Suzhen Wang

> It is real cool work! However I see it generates 256X256 video. > > Is that possible to generate 512X512 video? > > Thanks. The shared pre-trained models are...

> That's a bit odd, it should have `config.json`( The full model config) in the directory. Are you using a checkpoint for it? model = Qwen2_5_VLForConditionalGeneration.from_pretrained(model_base, low_cpu_mem_usage=True, config= **kwargs) idn...