | The format of the model checkpoint. <br>● `single_file` to search for `single file checkpoint` <br>●`diffusers` to search for `multifolder diffusers format checkpoint` |
143
+ | pipeline_tag | string | None | Tag to filter models by pipeline. |
144
+ | download | bool | False | Whether to download the model. |
145
+ | 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. |
146
+ | cache_dir | string, Path | None | Path to a directory where a downloaded pretrained model configuration is cached if the standard cache is not used. |
147
+ | token | string, bool | None | The token to use as HTTP bearer authorization for remote files. |
148
+ | include_params | bool | False | Whether to include parameters in the returned data. |
149
+ | skip_error | bool | False | Whether to skip errors and return None. |
150
+
151
+
152
+ ## License<a name = "License"></a>
153
+ In accordance with [Apache-2.0 license](https://github.com/suzukimain/auto_diffusers/blob/master/LICENSE)
154
+
155
+
156
+ ## Acknowledgement<a name = "Acknowledgement"></a>
157
+
158
+ I have used open source resources and free tools in the creation of this project.
159
+
160
+ I would like to take this opportunity to thank the open source community and those who provided free tools.
@@ -0,0 +1,134 @@
1
+ # auto_diffusers
2
+
3
+
4
+ <p>
5
+ <a href="https://github.com/suzukimain/auto_diffusers/blob/main/LICENSE"><img alt="GitHub release" src="https://img.shields.io/badge/license-Apache%202.0-blue.svg?style=social"></a>
6
+ </p>
7
+ <p>
8
+ <a href="https://pepy.tech/project/auto_diffusers"><img alt="GitHub release" src="https://static.pepy.tech/badge/auto_diffusers"></a>
9
+ <a href="https://github.com/suzukimain/auto_diffusers/releases"><img alt="GitHub release" src="https://img.shields.io/github/release/suzukimain/auto_diffusers.svg"></a>
10
+ <img src="https://visitor-badge.laobi.icu/badge?page_id=suzukimain.auto_diffusers" alt="Visitor Badge">
11
+ </p>
12
+
13
+
14
+ >CONTENTS
15
+ + [About The Project](#About_The_Project)
16
+ + [How to use](#How_to_use)
17
+ + [Search Hubs](#Search_Civitai_and_Huggingfacee)
18
+ - [Search Civitai](#Search_Civitai)
19
+ - [Search Huggingface](#Search_Huggingface)
20
+ + [License](#License)
21
+ + [Acknowledgement](#Acknowledgement)
22
+
23
+ ## About The Project<a name = "About_The_Project"></a>
24
+ Enhance the functionality of diffusers.
25
+ * Search models from huggingface and Civitai.
26
+
27
+
28
+ ## How to use<a name = "How_to_use"></a>
29
+
30
+ ```python
31
+ pip install --quiet auto_diffusers
32
+ ```
33
+
34
+ ```python
35
+ from auto_diffusers import EasyPipelineForText2Image
36
+
37
+ # Search for Huggingface
38
+ pipe = EasyPipelineForText2Image.from_huggingface("search_word").to("cuda")
39
+ img = pipe("cat").images[0]
40
+ img.save("cat.png")
41
+
42
+
43
+ # Search for Civitai
44
+ pipe = EasyPipelineForText2Image.from_civitai("search_word").to("cuda")
45
+ image = pipe("cat").images[0]
46
+ image.save("cat.png")
47
+
48
+ ```
49
+
50
+ ## Search Civitai and Huggingfacee<a name = "Search_Civitai_and_Huggingface"></a>
51
+
52
+ ```python
53
+ # Load Lora into the pipeline.
54
+ pipe.auto_load_lora_weights("Detail Tweaker")
55
+
56
+ # Load TextualInversion into the pipeline.
57
+ pipe.auto_load_textual_inversion("EasyNegative", token="EasyNegative")
58
+ ```
59
+
60
+ ### Search Civitai<a name = "Search_Civitai"></a>
61
+
62
+ > [!TIP]
63
+ > **If an error occurs, insert the `token` and run again.**
64
+
65
+ #### `EasyPipeline.from_civitai` parameters
66
+
67
+ | Name | Type | Default | Description |
68
+ |:---------------:|:----------------------:|:-------------:|:-----------------------------------------------------------------------------------:|
69
+ | search_word | string, Path | ー | The search query string. Can be a keyword, Civitai URL, local directory or file path. |
70
+ | model_type | string | `Checkpoint` | The type of model to search for. <br>(for example `Checkpoint`, `TextualInversion`, `Controlnet`, `LORA`, `Hypernetwork`, `AestheticGradient`, `Poses`) |
71
+ | base_model | string | None | Trained model tag (for example `SD 1.5`, `SD 3.5`, `SDXL 1.0`) |
72
+ | torch_dtype | string, torch.dtype | None | Override the default `torch.dtype` and load the model with another dtype. |
73
+ | 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. |
74
+ | cache_dir | string, Path | None | Path to the folder where cached files are stored. |
75
+ | resume | bool | False | Whether to resume an incomplete download. |
76
+ | token | string | None | API token for Civitai authentication. |
77
+
78
+
79
+ #### `search_civitai` parameters
80
+
81
+ | Name | Type | Default | Description |
82
+ |:---------------:|:--------------:|:-------------:|:-----------------------------------------------------------------------------------:|
83
+ | search_word | string, Path | ー | The search query string. Can be a keyword, Civitai URL, local directory or file path. |
84
+ | model_type | string | `Checkpoint` | The type of model to search for. <br>(for example `Checkpoint`, `TextualInversion`, `Controlnet`, `LORA`, `Hypernetwork`, `AestheticGradient`, `Poses`) |
85
+ | base_model | string | None | Trained model tag (for example `SD 1.5`, `SD 3.5`, `SDXL 1.0`) |
86
+ | download | bool | False | Whether to download the model. |
87
+ | force_download | bool | False | Whether to force the download if the model already exists. |
88
+ | cache_dir | string, Path | None | Path to the folder where cached files are stored. |
89
+ | resume | bool | False | Whether to resume an incomplete download. |
90
+ | token | string | None | API token for Civitai authentication. |
91
+ | include_params | bool | False | Whether to include parameters in the returned data. |
92
+ | skip_error | bool | False | Whether to skip errors and return None. |
93
+
94
+ ### Search Huggingface<a name = "Search_Huggingface"></a>
95
+
96
+ > [!TIP]
97
+ > **If an error occurs, insert the `token` and run again.**
98
+
99
+ #### `EasyPipeline.from_huggingface` parameters
100
+
101
+ | Name | Type | Default | Description |
102
+ |:---------------------:|:-------------------:|:--------------:|:----------------------------------------------------------------:|
103
+ | search_word | string, Path | ー | The search query string. Can be a keyword, Hugging Face URL, local directory or file path, or a Hugging Face path (`<creator>/<repo>`). |
104
+ | checkpoint_format | string | `single_file` | The format of the model checkpoint.<br>● `single_file` to search for `single file checkpoint` <br>●`diffusers` to search for `multifolder diffusers format checkpoint` |
105
+ | torch_dtype | string, torch.dtype | None | Override the default `torch.dtype` and load the model with another dtype. |
106
+ | 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. |
107
+ | cache_dir | string, Path | None | Path to a directory where a downloaded pretrained model configuration is cached if the standard cache is not used. |
108
+ | token | string, bool | None | The token to use as HTTP bearer authorization for remote files. |
109
+
110
+
111
+ #### `search_huggingface` parameters
112
+
113
+ | Name | Type | Default | Description |
114
+ |:---------------------:|:-------------------:|:--------------:|:----------------------------------------------------------------:|
115
+ | search_word | string, Path | ー | The search query string. Can be a keyword, Hugging Face URL, local directory or file path, or a Hugging Face path (`<creator>/<repo>`). |
116
+ | checkpoint_format | string | `single_file` | The format of the model checkpoint. <br>● `single_file` to search for `single file checkpoint` <br>●`diffusers` to search for `multifolder diffusers format checkpoint` |
117
+ | pipeline_tag | string | None | Tag to filter models by pipeline. |
118
+ | download | bool | False | Whether to download the model. |
119
+ | 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. |
120
+ | cache_dir | string, Path | None | Path to a directory where a downloaded pretrained model configuration is cached if the standard cache is not used. |
121
+ | token | string, bool | None | The token to use as HTTP bearer authorization for remote files. |
122
+ | include_params | bool | False | Whether to include parameters in the returned data. |
123
+ | skip_error | bool | False | Whether to skip errors and return None. |
124
+
125
+
126
+ ## License<a name = "License"></a>
127
+ In accordance with [Apache-2.0 license](https://github.com/suzukimain/auto_diffusers/blob/master/LICENSE)
128
+
129
+
130
+ ## Acknowledgement<a name = "Acknowledgement"></a>
131
+
132
+ I have used open source resources and free tools in the creation of this project.
133
+
134
+ I would like to take this opportunity to thank the open source community and those who provided free tools.
@@ -0,0 +1 @@
1
+ 2.0.16