After my successful experiments with RunwayML's animation capabilities, I decided to test the same prompts with Sora. While Sora has generated buzz in the AI community, my results show that it still has significant room for improvement compared to RunwayML's offerings.

The animations below demonstrate that while Sora can generate video content, it struggles with maintaining consistency and quality throughout the sequences. The results often lack the polish and coherence seen in RunwayML's outputs.

More notably, Sora appears to have corporate-driven limitations that RunwayML doesn't. For instance, the Mickey Mouse prompt that works perfectly fine in RunwayML isn't even possible in the latest version of Sora. This seems less about technical capability and more about OpenAI's business relationships - likely a strategic decision to maintain good relations with Disney for potential future partnerships.

Here are the test prompts, processed through Sora (minus the Mickey Mouse animation which Sora refuses to generate):

Castle Animation

Neuschwanstein castle, lightning, pixar style, volumetric lighting, unreal engine, hyper realistic, hyper detailed, maximum details, photorealistic, 8k, rimlight

Family Scene Animation

Family on their laptops while sitting around a Christmas tree with presents underneath and looking worried because they have to finish up work, realistic, 4k

Messi Animation

Lionel messi wearing his Argentina uniform floating in the air with beams of light behind him posed like Jesus. Sunrise breaking behind him and a soft halo behind his head, in the style of a gothic stained glass window of a church, volumetric lighting, unreal engine, hyper realistic, hyper detailed, maximum details, photorealistic, 8k, rimlight, maximum details

Robot Portrait Animation

rusty robot with bow tie, portrait, 8k, ultra realism, chrome background