From 2da594c831685003214a230df8a53c3f84b4fb0e Mon Sep 17 00:00:00 2001 From: zR <2448370773@qq.com> Date: Tue, 6 Aug 2024 02:16:43 +0800 Subject: [PATCH] GPU memory cost changed --- README.md | 8 +++++--- README_zh.md | 2 +- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 97415bb..3db483e 100644 --- a/README.md +++ b/README.md @@ -18,7 +18,8 @@ ## Update and News -- 🔥 **News**: ``2024/8/6``: We have also open-sourced **3D Causal VAE** used in **CogVideoX-2B**, which can reconstruct the video almost losslessly. +- 🔥 **News**: ``2024/8/6``: We have also open-sourced **3D Causal VAE** used in **CogVideoX-2B**, which can reconstruct + the video almost losslessly. - 🔥 **News**: ``2024/8/6``: We have open-sourced **CogVideoX-2B**，the first model in the CogVideoX series of video generation models. @@ -57,7 +58,7 @@ along with related basic information: | Model Name | CogVideoX-2B | |-------------------------------------------|--------------------------------------------------------------| | Prompt Language | English | -| GPU Memory Required for Inference (FP16) | 21.6GB | +| GPU Memory Required for Inference (FP16) | 36GB (will be optimized before the PR is merged) | | GPU Memory Required for Fine-tuning(bs=1) | 46.2GB | | Prompt Max Length | 226 Tokens | | Video Length | 6 seconds | @@ -76,7 +77,8 @@ of the **CogVideoX** open-source model. + [cli_demo](inference/cli_demo.py): A more detailed explanation of the inference code, mentioning the significance of common parameters. -+ [cli_vae_demo](inference/cli_vae_demo.py): Executing the VAE inference code alone currently requires 71GB of memory, but it will be optimized in the future. ++ [cli_vae_demo](inference/cli_vae_demo.py): Executing the VAE inference code alone currently requires 71GB of memory, + but it will be optimized in the future. + [convert_demo](inference/converter_demo.py): How to convert user input into a format suitable for CogVideoX. + [web_demo](inference/web_demo.py): A simple streamlit web application demonstrating how to use the CogVideoX-2B model to generate videos. diff --git a/README_zh.md b/README_zh.md index f864e06..b831df2 100644 --- a/README_zh.md +++ b/README_zh.md @@ -55,7 +55,7 @@ CogVideoX是 [清影](https://chatglm.cn/video) 同源的开源版本视频生 | 模型名字 | CogVideoX-2B | |----------------|--------------------------------------------------------------| | 提示词语言 | English | -| 推理显存消耗 (FP-16) | 21.6GB | +| 推理显存消耗 (FP-16) | 36GB | | 微调显存消耗 (bs=1) | 46.2GB | | 提示词长度上限 | 226 Tokens | | 视频长度 | 6 seconds |