-
When I use the Load Video node to generate images and then use the ic-light node for light generation, I find that only one image is generated in the end, what do I need to tweak the parameters so tha…
-
In Comfyui, the image to video, control, and video to video nodes all seem to have a progress bar.
The text to image node though is missing any kind of progress report.
-
In addition to flux, does nunchaku support prompt-to-video models, such as OpenSoraPlan, Cogvideo，etc.
Flux is also a transformer-based model
-
前向使用的代码如下，只改了questions和视频路径paths，具体的questions是："Generate a brief and accurate for this video"
```
import torch
import transformers
import sys
sys.path.append('./')
from videollama2.conversatio…
-
Hello, I saw that you used freenoise to generate longer videos in your paper. Could you please provide the code?
Thanks so much! My email is 1224432553@qq.com
-
hi, thanks for your open source again. i just find there has no difference between 16 frames yaml and 61 frames yaml except sc_attn_index, so i'm wondering that if i can training 240 frames just chang…
-
Problem Statement:
Currently, the QR code generator offers a generalized QR code creation process without clear predefined categories for specific use cases such as URLs, vCards, SMS, WiFi,Mp3, Video…
-
If we tokenise frames of a video with a VQGAN, we can autoregressively predict the next token using our current language model. More specifically, using our current context of 2 million tokens, we cou…
-
is there a (planned or existing) way to have variable IP Adapter weights for videos (e.g. with AnimateDiff)?
that means setting different values for different frames, as both scaling and masking cur…
-
Hi, thanks for your great work!
I read the code and found emu3 only use 1d rope for both visual and language content. I wonder if 1d rope will bring some problems to image and video generation res…