From fba930d40081da42aae49dd47fece841ccff2b6d Mon Sep 17 00:00:00 2001 From: Vikram Voleti Date: Mon, 18 Mar 2024 23:56:52 +0530 Subject: [PATCH] SV3D update README (#305) * Makes init changes for SV3D * Small fixes : cond_aug * Fixes SV3D checkpoint, fixes rembg * Black formatting * Adds streamlit demo, fixes simple sample script * Removes SV3D video_decoder, keeps SV3D image_decoder * Updates README * Minor updates * Remove GSO script * Updates REAME, fixes names --------- Co-authored-by: Vikram Voleti --- README.md | 10 ++++++++++ scripts/sampling/configs/sv3d_p.yaml | 2 +- scripts/sampling/configs/sv3d_u.yaml | 2 +- 3 files changed, 12 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index dd9d61d..896ebf1 100644 --- a/README.md +++ b/README.md @@ -12,8 +12,18 @@ - We extend the streamlit demo `scripts/demo/video_sampling.py` and the standalone python script `scripts/sampling/simple_video_sample.py` for inference of both models. - Please check our [project page](https://sv3d.github.io), [tech report](https://sv3d.github.io/static/paper.pdf) and [video summary](https://youtu.be/Zqw4-1LcfWg) for more details. +<<<<<<< HEAD +To run SV3D_u on a single image: +- Download `sv3d_u.safetensors` from https://huggingface.co/stabilityai/sv3d to `checkpoints/sv3d_u.safetensors` +- Run `python scripts/sampling/simple_video_sample.py --input_path --version sv3d_u` + +Additionally for SV3D_p, +- Specify sequences of 21 elevations and 21 azimuths (in degrees) to `elevations_deg` ([-90, 90]), and `azimuths_deg` [0, 360] in sorted order from 0 to 360. For example: +`python scripts/sampling/simple_video_sample.py --input_path --version sv3d_p --elevations_deg [] --azimuths_deg []` +======= To run SV3D on a single image: `python scripts/sampling/simple_video_sample.py --input_path --version sv3d_p` +>>>>>>> main To run SVD or SV3D on a streamlit server: `streamlit run scripts/demo/video_sampling.py` diff --git a/scripts/sampling/configs/sv3d_p.yaml b/scripts/sampling/configs/sv3d_p.yaml index bb3747c..af6e1ea 100644 --- a/scripts/sampling/configs/sv3d_p.yaml +++ b/scripts/sampling/configs/sv3d_p.yaml @@ -3,7 +3,7 @@ model: params: scale_factor: 0.18215 disable_first_stage_autocast: True - ckpt_path: checkpoints/sv3d_p_image_decoder.safetensors + ckpt_path: checkpoints/sv3d_p.safetensors denoiser_config: target: sgm.modules.diffusionmodules.denoiser.Denoiser diff --git a/scripts/sampling/configs/sv3d_u.yaml b/scripts/sampling/configs/sv3d_u.yaml index 8a7ce21..2d6f135 100644 --- a/scripts/sampling/configs/sv3d_u.yaml +++ b/scripts/sampling/configs/sv3d_u.yaml @@ -3,7 +3,7 @@ model: params: scale_factor: 0.18215 disable_first_stage_autocast: True - ckpt_path: checkpoints/sv3d_u_image_decoder.safetensors + ckpt_path: checkpoints/sv3d_u.safetensors denoiser_config: target: sgm.modules.diffusionmodules.denoiser.Denoiser