From f8f63b409702d8e265c6df35255d983027e0b234 Mon Sep 17 00:00:00 2001 From: Hang Gao Date: Wed, 19 Mar 2025 17:14:17 -0700 Subject: [PATCH 1/6] Update README.md --- README.md | 11 ++--------- 1 file changed, 2 insertions(+), 9 deletions(-) diff --git a/README.md b/README.md index bd2b19f..c169dac 100644 --- a/README.md +++ b/README.md @@ -15,21 +15,14 @@ # :wrench: Installation -## Windows Users: Please use WSL as flash attention isn't supported on native Windows yet: https://github.com/pytorch/pytorch/issues/108175 - -Clone the repository: - ```bash git clone --recursive https://github.com/Stability-AI/stable-virtual-camera -``` - -To setup the virtual environment and install all necessary model dependencies, simply run: - -```bash +cd stable-virtual-camera pip install -e . ``` Check [INSTALL.md](docs/INSTALL.md) for other dependencies if you want to use our demos or develop from this repo. +For windows users, please use WSL as flash attention isn't supported on native Windows [yet](https://github.com/pytorch/pytorch/issues/108175). # :open_book: Usage From 728718675e23994276682f9cf8d922534396b95e Mon Sep 17 00:00:00 2001 From: Hang Gao Date: Wed, 19 Mar 2025 17:22:20 -0700 Subject: [PATCH 2/6] Update README.md to make version specific --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index c169dac..38fc867 100644 --- a/README.md +++ b/README.md @@ -21,6 +21,8 @@ cd stable-virtual-camera pip install -e . ``` +Please note that you will need `python>=3.10` and `torch>=2.6.0`. + Check [INSTALL.md](docs/INSTALL.md) for other dependencies if you want to use our demos or develop from this repo. For windows users, please use WSL as flash attention isn't supported on native Windows [yet](https://github.com/pytorch/pytorch/issues/108175). From 9a046295faf4b4161ccbe912b860a7dc09c73585 Mon Sep 17 00:00:00 2001 From: jensen Date: Thu, 20 Mar 2025 03:15:53 +0000 Subject: [PATCH 3/6] Update docs/CLI_USAGE.md and default chunk_strategy in demo.py --- demo.py | 2 +- docs/CLI_USAGE.md | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/demo.py b/demo.py index 19c15ad..1f99a1d 100644 --- a/demo.py +++ b/demo.py @@ -290,7 +290,7 @@ def main( VERSION_DICT["T"] = [int(t) for t in T.split(",")] if isinstance(T, str) else T options = VERSION_DICT["options"] - options["chunk_strategy"] = "interp" + options["chunk_strategy"] = "nearest-gt" options["video_save_fps"] = 30.0 options["beta_linear_start"] = 5e-6 options["log_snr_shift"] = 2.4 diff --git a/docs/CLI_USAGE.md b/docs/CLI_USAGE.md index e9344fd..937a720 100644 --- a/docs/CLI_USAGE.md +++ b/docs/CLI_USAGE.md @@ -86,8 +86,7 @@ For example, you can run the following command on the example `dl3d140-165f5af8b python demo.py \ --data_path /path/to/assets_demo_cli/ \ --data_items dl3d140-165f5af8bfe32f70595a1c9393a6e442acf7af019998275144f605b89a306557 \ - --num_inputs 1 \ - --chunk_strategy nearest-gt \ + --num_inputs 3 \ --video_save_fps 10 ``` From 0d2a5105a443d6d3852a6bece1fd9b92aba026e3 Mon Sep 17 00:00:00 2001 From: jensen Date: Thu, 20 Mar 2025 03:16:46 +0000 Subject: [PATCH 4/6] Update docs/CLI_USAGE.md --- docs/CLI_USAGE.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/CLI_USAGE.md b/docs/CLI_USAGE.md index 937a720..51b7f2e 100644 --- a/docs/CLI_USAGE.md +++ b/docs/CLI_USAGE.md @@ -80,7 +80,7 @@ python demo.py \ - For the evaluation in semi-dense-view regime (i.e., DL3DV-140 and Tanks and Temples dataset) with `32` input views, we zero-shot extend `T` to fit all input and target views in one forward. Specifically, we set `--T 90` for the DL3DV-140 dataset and `--T 80` for the Tanks and Temples dataset. - For the evaluation on ViewCrafter split (including the RealEastate10K, CO3D, and Tanks and Temples dataset), we find zero-shot extending `T` to `25` to fit all input and target views in one forward is better. Also, the V split uses the original image resolutions: we therefore set `--T 25 --L_short 576`. -For example, you can run the following command on the example `dl3d140-165f5af8bfe32f70595a1c9393a6e442acf7af019998275144f605b89a306557` with 1 input view: +For example, you can run the following command on the example `dl3d140-165f5af8bfe32f70595a1c9393a6e442acf7af019998275144f605b89a306557` with 3 input view: ```bash python demo.py \ From 4fee6793de3f6193caedd5579a4f717023c5b3a6 Mon Sep 17 00:00:00 2001 From: jensen Date: Thu, 20 Mar 2025 03:18:13 +0000 Subject: [PATCH 5/6] Update docs/CLI_USAGE.md --- docs/CLI_USAGE.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/CLI_USAGE.md b/docs/CLI_USAGE.md index 51b7f2e..ecb9d3b 100644 --- a/docs/CLI_USAGE.md +++ b/docs/CLI_USAGE.md @@ -53,7 +53,7 @@ We provide