Getting Very Bad Quality outputs

[Deadsec69]

I was able to run the code exactly Somehow getting bad quality outputs and are not matching with the repo results These are some outputs I got for Text-conditional image-to-video generation Using the exactly same image mentioned in the results table

Prompt given: An image of a realistic cloud that spells “SORA”. https://github.com/lichao-sun/Mora/assets/27695803/c891546e-cdec-4801-806e-dac59f0e23d5

Prompt given: Monster Illustration in the flat design style of a diverse family of monsters. The group includes a furry brown monster, a sleek black monster with antennas, a spotted green monster, and a tiny polka-dotted monster, all interacting in a playful environment.

https://github.com/lichao-sun/Mora/assets/27695803/fb9a0190-dbfe-4158-a895-2fc98a04efec

I am using stable-diffusion-v1-4 as mentioned in the code as well as OllamaLLM

I guess some model or some weights have been misssing😅