Weifeng-Chen/control-a-video
Official Implementation of "Control-A-Video: Controllable Text-to-Video Generation with Diffusion Models"
PythonGPL-3.0
Issues
- 1
what is the encoder
#29 opened by parryppp - 1
Question about training CAV
#18 opened by SSUHan - 0
- 0
Training Script
#28 opened by ivaniliash - 2
- 4
- 2
How to make pretrained controlnet model?
#23 opened by WebtoonNayoung - 1
Residual-Based Noise Initialization
#21 opened by hzlhzlhzlhzl - 0
if someone is having an issue with Depth model
#26 opened by HyeonHo99 - 3
- 2
where to put the HED pth file?
#24 opened by G-force78 - 2
- 0
Enable versioning for each consecutive save
#22 opened by G-force78 - 0
Residual-Based Noise Initialization
#20 opened by hzlhzlhzlhzl - 2
problem with triton
#7 opened by gonduras - 1
Add output option
#16 opened by pravdomil - 0
Add start_frame option
#17 opened by pravdomil - 2
- 0
Rename input_video to input
#15 opened by pravdomil - 1
Rename num_sample_frames to frame_count
#14 opened by pravdomil - 1
Signle Character
#9 opened by p0mad - 1
can i export mov video?
#6 opened by D-Mad - 0
Rename sampling_rate to frame_skip
#13 opened by pravdomil - 0
Rename each_sample_frame to batch_size
#12 opened by pravdomil - 0
Update diffusers package
#11 opened by pravdomil - 0
Create pyproject.toml
#10 opened by pravdomil - 1
Condition on first frame
#2 opened by julkaztwittera - 1
- 1
Code Release
#1 opened by mayuelala