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
<font size="10"><b>M</b>ultimodal <b>A</b>dvanced, <b>G</b>enerative, and <b>I</b>ntelligent <b>C</b>reation (MMagic [em'mædʒɪk])</font>
6
+
</div>
7
+
<div> </div>
4
8
<divalign="center">
5
9
<b><font size="5">OpenMMLab website</font></b>
6
10
<sup>
@@ -57,7 +61,7 @@ English | [简体中文](README_zh-CN.md)
57
61
58
62
We are excited to announce the release of MMagic v1.0.0 that inherits from [MMEditing](https://github.com/open-mmlab/mmediting) and [MMGeneration](https://github.com/open-mmlab/mmgeneration).
59
63
60
-
After iterative updates with OpenMMLab 2.0 framework and merged with MMGeneration, MMEditing has become a powerful tool that supports low-level algorithms based on both GAN and CNN. Today, MMEditing embraces the Diffusion Model and transforms into a more advanced and comprehensive AIGC toolkit: **MMagic** (**M**ultimodal **A**dvanced, **G**enerative, and **I**ntelligent **C**reation). MMagic will provide more agile and flexible experimental support for researchers and AIGC enthusiasts, and help you on your AIGC exploration journey.
64
+
After iterative updates with OpenMMLab 2.0 framework and merged with MMGeneration, MMEditing has become a powerful tool that supports low-level algorithms based on both GAN and CNN. Today, MMEditing embraces Generative AI and transforms into a more advanced and comprehensive AIGC toolkit: **MMagic** (**M**ultimodal **A**dvanced, **G**enerative, and **I**ntelligent **C**reation). MMagic will provide more agile and flexible experimental support for researchers and AIGC enthusiasts, and help you on your AIGC exploration journey.
61
65
62
66
We highlight the following new features.
63
67
@@ -110,14 +114,14 @@ Please refer to [migration documents](docs/en/migration/overview.md) to migrate
<palign="right"><ahref="#top">🔝Back to top</a></p>
123
127
@@ -143,7 +147,7 @@ The best practice on our main branch works with **Python 3.8+** and **PyTorch 1.
143
147
144
148
-**Efficient Framework**
145
149
146
-
By using MMEngine and MMCV of OpenMMLab 2.0 framework, MMagic decompose the editing framework into different modules and one can easily construct a customized editor framework by combining different module. We can define the training process just like playing with Legos and provide rich components and strategies. In MMagic, you can complete controls on the training process with different levels of APIs. With the support of [MMSeparateDistributedDataParallel](https://github.com/open-mmlab/mmengine/blob/main/mmengine/model/wrappers/seperate_distributed.py), distributed training for dynamic architectures can be easily implemented.
150
+
By using MMEngine and MMCV of OpenMMLab 2.0 framework, MMagic decompose the editing framework into different modules and one can easily construct a customized editor framework by combining different modules. We can define the training process just like playing with Legos and provide rich components and strategies. In MMagic, you can complete controls on the training process with different levels of APIs. With the support of [MMSeparateDistributedDataParallel](https://github.com/open-mmlab/mmengine/blob/main/mmengine/model/wrappers/seperate_distributed.py), distributed training for dynamic architectures can be easily implemented.
147
151
148
152
<palign="right"><ahref="#top">🔝Back to top</a></p>
After installing MMagic successfully, now you are able to play with MMagic! To generate an image from text, you only need several lines of codes by MMagic!
193
198
194
199
```python
@@ -365,12 +370,12 @@ Please refer to [installation](docs/en/get_started/install.md) for more detailed
Copy file name to clipboardExpand all lines: docs/en/changelog.md
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -8,9 +8,9 @@ We are excited to announce the release of MMagic v1.0.0 that inherits from [MMEd
8
8
9
9
Since its inception, MMEditing has been the preferred algorithm library for many super-resolution, editing, and generation tasks, helping research teams win more than 10 top international competitions and supporting over 100 GitHub ecosystem projects. After iterative updates with OpenMMLab 2.0 framework and merged with MMGeneration, MMEditing has become a powerful tool that supports low-level algorithms based on both GAN and CNN.
10
10
11
-
Today, MMEditing embraces the Diffusion Model and transforms into a more advanced and comprehensive AIGC toolkit: **MMagic** (**M**ultimodal **A**dvanced, **G**enerative, and **I**ntelligent **C**reation).
11
+
Today, MMEditing embraces Generative AI and transforms into a more advanced and comprehensive AIGC toolkit: **MMagic** (**M**ultimodal **A**dvanced, **G**enerative, and **I**ntelligent **C**reation).
12
12
13
-
In MMagic, we have supports 53+ models in multiple tasks such as fine-tuning for stable diffusion, text-to-image, image and video restoration, super-resolution, editing and generation. With excellent training and experiment management support from [MMEngine](https://github.com/open-mmlab/mmengine), MMagic will provide more agile and flexible experimental support for researchers and AIGC enthusiasts, and help you on your AIGC exploration journey. With MMagic, experience more magic in generation! Let's open a new era beyond editing together. More than Editing, Unlock the Magic!
13
+
In MMagic, we have supported 53+ models in multiple tasks such as fine-tuning for stable diffusion, text-to-image, image and video restoration, super-resolution, editing and generation. With excellent training and experiment management support from [MMEngine](https://github.com/open-mmlab/mmengine), MMagic will provide more agile and flexible experimental support for researchers and AIGC enthusiasts, and help you on your AIGC exploration journey. With MMagic, experience more magic in generation! Let's open a new era beyond editing together. More than Editing, Unlock the Magic!
14
14
15
15
**Highlights**
16
16
@@ -51,15 +51,15 @@ For the Diffusion Model, we provide the following "magic" :
51
51
52
52
- Support video generation based on MultiFrame Render.
53
53
MMagic supports the generation of long videos in various styles through ControlNet and MultiFrame Render.
54
-
prompt key words: a handsome man, silver hair, smiling, play basketball
54
+
prompt keywords: a handsome man, silver hair, smiling, play basketball
@@ -74,7 +74,7 @@ For the Diffusion Model, we provide the following "magic" :
74
74
75
75
To improve your "spellcasting" efficiency, we have made the following adjustments to the "magic circuit":
76
76
77
-
- By using MMEngine and MMCV of OpenMMLab 2.0 framework, We decompose the editing framework into different modules and one can easily construct a customized editor framework by combining different module. We can define the training process just like playing with Legos and provide rich components and strategies. In MMagic, you can complete controls on the training process with different levels of APIs.
77
+
- By using MMEngine and MMCV of OpenMMLab 2.0 framework, We decompose the editing framework into different modules and one can easily construct a customized editor framework by combining different modules. We can define the training process just like playing with Legos and provide rich components and strategies. In MMagic, you can complete controls on the training process with different levels of APIs.
78
78
- Support for 33+ algorithms accelerated by Pytorch 2.0.
79
79
- Refactor DataSample to support the combination and splitting of batch dimensions.
80
80
- Refactor DataPreprocessor and unify the data format for various tasks during training and inference.
Copy file name to clipboardExpand all lines: docs/en/get_started/overview.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -58,7 +58,7 @@ MMagic supports various applications, including:
58
58
59
59
-**Efficient Framework**
60
60
61
-
By using MMEngine and MMCV of OpenMMLab 2.0 framework, MMagic decompose the editing framework into different modules and one can easily construct a customized editor framework by combining different module. We can define the training process just like playing with Legos and provide rich components and strategies. In MMagic, you can complete controls on the training process with different levels of APIs. With the support of [MMSeparateDistributedDataParallel](https://github.com/open-mmlab/mmengine/blob/main/mmengine/model/wrappers/seperate_distributed.py), distributed training for dynamic architectures can be easily implemented.
61
+
By using MMEngine and MMCV of OpenMMLab 2.0 framework, MMagic decompose the editing framework into different modules and one can easily construct a customized editor framework by combining different modules. We can define the training process just like playing with Legos and provide rich components and strategies. In MMagic, you can complete controls on the training process with different levels of APIs. With the support of [MMSeparateDistributedDataParallel](https://github.com/open-mmlab/mmengine/blob/main/mmengine/model/wrappers/seperate_distributed.py), distributed training for dynamic architectures can be easily implemented.
0 commit comments