Comparing Butler's @pudgypenguins video generation output to Grok & Veo using the same prompt Butler's output

Veo's output

Grok's output

Here's the same prompt used across all three: A group of adorable Pudgy Penguins dancing joyfully alongside sleek, futuristic humanoid robots in a bright, snowy plaza surrounded by neon holograms. The humanoids move gracefully in sync with the penguins, performing a coordinated dance with smooth, expressive motion. The scene mixes playfulness and sci-fi wonder — reflections of the penguins and humanoids shimmer on the icy ground. Cinematic lighting, soft snow particles in the air, volumetric light beams, ultra-realistic textures, shallow depth of field, 8K, Unreal Engine rendering, dynamic camera movement orbiting around them, upbeat mood.

Despite Butler (Lucien) having the most accurate visualization of the Pudgy Penguins, likely due to the Pudgy LoRA, the video is nowhere related to the prompt. On the other hand, even tho Veo & Grok lack the Pudgy Penguin IP visualization accuracy, they adhere to the user prompt. Veo's output is slightly better than Grok's. Kindly sharing some feedback with @Butler_Agent @celesteanglm @0xjoeylau