Comments (11)
Maybe the Input tensor shape is fixed。when i change the num_frames from 14 to 25 in yaml file,Error in background is Shape mismatch, can't divide axis of length 28 in chunks of 25。
from motionctrl.
Maybe the Input tensor shape is fixed。when i change the num_frames from 14 to 25 in yaml file,Error in background is Shape mismatch, can't divide axis of length 28 in chunks of 25。
can "axis of length 28" be changed to 50?
from motionctrl.
我生成了2s的视频,但是我不清楚它的原理是什么
首先我更换了SVD的模型,改成svd_xt
然后修改config_motionctrl_cmcm.yaml文件里面的 num_frames: 25 num_steps: 30 max_scale: 3.0 min_scale: 1.5
然后是app.py文件里面n = 16改成n = 25,for循环也要改掉;num_frames = 25 num_steps = 30
然后并不是每次都会生成成功,在报错时重启服务,前端gradio页面不刷新,直接点生成,会生成2s的视频。但是帧率默认是10不清楚原因。
from motionctrl.
tmpwmd99trw.mp4
from motionctrl.
当我第一次生成成功时,修改图片或者相机控制参数后台就会报错,RuntimeError: Sizes of tensors must match except in dimension 2. Expected size 25 but got size 16 for tensor number 1 in the list.
但是当我重启服务后,继续按照前端刚刚报错的相关参数去生成,它就会生成成功。
from motionctrl.
生成报错是因为 camera poses选择Provided Complex Camera Poses,如果是Basic Camera Poses是可以连续生成成功的,Custom Camera Poses选择Basic Camera Poses也是可以的。生成视频帧率固定10的原因是因为在motionctrl_cmcm_gradio.py里面写死了。
from motionctrl.
ok,多谢回复
from motionctrl.
当增加帧数生成的视频长度大于1s之后,感觉1s之后的视频会和这里生成的这个女生的视频一样,后半段不太运动而且会变得稍微糊一些,请问这收到训练数据的影响吗?请问调整哪个参数可以改善这一点呢?
eduardo-gorghetto-5auIBbcoRNw-unsplash_L.3.mp4
from motionctrl.
可以生成大于14帧的,设置一下参数就行了。下面这个片段是设置了24帧,fps为6时的情况,总长度4s,模式为zoom in。出现的问题是预测14帧之后的内容由于模型没有训练过,就无法按照固定的模式生成frame,感觉想用的话还得微调一下。
from motionctrl.
littleMan_I_f24.mp4
from motionctrl.
可以生成大于14帧的,设置一下参数就行了。下面这个片段是设置了24帧,fps为6时的情况,总长度4s,模式为zoom in。出现的问题是预测14帧之后的内容由于模型没有训练过,就无法按照固定的模式生成frame,感觉想用的话还得微调一下。
你好 请问您具体是修改了哪些参数呢 需要修改camera pose的json文件吗
from motionctrl.
Related Issues (20)
- the node Import failed
- camera speed meaning
- Downloaded example workflow for ComfyUI and it fails HOT 2
- Pretrained model produces noises HOT 9
- No module named 'sgm.motionctrl'
- Plans on releasing OMCM module weights for SVD?
- High rolling shutter distortion
- Static camera
- Plan to release the training code? HOT 2
- how many cuda vram needed to train motionctrl based on svd?
- AttributeError: module 'xformers' has no attribute 'ops'. Did you mean: 'os'? HOT 1
- Noises about MotionCtrl-SVD HOT 1
- No object trajectory in SVD
- config_motionctrl_cmcm.yaml中ckpt_path需要填svd的路径 但是推理代码中又没有用到svd
- MotionCtrl+svd是在svd模型上训练的CMCM吗
- About SVD Model Inference Code HOT 1
- readme中展示的比较大运动尺度的json文件
- How does it address scale ambiguity issue?
- what is the license for the svd check point?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from motionctrl.