Timon Käch
Timon Käch
Yes I'm I think it's easy to create such pipeline: 1. generate image using good finetuned sd 1.5 2. use this as reference image for the image to video model...
Hey @mayank64ce, I'm sorry but I can't tell you this. I'm not that experienced with stable video etc..
How did you change the SD 1.5 model? Do I have to create the entire pipeline out of it? Please tell me how you did it. Thanks
Do you mean sound quality or speed? If sound quality, yes I was expecting better too.
Thanks @lonzi for the answer! Will try out these tips tomorrow.
Can you @lonzi kindly provide us your sampling parameters or add a note in the readme with recommended paramteres? Thank you so much!
I'm testing out bitsandbytes 4bit but I'm also very interested in GGUF @monatis @vikhyat
I'm experimenting with quants today. Will keep you guys updated.
I've tried to integrate this model with transformers but couldn't manage to correctly implement the image embeddings. Text was generating successfully even quantized. The model would actually be useful if...
It looks so cool. I really can't wait for the code. PS: Is the code in the huggingface space not enough to work with?