-
Make an integration to comfyui
nodes for taking clip prompts for lryics, music styles, etc
nodes for generating lyrics from clip prompts, with outputs that can be tweaked before deciding to go ahead…
-
I am getting a strange output for t2v and i2v.
_I am on a mac with m2 24GB, python 3.10.13, torch 2.6.0(nightly), torchvision 0.20.0(nightly)._
_I modified the code to support MPS_
1. switch…
-
Experiencing severe face distortion with image to video, here is an example:
![977](https://github.com/user-attachments/assets/991e0a16-9d77-4106-bc09-0989f3493a2f)
https://github.com/user-attachm…
-
what's the actual pose image F_t you render? Is the first colored image type or the skeleton-like type?
最终渲染出来的pose图是pipeline里这个彩色的,还是后文图里那个骨骼?This really makes me confused!
![UZNYC~`IO2VW}VDJ%41U…
-
Output results\9d358038-9b78-457c-8698-35044f5456e6\00003-3404085431##audio_full.mp4 same as Input #0 - exiting
FFmpeg cannot edit existing files in-place.
Error opening output file results\9d358038…
-
The SVD model [stabilityai/stable-video-diffusion-img2vid-xt-1-1](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt-1-1) will be automatically downloaded.
这个模型可以自行下载,然后设置路径么?
感谢感谢
-
### 🐛 Describe the bug
(While trying to enable torch.compile for https://github.com/nateraw/stable-diffusion-videos). We get an exception when tracing `super(Fraction, cls).__new__(cls)`. The solutio…
-
-
### OpenVINO Version
2024.4.0
### Operating System
Windows System
### Device used for inference
GPU
### Framework
None
### Model used
laion/CLIP-ViT-B-32-laion2B-s34B-b79K
…
-
If you take a look at the weights of the learned positional embedding in THUDM/CogVideoX-5b-I2V, you will find that the mean is close to 0 and standard deviation is very low. This is to say that the w…