From 4f647534be5e3d588e30039ce45d3cac64a43308 Mon Sep 17 00:00:00 2001 From: bubbliiiing <3323290568@qq.com> Date: Wed, 18 Sep 2024 13:54:15 +0800 Subject: [PATCH] update readme --- README.md | 10 +++++----- README_zh-CN.md | 10 +++++----- cogvideox/api/api.py | 2 +- comfyui/README.md | 4 ++-- 4 files changed, 13 insertions(+), 13 deletions(-) diff --git a/README.md b/README.md index 03e8fc1..bbb920f 100644 --- a/README.md +++ b/README.md @@ -21,7 +21,7 @@ CogVideoX-Fun is a modified pipeline based on the CogVideoX structure, designed We will support quick pull-ups from different platforms, refer to [Quick Start](#quick-start). What's New: -- Create code! Now supporting Windows and Linux. Supports 2b and 5b models. Supports video generation at any resolution from 256x256x49 to 1024x1024x49. [ 2024.09.09 ] +- Create code! Now supporting Windows and Linux. Supports 2b and 5b models. Supports video generation at any resolution from 256x256x49 to 1024x1024x49. [ 2024.09.18 ] Function： - [Data Preprocessing](#data-preprocess) @@ -112,7 +112,7 @@ We'd better place the [weights](#model-zoo) along the specified path: # Video Result The results displayed are all based on image. -### CogVideoX-5B +### CogVideoX-Fun-5B Resolution-1024 @@ -171,7 +171,7 @@ Resolution-512 -### CogVideoX-2B +### CogVideoX-Fun-2B @@ -290,8 +290,8 @@ For details on setting some parameters, please refer to [Readme Train](scripts/R | Name | Storage Space | Url | Hugging Face | Description | |--|--|--|--|--| -| CogVideoX-Fun-2b-InP.tar.gz | Before extraction:9.69 GB \/ After extraction: 13.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-2b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-2b-InP)| Our official graph-generated video model is capable of predicting videos at multiple resolutions (512, 768, 1024, 1280) and has been trained on 144 frames at a rate of 24 frames per second. | -| CogVideoX-Fun-5b-InP.tar.gz | Before extraction:9.69 GB \/ After extraction: 13.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-5b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-5b-InP)| Our official graph-generated video model is capable of predicting videos at multiple resolutions (512, 768, 1024, 1280) and has been trained on 144 frames at a rate of 24 frames per second. | +| CogVideoX-Fun-2b-InP.tar.gz | Before extraction:9.7 GB \/ After extraction: 13.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-2b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-2b-InP)| Our official graph-generated video model is capable of predicting videos at multiple resolutions (512, 768, 1024, 1280) and has been trained on 49 frames at a rate of 24 frames per second. | +| CogVideoX-Fun-5b-InP.tar.gz | Before extraction:16.0 GB \/ After extraction: 20.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-5b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-5b-InP)| Our official graph-generated video model is capable of predicting videos at multiple resolutions (512, 768, 1024, 1280) and has been trained on 49 frames at a rate of 24 frames per second. | # TODO List - Support Chinese. diff --git a/README_zh-CN.md b/README_zh-CN.md index 42f2080..9ef4e8b 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -21,7 +21,7 @@ CogVideoX-Fun是一个基于CogVideoX结构修改后的的pipeline，是一个 我们会逐渐支持从不同平台快速启动，请参阅 [快速启动](#快速启动)。 新特性： -- 创建代码！现在支持 Windows 和 Linux。支持2b与5b最大256x256x49到1024x1024x49的任意分辨率的视频生成。[ 2024.09.09 ] +- 创建代码！现在支持 Windows 和 Linux。支持2b与5b最大256x256x49到1024x1024x49的任意分辨率的视频生成。[ 2024.09.18 ] 功能概览： - [数据预处理](#data-preprocess) @@ -110,7 +110,7 @@ Linux 的详细信息： # 视频作品 所展示的结果都是图生视频获得。 -### CogVideoX-5B +### CogVideoX-Fun-5B Resolution-1024 @@ -169,7 +169,7 @@ Resolution-512
-### CogVideoX-2B +### CogVideoX-Fun-2B Resolution-768 @@ -291,8 +291,8 @@ sh scripts/train.sh # 模型地址 | 名称 | 存储空间 | 下载地址 | Hugging Face | 描述 | |--|--|--|--|--| -| CogVideoX-Fun-2b-InP.tar.gz | 解压前 9.69 GB / 解压后 13.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-2b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-2b-InP)| 官方的图生视频权重。支持多分辨率（512，768，1024，1280）的视频预测，以144帧、每秒24帧进行训练 | -| CogVideoX-Fun-5b-InP.tar.gz | 解压前 9.69 GB / 解压后 13.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-5b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-5b-InP)| 官方的图生视频权重。支持多分辨率（512，768，1024，1280）的视频预测，以144帧、每秒24帧进行训练 | +| CogVideoX-Fun-2b-InP.tar.gz | 解压前 9.7 GB / 解压后 13.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-2b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-2b-InP)| 官方的图生视频权重。支持多分辨率（512，768，1024，1280）的视频预测，以49帧、每秒24帧进行训练 | +| CogVideoX-Fun-5b-InP.tar.gz | 解压前 16.0GB / 解压后 20.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-5b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-5b-InP)| 官方的图生视频权重。支持多分辨率（512，768，1024，1280）的视频预测，以49帧、每秒24帧进行训练 | # 未来计划 - 支持中文。 diff --git a/cogvideox/api/api.py b/cogvideox/api/api.py index 24d24fd..60c80bb 100644 --- a/cogvideox/api/api.py +++ b/cogvideox/api/api.py @@ -86,7 +86,7 @@ def infer_forward_api(_: gr.Blocks, app: FastAPI, controller): base_resolution = datas.get('base_resolution', 512) is_image = datas.get('is_image', False) generation_method = datas.get('generation_method', False) - length_slider = datas.get('length_slider', 144) + length_slider = datas.get('length_slider', 49) overlap_video_length = datas.get('overlap_video_length', 4) partial_video_length = datas.get('partial_video_length', 72) cfg_scale_slider = datas.get('cfg_scale_slider', 6) diff --git a/comfyui/README.md b/comfyui/README.md index a537784..d1faf34 100644 --- a/comfyui/README.md +++ b/comfyui/README.md @@ -30,8 +30,8 @@ python install.py | Name | Storage Space | Url | Hugging Face | Description | |--|--|--|--|--| -| CogVideoX-Fun-2b-InP.tar.gz | Before extraction:9.69 GB \/ After extraction: 13.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-2b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-2b-InP)| Our official graph-generated video model is capable of predicting videos at multiple resolutions (512, 768, 1024, 1280) and has been trained on 144 frames at a rate of 24 frames per second. | -| CogVideoX-Fun-5b-InP.tar.gz | Before extraction:9.69 GB \/ After extraction: 13.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-5b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-5b-InP)| Our official graph-generated video model is capable of predicting videos at multiple resolutions (512, 768, 1024, 1280) and has been trained on 144 frames at a rate of 24 frames per second. | +| CogVideoX-Fun-2b-InP.tar.gz | Before extraction:9.7 GB \/ After extraction: 13.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-2b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-2b-InP)| Our official graph-generated video model is capable of predicting videos at multiple resolutions (512, 768, 1024, 1280) and has been trained on 49 frames at a rate of 24 frames per second. | +| CogVideoX-Fun-5b-InP.tar.gz | Before extraction:16.0 GB \/ After extraction: 20.0 GB | [Download](https://pai-aigc-photog.oss-cn-hangzhou.aliyuncs.com/cogvideox_fun/Diffusion_Transformer/CogVideoX-Fun-5b-InP.tar.gz) | [🤗Link](https://huggingface.co/alibaba-pai/CogVideoX-Fun-5b-InP)| Our official graph-generated video model is capable of predicting videos at multiple resolutions (512, 768, 1024, 1280) and has been trained on 49 frames at a rate of 24 frames per second. | ## Node types - **LoadCogVideoX_Fun_Model**