frankleeeee commited on
Commit
45dcc28
1 Parent(s): 3065798

added readme

Browse files
Files changed (1) hide show
  1. README.md +48 -0
README.md CHANGED
@@ -1,3 +1,51 @@
1
  ---
2
  license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
  ---
4
+
5
+ ## Open-Sora: Democratizing Efficient Video Production for All
6
+ We present [Open-Sora](https://github.com/hpcaitech/Open-Sora), an initiative dedicated to **efficiently** produce high-quality video and make the model,
7
+ tools and contents accessible to all. By embracing **open-source** principles,
8
+ Open-Sora not only democratizes access to advanced video generation techniques, but also offers a
9
+ streamlined and user-friendly platform that simplifies the complexities of video production.
10
+ With Open-Sora, we aim to inspire innovation, creativity, and inclusivity in the realm of content creation.
11
+
12
+ <h4>Open-Sora is still at an early stage and under active development.</h4>
13
+
14
+ More details can be founded at [Open-Sora GitHub](https://github.com/hpcaitech/Open-Sora).
15
+
16
+
17
+ ## 📰 News
18
+
19
+ * **[2024.03.18]** 🔥 We release **Open-Sora 1.0**, a fully open-source project for video generation.
20
+ Open-Sora 1.0 supports a full pipeline of video data preprocessing, training with
21
+ [ColossalAI](https://github.com/hpcaitech/ColossalAI) acceleration,
22
+ inference, and more. Our provided checkpoints can produce 2s 512x512 videos with only 3 days training.
23
+ [[blog]](https://hpc-ai.com/blog/open-sora-v1.0)
24
+ * **[2024.03.04]** Open-Sora provides training with 46% cost reduction.
25
+ [[blog]](https://hpc-ai.com/blog/open-sora)
26
+
27
+
28
+ ## 🛠 Usage
29
+
30
+ You can launch this video generation with this model in a Gradio application.
31
+
32
+ ```bash
33
+ # git clone Open-Sora
34
+ git clone https://github.com/hpcaitech/Open-Sora.git
35
+ cd Open-Sora
36
+
37
+ # launch gradio
38
+ python scripts/demo.py --model-type v1-HQ-16x512x512
39
+ ```
40
+
41
+ If you want to use this STDiT model in code,
42
+
43
+ ```python
44
+ from transformers import AutoModel
45
+
46
+ stdit = AutoModel.from_pretrained("hpcai-tech/OpenSora-STDiT-v1-HQ-16x512x512")
47
+ ```
48
+
49
+ Do note that this model alone cannot generate video, it should work alongside a vae model and a text encoder model like how we did in the demo.
50
+
51
+