This is an AI video generation comparison for text-to-video prompt:
The scene begins with a close-up of striking red high heels, sharp and polished, walking away on a fractured asphalt road. The camera remains low to the ground, fully focused on the legs as they walk with deliberate confidence. The camera steadily tracks the legs from behind, capturing their motion as they stride through a desolate, post-apocalyptic street.
Generated: February 1, 2025
Pika's Turbo mode deliveres coherent visuals with good promp adherence quickly but lacks some sharpness on the objects in focus.
Generated: February 16, 2025
Using deepbeepmeep HunyuanVideoGP forked from Tencent/HunyuanVideo
Generated: February 18, 2025
Mochi 1, generated in Genmo AI playground. "walking away" part got ignored.
Generated: February 28, 2025
1.3 billion Wan2.1
Shoes and shine. Bright red heels with a slick finish sharp shape and light bouncing off every step like they were polished just for this walk.
Legs in motion. She walks with purpose steady and smooth each step shows weight shifting knees and ankles moving like they should.
Ground play. The road’s all cracked and rough her heels land right in sync with the uneven ground little puffs of dust kick up behind her.
Camera angle. Shot from low and behind it sticks close to her feet.
Check out the results from Pika, Hunyuan Video, Mochi (Genmo AI), Wan by Alibaba for similar or identical prompts side-by-side. Note generation dates and comments about models used.