From 96c1df89e6dc1904b847c6281e7e1c1f95d4dfd1 Mon Sep 17 00:00:00 2001 From: bubbliiiing <3323290568@qq.com> Date: Thu, 19 Sep 2024 15:44:11 +0800 Subject: [PATCH] update readme and prompts --- README.md | 10 ++++++---- README_zh-CN.md | 10 ++++++---- cogvideox/ui/ui.py | 8 ++++---- predict_i2v.py | 4 ++-- predict_t2v.py | 2 +- predict_v2v.py | 2 +- 6 files changed, 20 insertions(+), 16 deletions(-) diff --git a/README.md b/README.md index 0c90ad3..98c6028 100644 --- a/README.md +++ b/README.md @@ -2,6 +2,8 @@ 😊 Welcome! +[![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-yellow)](https://huggingface.co/spaces/alibaba-pai/CogVideoX-Fun-5b) + English | [简体中文](./README_zh-CN.md) # Table of Contents @@ -288,10 +290,10 @@ For details on setting some parameters, please refer to [Readme Train](scripts/R # Model zoo -| Name | Storage Space | Url | Hugging Face | Description | -|--|--|--|--|--| -| 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 8 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 8 frames per second. | +| Name | Storage Space | Url | Hugging Face | Model Scope | Description | +|--|--|--|--|--|--| +| 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) | [😄Link](https://modelscope.cn/models/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 8 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)| [😄Link](https://modelscope.cn/models/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 8 frames per second. | # TODO List - Support Chinese. diff --git a/README_zh-CN.md b/README_zh-CN.md index af993af..b97fc52 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -2,6 +2,8 @@ 😊 Welcome! +[![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-yellow)](https://huggingface.co/spaces/alibaba-pai/CogVideoX-Fun-5b) + [English](./README.md) | 简体中文 # 目录 @@ -289,10 +291,10 @@ sh scripts/train.sh 关于一些参数的设置细节，可以查看[Readme Train](scripts/README_TRAIN.md)与[Readme Lora](scripts/README_TRAIN_LORA.md) # 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 9.7 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8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8帧进行训练 | +| 名称 | 存储空间 | 下载地址 | Hugging Face | Model Scope | 描述 | +|--|--|--|--|--|--| +| 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) | [😄Link](https://modelscope.cn/models/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8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) | [😄Link](https://modelscope.cn/models/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8帧进行训练 | # 未来计划 - 支持中文。 diff --git a/cogvideox/ui/ui.py b/cogvideox/ui/ui.py index 1682832..f556ec9 100644 --- a/cogvideox/ui/ui.py +++ b/cogvideox/ui/ui.py @@ -535,7 +535,7 @@ def ui(low_gpu_memory_mode, weight_dtype): template_gallery_path = ["asset/1.png", "asset/2.png", "asset/3.png", "asset/4.png", "asset/5.png"] def select_template(evt: gr.SelectData): text = { - "asset/1.png": "The dog is looking at camera and smiling. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", + "asset/1.png": "The dog is shaking head. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", "asset/2.png": "a sailboat sailing in rough seas with a dramatic sunset. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", "asset/3.png": "a beautiful woman with long hair and a dress blowing in the wind. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", "asset/4.png": "a man in an astronaut suit playing a guitar. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", @@ -964,7 +964,7 @@ def ui_modelscope(model_name, savedir_sample, low_gpu_memory_mode, weight_dtype) template_gallery_path = ["asset/1.png", "asset/2.png", "asset/3.png", "asset/4.png", "asset/5.png"] def select_template(evt: gr.SelectData): text = { - "asset/1.png": "The dog is looking at camera and smiling. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", + "asset/1.png": "The dog is shaking head. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", "asset/2.png": "a sailboat sailing in rough seas with a dramatic sunset. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", "asset/3.png": "a beautiful woman with long hair and a dress blowing in the wind. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", "asset/4.png": "a man in an astronaut suit playing a guitar. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", @@ -1258,7 +1258,7 @@ def ui_eas(model_name, savedir_sample): ) prompt_textbox = gr.Textbox(label="Prompt", lines=2, value="A young woman with beautiful and clear eyes and blonde hair standing and white dress in a forest wearing a crown. She seems to be lost in thought, and the camera focuses on her face. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.") - negative_prompt_textbox = gr.Textbox(label="Negative prompt", lines=2, value="The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. " ) + negative_prompt_textbox = gr.Textbox(label="Negative prompt", lines=2, value="The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. " ) with gr.Row(): with gr.Column(): @@ -1295,7 +1295,7 @@ def ui_eas(model_name, savedir_sample): template_gallery_path = ["asset/1.png", "asset/2.png", "asset/3.png", "asset/4.png", "asset/5.png"] def select_template(evt: gr.SelectData): text = { - "asset/1.png": "The dog is looking at camera and smiling. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", + "asset/1.png": "The dog is shaking head. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", "asset/2.png": "a sailboat sailing in rough seas with a dramatic sunset. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", "asset/3.png": "a beautiful woman with long hair and a dress blowing in the wind. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", "asset/4.png": "a man in an astronaut suit playing a guitar. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", diff --git a/predict_i2v.py b/predict_i2v.py index 52c237a..ecd1cb5 100644 --- a/predict_i2v.py +++ b/predict_i2v.py @@ -51,8 +51,8 @@ validation_image_start = "asset/1.png" validation_image_end = None # prompts -prompt = "The dog is looking at camera and smiling. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic." -negative_prompt = "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. " +prompt = "The dog is shaking head. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic." +negative_prompt = "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. " guidance_scale = 6.0 seed = 43 num_inference_steps = 50 diff --git a/predict_t2v.py b/predict_t2v.py index e7433fc..8251d1d 100644 --- a/predict_t2v.py +++ b/predict_t2v.py @@ -43,7 +43,7 @@ fps = 8 # ome graphics cards, such as v100, 2080ti, do not support torch.bfloat16 weight_dtype = torch.bfloat16 prompt = "A young woman with beautiful and clear eyes and blonde hair standing and white dress in a forest wearing a crown. She seems to be lost in thought, and the camera focuses on her face. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic." -negative_prompt = "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. " +negative_prompt = "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. " guidance_scale = 6.0 seed = 43 num_inference_steps = 50 diff --git a/predict_v2v.py b/predict_v2v.py index ba4cb20..552db61 100644 --- a/predict_v2v.py +++ b/predict_v2v.py @@ -48,7 +48,7 @@ denoise_strength = 0.70 # prompts prompt = "A young woman with beautiful and clear eyes and blonde hair standing and white dress in a forest wearing a crown. She seems to be lost in thought, and the camera focuses on her face. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic." -negative_prompt = "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. " +negative_prompt = "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. " guidance_scale = 6.0 seed = 43 num_inference_steps = 50