From 08d574d29f20173bde78db03aa029b2bc41b34f2 Mon Sep 17 00:00:00 2001 From: Zangwei Zheng Date: Mon, 18 Mar 2024 12:32:21 +0800 Subject: [PATCH] update readme --- README.md | 3 +-- docs/README_zh.md | 3 +-- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index ce7d399..add4212 100644 --- a/README.md +++ b/README.md @@ -26,7 +26,7 @@ With Open-Sora, we aim to inspire innovation, creativity, and inclusivity in the * **[2024.03.18]** 🔥 We release **Open-Sora 1.0**, a fully open-source project for video generation. Open-Sora 1.0 supports a full pipeline of video data preprocessing, training with acceleration, -inference, and more. Our provided [checkpoints](#model-weights) can produce 2~5s 512x512 videos with only 3 days training. +inference, and more. Our provided [checkpoints](#model-weights) can produce 2s 512x512 videos with only 3 days training. * **[2024.03.04]** Open-Sora provides training with 46% cost reduction. ## 🎥 Latest Demo @@ -123,7 +123,6 @@ After installation, we suggest reading [structure.md](docs/structure.md) to lear | 16×256×256 | 366K | 80k | 8×64 | 117 | [:link:](https://huggingface.co/hpcai-tech/Open-Sora/blob/main/OpenSora-v1-16x256x256.pth) | | 16×256×256 | 20K HQ | 24k | 8×64 | 45 | [:link:](https://huggingface.co/hpcai-tech/Open-Sora/blob/main/OpenSora-v1-HQ-16x256x256.pth) | | 16×512×512 | 20K HQ | 20k | 2×64 | 35 | [:link:](https://huggingface.co/hpcai-tech/Open-Sora/blob/main/OpenSora-v1-HQ-16x512x512.pth) | -| 64×512×512 | 50K HQ | | | | TBD | Our model's weight is partially initialized from [PixArt-α](https://github.com/PixArt-alpha/PixArt-alpha). The number of parameters is 724M. More information about training can be found in our **[report](/docs/report_v1.md)**. More about dataset can be found in [dataset.md](/docs/dataset.md). HQ means high quality. diff --git a/docs/README_zh.md b/docs/README_zh.md index 7ed0b81..d440550 100644 --- a/docs/README_zh.md +++ b/docs/README_zh.md @@ -23,7 +23,7 @@ * **[2024.03.18]** 🔥 我们发布了**Open-Sora 1.0**，这是一个完全开源的视频生成项目。 * Open-Sora 1.0 支持视频数据预处理、 加速训练、推理等全套流程。 -* 我们提供的[模型权重](#model-weights)只需 3 天的训练就能生成 2~5 秒的 512x512 视频。 +* 我们提供的[模型权重](#model-weights)只需 3 天的训练就能生成 2 秒的 512x512 视频。 * **[2024.03.04]** Open-Sora：开源Sora复现方案，成本降低46%，序列扩充至近百万 ## 🎥 最新视频 @@ -119,7 +119,6 @@ pip install -v . | 16×256×256 | 366K | 80k | 8×64 | 117 | [:link:]() | | 16×256×256 | 20K HQ | 24k | 8×64 | 45 | [:link:]() | | 16×512×512 | 20K HQ | 20k | 2×64 | 35 | [:link:]() | -| 64×512×512 | 50K HQ | | | | TBD | 我们模型的权重部分由[PixArt-α](https://github.com/PixArt-alpha/PixArt-alpha) 初始化。参数数量为 724M。有关训练的更多信息，请参阅我们的 **[报告](/docs/report_v1.md)**。有关数据集的更多信息，请参阅[数据](/docs/dataset.md)。HQ 表示高质量。 :warning: **局限性**：我们的模型是在有限的预算内训练出来的。质量和文本对齐度相对较差。特别是在生成人类时，模型表现很差，无法遵循详细的指令。我们正在努力改进质量和文本对齐。