control-a-video icon indicating copy to clipboard operation
control-a-video copied to clipboard

Official Implementation of "Control-A-Video: Controllable Text-to-Video Generation with Diffusion Models"

Results 19 control-a-video issues
Sort by recently updated
recently updated
newest added

Any training script would be highly appreciated! Want to train my own Control-A-Video model :)

Hi,it's a great work,but it looks like the code lacks training modules, will you release it?

Hi! I have a question. How can I create a pretrained ControlNet 3D model? Do I need to train additional 3D parameters, or is it possible to use the pretrained...

Using these arguments !python3 /content/control-a-video/inference.py --prompt "a bear practicing kungfu, with a background of mountains" --input_video /content/kungfubear.mp4 --control_mode depth --num_sample_frames 24 --inference_step 10 --guidance_scale 5 --init_noise_thres 0.75 FPS 8 output...

(venv) E:\ControlVideo>python inference.py A matching Triton is not available, some optimizations will not be enabled. Error caught was: No module named 'triton.language' Traceback (most recent call last): File "E:\ControlVideo\inference.py", line...

Hi, I'm sincerely glad that you shared your great work! I tried to reimplement the training logic of CAV but had some troubles.. Can you take a look at what...

like so https://github.com/Weifeng-Chen/control-a-video/issues/6#issuecomment-1638973711

to control from which frame to start

Thanks for the release code! I have experiencd severe color changes for long video generation, e.g more than 60 frames. And finally the color becomes oversaturated. Tune off the init_noise_by_residual_thres...