规范化

.github/ISSUE_TEMPLATE/bug_report.yaml

@@ -0,0 +1,51 @@
+name: "\U0001F41B Bug Report"
+description: Submit a bug report to help us improve CogVideoX / 提交一个 Bug 问题报告来帮助我们改进 CogVideoX 开源模型
+body:
+  - type: textarea
+    id: system-info
+    attributes:
+      label: System Info / 系統信息
+      description: Your operating environment / 您的运行环境信息
+      placeholder: Includes Cuda version, Diffusers version, Python version, operating system, hardware information (if you suspect a hardware problem)... / 包括Cuda版本，Diffusers，Python版本，操作系统，硬件信息(如果您怀疑是硬件方面的问题)...
+    validations:
+      required: true
+
+  - type: checkboxes
+    id: information-scripts-examples
+    attributes:
+      label: Information / 问题信息
+      description: 'The problem arises when using: / 问题出现在'
+      options:
+        - label: "The official example scripts / 官方的示例脚本"
+        - label: "My own modified scripts / 我自己修改的脚本和任务"
+
+  - type: textarea
+    id: reproduction
+    validations:
+      required: true
+    attributes:
+      label: Reproduction / 复现过程
+      description: |
+        Please provide a code example that reproduces the problem you encountered, preferably with a minimal reproduction unit.
+        If you have code snippets, error messages, stack traces, please provide them here as well.
+        Please format your code correctly using code tags. See https://help.github.com/en/github/writing-on-github/creating-and-highlighting-code-blocks#syntax-highlighting
+        Do not use screenshots, as they are difficult to read and (more importantly) do not allow others to copy and paste your code.
+        
+        请提供能重现您遇到的问题的代码示例,最好是最小复现单元。
+        如果您有代码片段、错误信息、堆栈跟踪，也请在此提供。
+        请使用代码标签正确格式化您的代码。请参见 https://help.github.com/en/github/writing-on-github/creating-and-highlighting-code-blocks#syntax-highlighting
+        请勿使用截图，因为截图难以阅读，而且（更重要的是）不允许他人复制粘贴您的代码。
+      placeholder: |
+        Steps to reproduce the behavior/复现Bug的步骤:
+          
+          1.
+          2.
+          3.
+
+  - type: textarea
+    id: expected-behavior
+    validations:
+      required: true
+    attributes:
+      label: Expected behavior / 期待表现
+      description: "A clear and concise description of what you would expect to happen. /简单描述您期望发生的事情。"

.github/ISSUE_TEMPLATE/feature-request.yaml

@@ -0,0 +1,34 @@
+name: "\U0001F680 Feature request"
+description: Submit a request for a new CogVideoX feature / 提交一个新的 CogVideoX开源模型的功能建议
+labels: [ "feature" ]
+body:
+  - type: textarea
+    id: feature-request
+    validations:
+      required: true
+    attributes:
+      label: Feature request  / 功能建议
+      description: |
+        A brief description of the functional proposal. Links to corresponding papers and code are desirable.
+        对功能建议的简述。最好提供对应的论文和代码链接。
+
+  - type: textarea
+    id: motivation
+    validations:
+      required: true
+    attributes:
+      label: Motivation / 动机
+      description: |
+        Your motivation for making the suggestion. If that motivation is related to another GitHub issue, link to it here.
+        您提出建议的动机。如果该动机与另一个 GitHub 问题有关，请在此处提供对应的链接。
+
+  - type: textarea
+    id: contribution
+    validations:
+      required: true
+    attributes:
+      label: Your contribution / 您的贡献
+      description: |
+        
+        Your PR link or any other link you can help with.
+        您的PR链接或者其他您能提供帮助的链接。

.github/PULL_REQUEST_TEMPLATE/pr_template.md

@@ -0,0 +1,34 @@
+#  Raise valuable PR / 提出有价值的PR
+
+## Caution / 注意事项:
+Users should keep the following points in mind when submitting PRs:
+
+1. Ensure that your code meets the requirements in the [specification](../../resources/contribute.md).
+2. the proposed PR should be relevant, if there are multiple ideas and optimizations, they should be assigned to different PRs.
+
+用户在提交PR时候应该注意以下几点:
+
+1. 确保您的代码符合 [规范](../../resources/contribute_zh.md) 中的要求。
+2. 提出的PR应该具有针对性，如果具有多个不同的想法和优化方案，应该分配到不同的PR中。
+
+## 不应该提出的PR / PRs that should not be proposed
+
+If a developer proposes a PR about any of the following, it may be closed or Rejected.
+
+1. those that don't describe improvement options.
+2. multiple issues of different types combined in one PR.
+3. The proposed PR is highly duplicative of already existing PRs.
+
+如果开发者提出关于以下方面的PR，则可能会被直接关闭或拒绝通过。
+
+1. 没有说明改进方案的。
+2. 多个不同类型的问题合并在一个PR中的。
+3. 提出的PR与已经存在的PR高度重复的。
+
+
+# 检查您的PR
+- [ ] Have you read the Contributor Guidelines, Pull Request section? / 您是否阅读了贡献者指南、Pull Request 部分？
+- [ ] Has this been discussed/approved via a Github issue or forum? If so, add a link. / 是否通过 Github 问题或论坛讨论/批准过？如果是，请添加链接。
+- [ ] Did you make sure you updated the documentation with your changes? Here are the Documentation Guidelines, and here are the Documentation Formatting Tips. /您是否确保根据您的更改更新了文档？这里是文档指南，这里是文档格式化技巧。
+- [ ] Did you write new required tests? / 您是否编写了新的必要测试？
+- [ ]  Are your PRs for only one issue / 您的PR是否仅针对一个问题

sat/data_video.py

@@ -425,7 +425,7 @@ def nearest_smaller_4k_plus_1(n):
                     self.videos_list.append(tensor_frms)
 
                     # caption
-                    caption_path = os.path.join(root, filename.replace('videos', 'labels').replace('.mp4', '.txt'))
+                    caption_path = os.path.join(root, filename.replace("videos", "labels").replace(".mp4", ".txt"))
                     if os.path.exists(caption_path):
                         caption = open(caption_path, "r").read().splitlines()[0]
                     else:

sat/sample_video.py

@@ -178,18 +178,18 @@ def sampling_main(args, model_cls):
                     shape=(T, C, H // F, W // F),
                 )
                 samples_z = samples_z.permute(0, 2, 1, 3, 4).contiguous()
-                
+
                 # Unload the model from GPU to save GPU memory
-                model.to('cpu')
+                model.to("cpu")
                 torch.cuda.empty_cache()
                 first_stage_model = model.first_stage_model
                 first_stage_model = first_stage_model.to(device)
 
                 latent = 1.0 / model.scale_factor * samples_z
-                
+
                 # Decode latent serial to save GPU memory
                 recons = []
-                loop_num = (T-1)//2
+                loop_num = (T - 1) // 2
                 for i in range(loop_num):
                     if i == 0:
                         start_frame, end_frame = 0, 3
@@ -200,20 +200,23 @@ def sampling_main(args, model_cls):
                     else:
                         clear_fake_cp_cache = False
                     with torch.no_grad():
-                        recon = first_stage_model.decode(latent[:, :, start_frame:end_frame].contiguous(), clear_fake_cp_cache=clear_fake_cp_cache)
+                        recon = first_stage_model.decode(
+                            latent[:, :, start_frame:end_frame].contiguous(), clear_fake_cp_cache=clear_fake_cp_cache
+                        )
 
                     recons.append(recon)
 
                 recon = torch.cat(recons, dim=2).to(torch.float32)
                 samples_x = recon.permute(0, 2, 1, 3, 4).contiguous()
                 samples = torch.clamp((samples_x + 1.0) / 2.0, min=0.0, max=1.0).cpu()
 
-                save_path = os.path.join(args.output_dir, str(cnt) + '_' + text.replace(' ', '_').replace('/', '')[:120], str(index))
+                save_path = os.path.join(
+                    args.output_dir, str(cnt) + "_" + text.replace(" ", "_").replace("/", "")[:120], str(index)
+                )
                 if mpu.get_model_parallel_rank() == 0:
                     save_video_as_grid_and_mp4(samples, save_path, fps=args.sampling_fps)
 
 
-
 if __name__ == "__main__":
     if "OMPI_COMM_WORLD_LOCAL_RANK" in os.environ:
         os.environ["LOCAL_RANK"] = os.environ["OMPI_COMM_WORLD_LOCAL_RANK"]