Text-to-Video
Diffusers
Safetensors
I2VGenXLPipeline
image-to-video

can't reproduce the same result as space demo

#13
by fenglinsen - opened

hello,
I build the environment, and use the diffusers, safetensors model to infer a same picture with the same prompt, but the result is much bad than the space demo, I don't know why , is this because I use fp16 in my own project?

Sign up or log in to comment