Mirrors/AnimateDiff
1
0
Fork 0
mirror of https://github.com/guoyww/AnimateDiff.git synced 2026-04-03 17:56:15 +02:00
Code Issues Packages Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
Yuwei Guo
2023-07-12 17:07:44 +08:00
parent 3742e3e524
commit 33a89796aa
1 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@@ -27,10 +27,12 @@ Bo Dai
## Setup for Inference ## Setup for Inference
### Prepare Environment ### Prepare Environment
Our approach takes around 60 GB GPU memory to inference. NVIDIA A100 is recommanded. ~~Our approach takes around 60 GB GPU memory to inference. NVIDIA A100 is recommanded.~~
***We updated our inference code with xformers and a sequential decoding trick. Now AnimateDiff takes only ~12GB VRAM to inference, and can be run on a single RTX3090 !!***
``` ```
git clone https://github.com/guoyww/animatediff.git git clone https://github.com/guoyww/AnimateDiff.git
cd AnimateDiff cd AnimateDiff
conda env create -f environment.yaml conda env create -f environment.yaml
@@ -107,7 +109,7 @@ Here we demonstrate several best results we found in our experiments or generate
<td><img src="__assets__/animations/model_07/04.gif"></td> <td><img src="__assets__/animations/model_07/04.gif"></td>
</tr> </tr>
</table> </table>
<p style="margin-left: 2em; margin-top: -1em">Model：<a href="https://civitai.com/models/107295?modelVersionId=115371">holding_sign</a> (samples are contributed by CivitAI artists)</p> <p style="margin-left: 2em; margin-top: -1em">Model：<a href="https://civitai.com/models/107295?modelVersionId=115371">holding_sign</a>, etc. (samples are contributed by CivitAI artists)</p>
<table class="center"> <table class="center">
<tr> <tr>