Comments (4)
oh. my bad. I'll fix and reopen if it breaks again. thanks
from text2video-zero.
HI @johndpope,
we have updated the README and code, regarding your issue.
from text2video-zero.
from pathlib import Path
import torch
from model import Model
model = Model(device = "cuda", dtype = torch.float16)
prompt = 'sexy asian gta-5 style'
video_path = Path('./crop.mp4')
dreambooth_model_path = Path("GTA-5 DB")
out_path = Path(f'./{prompt}.gif')
model.process_controlnet_canny_db(dreambooth_model_path.as_posix(), video_path.as_posix(), prompt=prompt, save_path=out_path.as_posix())%
still blows up
/home/oem/Documents/gitWorkspace/Text2Video-Zero/annotator/openpose/body.py:5: DeprecationWarning: Please use gaussian_filter
from the scipy.ndimage
namespace, the scipy.ndimage.filters
namespace is deprecated.
from scipy.ndimage.filters import gaussian_filter
/home/oem/Documents/gitWorkspace/Text2Video-Zero/annotator/openpose/hand.py:6: DeprecationWarning: Please use gaussian_filter
from the scipy.ndimage
namespace, the scipy.ndimage.filters
namespace is deprecated.
from scipy.ndimage.filters import gaussian_filter
/home/oem/miniconda3/envs/ldm/lib/python3.10/site-packages/skimage/util/dtype.py:27: DeprecationWarning: np.bool8
is a deprecated alias for np.bool_
. (Deprecated NumPy 1.24)
np.bool8: (False, True),
cuda
cuda
Traceback (most recent call last):
File "/home/oem/Documents/gitWorkspace/Text2Video-Zero/test.py", line 10, in
model.process_controlnet_canny_db(dreambooth_model_path.as_posix(), video_path.as_posix(), prompt=prompt, save_path=out_path.as_posix())
File "/home/oem/Documents/gitWorkspace/Text2Video-Zero/model.py", line 247, in process_controlnet_canny_db
video_path = gradio_utils.get_video_from_canny_selection(video_path)
File "/home/oem/Documents/gitWorkspace/Text2Video-Zero/gradio_utils.py", line 53, in get_video_from_canny_selection
raise Exception
Exception
the readme says
dreambooth_model_path = "GTA-5 DB"
but it won't run / crashes with as_posix error
dreambooth_model_path = Path("GTA-5 DB")
this gets around this crash.
from text2video-zero.
Hi @johndpope,
from the error message I can see that you did not update the code.
With the latest code you can do as written in the documentation:
import torch
from model import Model
model = Model(device = "cuda", dtype = torch.float16)
prompt = 'woman gta-5 style'
video_path = "woman1"
dreambooth_model_path = "GTA-5 DB"
out_path = f'./{prompt}.gif'
model.process_controlnet_canny_db(dreambooth_model_path, video_path, prompt=prompt, save_path=out_path)%
You can replace video_path = "woman1"
with your custom video, e.g. video_path = "./crop.mp4"
from text2video-zero.
Related Issues (20)
- About the process of generating latent code HOT 1
- Which conference do you submit this paper?
- How much memory GPU is required for text-to-video generation?
- FACE + Hand Guidance
- Dependencies in `requirements.txt` have module conflicts.
- Image prompt in video generator
- Ai video prompt not working
- How to only use dreambooth without controlnet for zero-shot T2V?
- ValueError: cross_attention_dim must be specified for CrossAttnDownBlock2D HOT 1
- About the Background Smoothing
- AttributeError: while importing model
- Does it support Stable diffusion XL
- Please continue development in the vein of Animatediff, but undo diffusers work
- Inference on CPU HOT 1
- Not reproducible
- Questions about cross frame attention
- Hello, How can I contact lead developer of this project? HOT 1
- AssertionError: Torch not compiled with CUDA enabled HOT 1
- Video generation takes too long even with GPU HOT 3
- No module named 'distutils.cmd'
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 text2video-zero.