JLNTV_IPD/CogVideo
4
0
Fork 0
mirror of https://github.com/THUDM/CogVideo.git synced 2025-04-06 03:57:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

docs: add hardware requirements for model training

Browse Source 
Add a table in README files showing hardware requirements for training
different CogVideoX models, including:
- Memory requirements for each model variant
- Supported training types (LoRA)
- Training resolutions
- Mixed precision settings

Updated in all language versions (EN/ZH/JA).
This commit is contained in:
OleehyO 2025-01-08 01:39:37 +00:00
parent 10de04fc08
commit 249fadfb76
3 changed files with 36 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
finetune/README.md
View File

@ -6,6 +6,17 @@
If you're looking for the fine-tuning instructions for the SAT version, please check [here](../sat/README_zh.md). The dataset format for this version differs from the one used here.
## Hardware Requirements
| Model | Training Type | Mixed Precision | Training Resolution (frames x height x width) | Hardware Requirements |
|---------------------|-----------------|----------------|---------------------------------------------|------------------------|
| cogvideox-t2v-2b | lora (rank128) | fp16 | 49x480x720 | 16GB VRAM (NVIDIA 4080) |
| cogvideox-t2v-5b | lora (rank128) | bf16 | 49x480x720 | 24GB VRAM (NVIDIA 4090) |
| cogvideox-i2v-5b | lora (rank128) | bf16 | 49x480x720 | 24GB VRAM (NVIDIA 4090) |
| cogvideox1.5-t2v-5b | lora (rank128) | bf16 | 81x768x1360 | 35GB VRAM (NVIDIA A100) |
| cogvideox1.5-i2v-5b | lora (rank128) | bf16 | 81x768x1360 | 35GB VRAM (NVIDIA A100) |
## Install Dependencies
Since the relevant code has not yet been merged into the official `diffusers` release, you need to fine-tune based on the diffusers branch. Follow the steps below to install the dependencies:

11
finetune/README_ja.md
View File

@ -6,6 +6,17 @@
SATバージョンのファインチューニング手順については、[こちら](../sat/README_zh.md)をご確認ください。このバージョンのデータセットフォーマットは、こちらのバージョンとは異なります。
## ハードウェア要件
| モデル | トレーニングタイプ | 混合精度学習 | トレーニング解像度(フレーム数x高さx幅) | ハードウェア要件 |
|----------------------|-----------------|------------|----------------------------------|----------------|
| cogvideox-t2v-2b | lora (rank128) | fp16 | 49x480x720 | 16GB VRAM (NVIDIA 4080) |
| cogvideox-t2v-5b | lora (rank128) | bf16 | 49x480x720 | 24GB VRAM (NVIDIA 4090) |
| cogvideox-i2v-5b | lora (rank128) | bf16 | 49x480x720 | 24GB VRAM (NVIDIA 4090) |
| cogvideox1.5-t2v-5b | lora (rank128) | bf16 | 81x768x1360 | 35GB VRAM (NVIDIA A100) |
| cogvideox1.5-i2v-5b | lora (rank128) | bf16 | 81x768x1360 | 35GB VRAM (NVIDIA A100) |
## 依存関係のインストール
関連するコードがまだ `diffusers` の公式リリースに統合されていないため、`diffusers` ブランチを基にファインチューニングを行う必要があります。以下の手順に従って依存関係をインストールしてください：

14
finetune/README_zh.md
View File

@ -6,6 +6,20 @@
如果您想查看SAT版本微调，请查看[这里](../sat/README_zh.md)。其数据集格式与本版本不同。
## 硬件要求
| 模型 | 训练类型 | 混合训练精度 | 训练分辨率(帧数x高x宽) | 硬件要求 |
|----------------------|----------------|------------|----------------------|-----------------------|
| cogvideox-t2v-2b | lora (rank128) | fp16 | 49x480x720 | 16G显存 (NVIDIA 4080) |
| cogvideox-t2v-5b | lora (rank128) | bf16 | 49x480x720 | 24G显存 (NVIDIA 4090) |
| cogvideox-i2v-5b | lora (rank128) | bf16 | 49x480x720 | 24G显存 (NVIDIA 4090) |
| cogvideox1.5-t2v-5b | lora (rank128) | bf16 | 81x768x1360 | 35G显存 (NVIDIA A100) |
| cogvideox1.5-i2v-5b | lora (rank128) | bf16 | 81x768x1360 | 35G显存 (NVIDIA A100) |
<!-- | cogvideox-t2v-5b | sft | bf16 | 49x480x720 | |
| cogvideox-i2v-5b | sft | bf16 | 49x480x720 | |
| cogvideox1.5-t2v-5b | sft | bf16 | 81x768x1360 | |
| cogvideox1.5-i2v-5b | sft | bf16 | 81x768x1360 | | -->
## 安装依赖
由于相关代码还没有被合并到diffusers发行版，你需要基于diffusers分支进行微调。请按照以下步骤安装依赖：