Fang-Yi Su
Fang-Yi Su
`CUDA_VISIBLE_DEVICES=0 python inference_realesrgan_video.py -i inputs/video/short.mp4 -n realesr-animevideov3 -s 3 --suffix outx3 --num_process_per_gpu 4 --extract_frame_first` I used the code to process a 27 secs video (with audio). The processed video length...
Hello, I'm really new to streamlit. I gotta to obtain the coordinate of mouse clicking on the image. Can I get the information from canvas?
Hi, thanks for the implementation first. Just installed the requirements and give it a try. I met this error as title after running some steps. `55 3.7432401180267334 [tensor([755., 361.]), tensor([502.,...
There's some quantization example [here](https://github.com/cauyxy/bilivideos/blob/master/qlora/quant_compare.ipynb) It showed that there is `bnb.functional.quantize_fp4(x)` But I didn't find it in documentations.
Hello, thanks for sharing this work! Need to figure it out something in CoDi. Is the environment encoder V in paper as `clap_encode_audio` like [this](https://github.com/microsoft/i-Code/blob/cba6421cb1ceb22d915cdfe3fdcbb8088b77122e/i-Code-V3/core/models/model_module_infer.py#L110C27-L110C44) ?
Hi Ziming, A few months ago, we discussed my toy examples and some experimental results with real-world data. I’ve made some progress since then, still using the original KAN model....
Hi, If I want to resume my interrupted training process, which checkpoint should I load?
Hi, I'm new to ComfyUI and thanks for the good extensions! I found this in setting panels, but there is nothing to choose. I've tried re-install and update everything. How...
Hello, thanks for sharing this awesome research work! May I ask if there's a possibility to provide a training script? Or could you offer some hints on how to quickly...