Merge branch 'dev-1.x' into fix-rand_degradation

.circleci/test.yml

@@ -144,7 +144,7 @@ workflows:
           name: minimum_version_cpu
           torch: 1.6.0
           torchvision: 0.7.0
-          python: 3.6.9  # The lowest python 3.6.x version available on CircleCI images
+          python: 3.7.4
           requires:
             - lint
       - build_cpu:

.github/workflows/merge_stage_test.yml

@@ -26,7 +26,7 @@ jobs:
     runs-on: ubuntu-18.04
     strategy:
       matrix:
-        python-version: [3.6, 3.8, 3.9]
+        python-version: [3.8, 3.9]
         torch: [1.8.1]
         include:
           - torch: 1.8.1

.gitignore

@@ -124,6 +124,7 @@ mmedit/.mim
 demo/*.png
 *.csv
 out/*.png
+resources/
 
 # Pytorch
 *.pth

configs/stable_diffusion/README.md

@@ -10,13 +10,34 @@
 
 <!-- [ABSTRACT] -->
 
-Stable Diffusion is a latent diffusion model conditioned on the text embeddings of a CLIP text encoder, which allows you to create images from text inputs.
+Stable Diffusion is a latent diffusion model conditioned on the text embeddings of a CLIP text encoder, which allows you to create images from text inputs. This model builds upon the CVPR'22 work [High-Resolution Image Synthesis with Latent Diffusion Models](https://ommer-lab.com/research/latent-diffusion-models/). The official code was released at [stable-diffusion](https://github.com/CompVis/stable-diffusion) and also implemented at [diffusers](https://github.com/huggingface/diffusers). We support this algorithm here to facilitate the community to learn together and compare it with other text2image methods.
 
 <!-- [IMAGE] -->
 
-<div align=center >
- <img src="https://user-images.githubusercontent.com/12782558/209609229-8221c7cc-d5c9-44d5-a1af-c254b5a95fae.png" width="400"/>
-</div >
+<table align="center">
+<thead>
+  <tr>
+    <td>
+<div align="center">
+  <img src="https://user-images.githubusercontent.com/12782558/209609229-8221c7cc-d5c9-44d5-a1af-c254b5a95fae.png" width="400"/>
+  <br/>
+  <b>A mecha robot in a favela in expressionist style</b>
+</div></td>
+    <td>
+<div align="center">
+  <img src="https://user-images.githubusercontent.com/12782558/210951970-a81e80c3-822e-4782-901e-db52e34b85a3.png" width="400"/>
+  <br/>
+  <b>A Chinese palace is beside a beautiful lake</b>
+</div></td>
+    <td>
+<div align="center">
+  <img src="https://user-images.githubusercontent.com/12782558/210952108-df82e5ad-6eb6-4948-8d22-3802299d1131.png" width="400"/>
+  <br/>
+  <b>A panda is having dinner in KFC</b>
+</div></td>
+  </tr>
+</thead>
+</table>
 
 ## Pretrained models
 

mmedit/datasets/transforms/aug_pixel.py

@@ -20,8 +20,8 @@ class BinarizeImage(BaseTransform):
     Args:
         keys (Sequence[str]): The images to be binarized.
         binary_thr (float): Threshold for binarization.
-        amin (int): Lower limits of pixel value.
-        amx (int): Upper limits of pixel value.
+        a_min (int): Lower limits of pixel value.
+        a_max (int): Upper limits of pixel value.
         dtype (np.dtype): Set the data type of the output. Default: np.uint8
     """
 
@@ -86,8 +86,8 @@ class Clip(BaseTransform):
 
     Args:
         keys (list[str]): The keys whose values are clipped.
-        amin (int): Lower limits of pixel value.
-        amx (int): Upper limits of pixel value.
+        a_min (int): Lower limits of pixel value.
+        a_max (int): Upper limits of pixel value.
     """
 
     def __init__(self, keys, a_min=0, a_max=255):

setup.py

@@ -252,7 +252,6 @@ def add_mim_extention():
             'License :: OSI Approved :: Apache Software License',
             'Operating System :: OS Independent',
             'Programming Language :: Python :: 3',
-            'Programming Language :: Python :: 3.6',
             'Programming Language :: Python :: 3.7',
             'Programming Language :: Python :: 3.8',
             'Programming Language :: Python :: 3.9',