Open-Sora: Democratizing Efficient Video Production for All
Python
update readme
zhengzangwecebf888657c
diff --git a/configs/opensora-v1-2/train/demo_360p.py b/configs/opensora-v1-2/train/demo_360p.pyindex e27bd3c..f49a00e 100644--- a/configs/opensora-v1-2/train/demo_360p.py+++ b/configs/opensora-v1-2/train/demo_360p.py@@ -5,7 +5,7 @@ dataset = dict()# webvid-bucket_config = {"360p": {102: (1.0, 5)}}+bucket_config = {"360p": {102: (1.0, 1)}}grad_checkpoint = True# Acceleration settingsdiff --git a/docs/report_03.md b/docs/report_03.mdindex d6012e4..88baf3a 100644--- a/docs/report_03.md+++ b/docs/report_03.md@@ -7,7 +7,7 @@- [Evaluation](#evaluation)- [Sequence parallelism](#sequence-parallelism)-In Open-Sora 1.2 release, we train a 1.1B models on >30M data (~80k hours), with training cost 35k H100 GPU hours, supporting 0s~16s, 144p to 720p, various aspect ratios video generation. Our configurations is listed below. Following our 1.1 version, Open-Sora 1.2 can also do image-to-video generation and video extension.+In Open-Sora 1.2 release, we train a 1.1B models on >30M data (about 80k hours), with training cost 35k H100 GPU hours, supporting 0s to 16s, 144p to 720p, various aspect ratios video generation. Our configurations is listed below. Following our 1.1 version, Open-Sora 1.2 can also do image-to-video generation and video extension.| | image | 2s | 4s | 8s | 16s || ---- | ----- | --- | --- | --- | --- |